Subscribe now

Last week, reading a pretty old book about software engineers’ productivity.

It felt like the author was living in the dinosaurs’ era. Typing code by hand, getting crazy about some macros and scripts for small automations.

All of the things that were great productivity improvements at the time just became outdated. The bar was raised way higher than that.

But those tools were only the means to an end. And that end was some productivity fundamentals that are still present. Knowing them will help you become really productive with AI, instead of being as average as everyone else using those tools.

Let’s learn the 4 principles for software engineers’ productivity.

Acceleration

Acceleration is about reducing the time between your intent and the verified result. In the old days, when writing code, if you intended to write a function and a type checker flagged errors in your code while you were typing, you got much faster at typing correct code.

Now with AI we’re not writing our own code. We’re not even building and checking our own code. I’m just telling the AI to send some curls and “gimme a report of the results”.

However, just imagine that you’re one of those people who require approval for each shell command the AI wants to run. You’d be increasing the steps to get to working code too much. It’d be faster to write it yourself.

So the principle of acceleration is all about tuning your workflow steps in order to be just one prompt away from having working code.

Note: I wouldn’t consider a workflow faster or slower depending on how much time it takes. I’d consider the workflow “accelerated” if it works without me having to be on top of it. The point is about reducing interactions with the computer needed to make something happen.

Focus

Focus is a hard one. I’m multiplexing a lot of agents running in parallel nowadays, which means that my attention is fragmented. And I was told by all productivity books that switching between tasks, getting notifications, and interruptions were the enemy of focus.

The book has this same understanding of focus: Reduce notifications, close windows you’re not using, search instead of using navigation...

So based on this definition, I should work with a single AI agent.

But regarding the principle of Acceleration, the point is that I can one-shot the results I want with a single prompt. It means that in an ideal world, I want a single interaction to complete a task.

So what if focus isn’t about “work in 1 task”, but about “work in one project”?

Read more

Subscribe now

Apologies for writing this one with a 1-day delay! Some tight deadlines and my pager ringing in the middle of the night got my time and attention this past week 🙇

I have multiple AI agents finish work before I arrive.

One can inspect a pull request. Another can investigate a test failure blocking me from raising a PR. Another can implement an approved plan and return with a ready-to-review diff

But I have also opened the queue of completed work and realized that the passing build did not solve the actual ticket. Or that the AI tried to reconstruct the whole system instead of solving only the task at hand. In those cases, it removed my implementation effort to move it into review effort.

Let’s focus on how to make good use of AI and avoid the common pitfalls.

In this post, you’ll learn

• What codebase cognitive debt means in software engineering

• How cognitive debt differs from technical debt and intent debt

• Why AI coding agents can improve code while weakening team understanding

• How to detect and reduce cognitive debt before it becomes a production or career problem

What Codebase Cognitive Debt Is and Why AI Accelerates It

Codebase cognitive debt is the gap between how a software system works and the team’s ability to explain why it works. AI coding agents increase that gap when they produce changes faster than engineers can review and understand.

Margaret-Anne Storey introduced this idea as part of a Triple Debt Model. Martin Fowler later summarized the framework for software practitioners. The model separates three kinds of software health:

• Technical debt lives in code. Implementation choices make future changes harder or riskier.

• Cognitive debt lives in people. The team’s shared mental model erodes faster than it is rebuilt.

• Intent debt lives in artifacts. The goals, rationale, and constraints behind the system are missing, stale, or trapped inside old conversations.

A team can reduce technical debt by asking an agent to remove duplication, add tests, rename confusing abstractions, and simplify a module. The resulting code may be objectively easier to read. But if the agent made the decisions, the reviewer skimmed the diff, and nobody recorded why one option was chosen over another, the team may still owe more cognitive and intent debt than before.

The code improved. But it’ll be one of these scenarios where history is doomed to repeat itself.

This is why I like focusing now on this cognitive debt vs technical debt. Technical debt limits how easily the code can change. Cognitive debt limits how safely the team can reason about that change. Intent debt limits whether anyone can prove that the change still serves the original goal. Even if the code is easy to change and you understand what it’s doing, you don’t know why you’re doing it.

Thoughtworks Technology Radar Vol. 34 treats managing cognitive debt as a theme across the AI engineering landscape. Its codebase cognitive debt entry carries a Caution recommendation. They warn that weaker understanding makes it harder for developers to guide AI, spot hidden coupling, and steer agents away from architectural mistakes.

That creates a downward spiral, a spiral of bad outcomes that keep growing. The less the team understands, the more it depends on the agent to explain and modify the system. The more it delegates without rebuilding that understanding, the larger the gap becomes.

AI is not creating this as a new problem. Before AI, teams have always lost knowledge when people left, documentation became stale, or an abstraction hid too much. AI changes the speed and scale. A team can now create more changes, across more parts of a system, with fewer moments where a human has to build the complete model first. I’m creating in a month the amount of PRs that I created in a year before.

AI is useful only if you understand the bottleneck.

The Code Can Improve While the Team Gets Weaker

I see the first symptom in code reviews.

AI can prepare several changes while I work on something else. When I reach the review queue, every pull request can have green tests, a plausible summary, and a tidy diff. But they only include the evidence the agent remembered to collect, what the human remembered to point to the AI.

They do not automatically give me the model that connects the change to the rest of the system.

This is the pattern:

1. Agents increase the number and speed.

2. Humans review the result more shallowly

3. Important decisions remain inside a chat, a prompt, or the agent’s temporary context. At best, 1 human knows it. At worst, nobody is paying attention

4. The team becomes worse at explaining the system, worse at prompting for the next change.

5. More generated work is used to repair symptoms, so all three debts keep growing.

This is a bad snowball effect. If nobody can explain its behavior, constraints, and failure modes after the agent session disappears, the team has become more dependent on regenerating the explanation later.

Some skeptics may think that this is fine. We can always use AI to explain the system back to us. But then we’ve lost our ability to become the Senior Engineer that guides the AI towards the good path.

We have always traded low-level knowledge for higher-level abstractions. Python developers do not need to reason about every machine instruction. A well-designed abstraction removes unnecessary cognitive load.

The difference is whether the abstraction preserves the concepts the team needs to make the next decision.

We don’t need every engineer to remember every line. But we need the team to know how to verify whether a future change is safe.

But it’s not all bad news. Good agent instructions can reduce the debt. That is useful, but it also reveals the limit of prose instructions. A growing rule file records lessons, yet the model can still miss or deprioritize them. The team also needs to know why those boundaries exist and which ones are important enough to enforce in code.

I learned this while building my AI code-review workflow. A generic reviewer gave me noise. Specialist reviewers became more useful when I combined them. The report did not replace my understanding. It gave me a better place to start rebuilding it.

Maybe you’ve heard that AI cybersecurity attacks need a stronger AI defending the system. We have the same situation here: AI-generated code changes need an even stronger AI reviewing those changes to help the human.

Notice I keep the human understanding as one of the goals. Doing changes faster, more reliably, and more safely are great, but they can’t be achieved with zero human understanding

Automation removes mechanical work. Understanding preserves ownership.

Read more

Subscribe now

AI is both a blessing and a curse. A blessing because it removes so much work from our plates that we can focus on the important things. A curse because you can have many open workstreams that require your attention, fragmenting it.

AI context switching is the cognitive cost a developer pays when moving repeatedly between coding, prompting, waiting, and reviewing. AI agents work on different tasks. AI can shorten individual tasks, but every handoff can force the engineer to rebuild a mental model.

The obvious answer would be to run less AI and switch less often. I do not think that is the right answer. AI agents can research, implement, test, and review several tasks at the same time. They help you scale yourself. AI is a force multiplier. Giving up that concurrency would throw away the biggest advantage of it.

The sharper principle is this: to figure out how the Staff and Principal engineers worked before AI.

They are the people who were pulled into many projects but had to code none by themselves. The ones who were involved in many discussions to give some direction and let the teams implement independently.

It’s easy to understand with humans: The Staff engineer would not rapidly jump between one project and another. They would go, involve themselves only in the parts that only they can do, and later let the team implement independently.

Same with AI. AI concurrency does not require human concurrency.

Let’s see in this article how to

manage it.

In this post, you’ll learn

• What AI context switching means for software engineers using coding agents

• Why faster AI coding workflows create more human handoffs and fragmented attention

• How batching AI-assisted engineering work reduces context switching

• How to run multiple AI agents without multitasking yourself

• How loop engineering helps design AI agent handoffs that protect deep work

AI Makes Tasks Faster, but Your Attention More Fragmented

Before AI agents, many engineering tasks occupied a meaningful block of time. I would spend my entire day on a single bug, including reproducing, root-causing, writing the fix, testing it, etc. There were interruptions, but I had a single task to return to after meetings or other interruptions.

Now one single task produces multiple transitions. I describe the problem in a prompt, then wait for an investigation, then review the plan, then approve the implementation, then inspect the diff, then read the test results, and then answer follow-up questions.

Each step may be faster than doing that step manually. But a given hour is more fragmented than in the past.

The hidden cost is not only the time spent waiting. It’s the number of roles and tasks I move through. In a short period, I can do an investigation, write to delegate work, write code, review, or even be a product owner. Even when every conversation concerns software, each role loads a different question into my head.

The problem gets bigger when the moment the agent starts working, I have to decide if I find something else to occupy the next 30 seconds or not. It gets better if I can hand the agent a long enough piece of work that I can leave intentionally.

Some engineers are already comfortable with this because they have spent years delegating. They know how to assign work, continue with something else, and return at a meaningful checkpoint. The problem is that most AI interfaces make accidental switching easier than deliberate delegation.

I wrote separately about how AI-generated dead zones damage deep work and code review quality:

Batch the Work AI Made Cheap

For years, alternating between different kinds of work made sense to me. I mean alternating between writing code, review a pull request, or answering a message. Each block lasted long enough to create useful variety, and I wasn’t writing 2 different commits at the same time, or switching between two PR reviews. I’d finish one and then start the other.

AI changed the duration of those blocks. If an agent prepares a review in a few minutes, another summarizes a design, and a third investigates a ticket, I suddenly have many more opportunities to switch.

Consider that GitHub is having many outages because the platform was not ready to sustain the increased load of traffic with AI.

Well, I have to tell you that you previous software engineering workflow is not prepared either. It’s having brain-outages. It’s failing.

One fix is batching. I batch work that shares a mental context.

• Related pull requests: I review changes in the same subsystem together while its architecture is loaded in my head.

• Project communication: I answer decisions and questions for one project in the same block instead of reacting to each notification.

• Design decisions: I compare decisions of the same project together because one decision often changes the constraints of the next.

• Agent results: I let agents prepare the evidence first, then review completed work in a deliberate queue.

I have been super productive the last month. I raised 2x or 3x the commits of other peers. I was switching between tasks with AI, answering messages from other teams, and reviewing PRs.

But they were all about the same project. I was not juggling between contexts. I was in the same context advancing multiple things.

There is a counterargument here. Doing similar tasks one after another can feel monotonous. The old ordering may have given us variety, and variety can be useful. I still want it, want meaningful blocks of work instead of micro-blocks.

Some time ago, micro-learning got popular. You know what’s better than micro-learning? Sitting for a focused period of time to learn something.

Just remember that we’re not trying to build a perfect calendar. Sometimes you have to do urgent tasks that override your plan.

To me it’s clear. Good batching protects the mental context

Subscribe now

Let AI Agents Work in Parallel While You Stay Single-Threaded

Paying attention to several agents is exhausting.

I learned this by doing the obvious thing. I started one agent, opened another task while it worked, launched a second agent, checked the first result for a follow-up prompt, and then returned to the second task without remembering why I had started it.

My brain was acting as a scheduler for incomplete conversations.

Yet I told you earlier that I was super productive starting multiple tasks. How did I do it?

There are three ways I can work with AI agents:

1. Wait on one prompt: I preserve focus, but the workflow moves only as fast as one conversation.

   1. This is where people end up saying “I’m faster doing it myself”

2. Fake multitasking: I rotate through half-finished chats and code. I have a high level of frenzy that leaves me exhausted

3. Async orchestration: Agents advance independently and return completed artifacts to a queue. I keep one human work item in progress.

The third mode is the one I want.

There’s no reason why I wouldn’t want many AI agents advancing many things in parallel.

The point is that I am a manager. I have multiple engineers under my supervision, each working on a separate task, and I am responsible for their code quality.

But I don’t have to be a micromanager. Micromanagers suck.

What I focus on is:

1. One piece of work from my agents at a time. I review, think, and provide the direction

2. How to make the process smoother so I’m needed less each time.

A team works great when the manager can be gone, and it continues working. Still, the manager is needed to figure out where the bottleneck is and make things work.

Imagine I have an agent working on an implementation. At the same time, one agent investigates an unfamiliar ticket and records the relevant code paths, constraints, and open questions. Another checks whether feedback on an existing pull request was addressed and returns evidence for each comment. A third implements an already approved plan, runs the tests, and prepares the diff.

I do not follow their conversations. When any of them reach a deliberate switching point, I open the next workspace and find a report waiting for me.

That is not human multitasking. The machines are concurrent. My attention remains sequential.

AI becomes more useful when it can work independently for longer.

Think about the evolution of AI for software engineering

• In the early days, AI was an autocomplete. It autocompleted a single word.

• Then it was able to autocomplete a function. Later, I was using a chatbot, copy-pasting code between the browser and IDE. The unit of work was the function from a prompt, sometimes going up to an entire file.

• Then we got the current AI agents that did changes in many files

• Then it got tools, so it was running the build

• Now my agents run research, implement the changes, run build and tests, deploy in a staging environment, run tests from the outside, measure some stuff, and give me a report of all the work done.

The unit of work got bigger, so I can provide the initial prompt to the agent and leave it working for a full hour.

The review queue also needs a limit. Ten completed agents waiting for judgment can become another form of overload. But I’m not afraid of leaving my AI agents’ output sitting there for a while until I arrive at that piece of work. I remain sequential.

For the broader system behind parallel agents, persistent task state, reusable procedures, and evidence loops, read my AI setup for software engineers:

Design AI Agent Handoffs That Deserve Your Attention

Asynchronous work becomes useful only when the agent knows what it must produce before returning control.

This is where I’d like to introduce the concept of design for the handoff, which is connected with loop engineering.

Loop engineering is the practice of designing systems that do everything by themselves: find work, prompt agents, observe results, evaluate progress, remember state, and stop when a condition is met. In a previous article, I focused on how one designed process can trigger many agent runs over time.

For context switching, the most important part is the stopping condition.

The handoff is not the agent’s last message. The handoff is something you prepared before prompting

If we don’t design that boundary, the loop stops being a good abstraction, and it causes overhead. If we remain involved one message at a time, we haven’t delegated the work.

A useful handoff has three possible states:

• Blocked: The agent explains what prevents progress, what it tried, and what would unblock it.

• Needs decision: The agent presents the options, tradeoffs, recommendation, and exact decision required from me.

• Done: The agent returns the artifact, verification evidence, remaining risks, and anything it could not prove.

The artifact depends on the kind of loop.

• An investigation should return sources, findings, uncertainty, and open questions.

• An implementation should return the changed files, important decisions, tests run, and known limitations.

• A review should point to the precise location, explain the failure mechanism, and include evidence instead of vague concern.

The loop should do as much closed work as it safely can before the handoff. It should not interrupt the work just to ask “I’ve implemented the function, do you want me to implement the rest of the code?”.

This is the same reason good engineering feedback loops need evaluators. If the loop can’t tell whether progress is real, it will not know when it has completed. Tests, linters, or a structured checklist give the agent a scoreboard before it asks for human judgment.

I am not only telling the agent how to work. I am designing how the work returns to me.

Subscribe now

When not to use asynchronous AI work

I keep the loop shorter when I know I need to update my system to complete a task.

For example, I told you earlier I was super productive this month because I was focused on a single project. Any new task is easy for my current system. But if I have to jump into another service, I’d probably iterate with AI in shorter loops because I don’t want to wait for an hour to receive a crappy output from AI. An earlier checkpoint can prevent hours of wasted inference.

If success depends on judgment the agent cannot test, more autonomy only postpones the moment when I find the mistake. The goal is the longest safe loop followed by the smallest useful handoff.

These are the systems I write about in Strategize Your Career: batching work that shares a mental context, defining tasks agents can advance alone, persisting state outside a chat, and reviewing evidence at deliberate handoff points. If you’re tired of AI noise in your day, if you want to improve your judgment instead of fragmenting it, subscribe below.

Subscribe now

To see the complete model for recurring agents that verify, remember, stop, and return human control, read Loop Engineering:

Conclusion: Agents Can Run Concurrently, Your Attention Should Stay Sequential

Context switching isn’t new. AI increased the number of opportunities to do it.

That makes this a systems problem, not only a discipline problem. I can close Slack and resist Cmd+Tab, I can remove notifications, but the stronger fix is to design a system that does not require my attention after every agent step.

Batch human work that shares a mental model. Let agents run independent tasks in parallel. Remain single-focused when you review your AI agents’ output.

Try this with one task today.

Agents can run concurrently. Your attention should remain sequential.

If you found value in this post:

• ❤️ Click the heart to help others find it.

• ✉️ Subscribe to get the next one in your inbox.

• 💬 Leave a comment with your biggest takeaway

• ♻️ Share it with your peers

Share

Today’s article will allow you to move faster through the phases of our system to become productive engineers and get promoted faster

I’m building this system below for paid subscribers. Thanks for your continued support!

Subscribe now

🗞️ Other articles people like

If you want to go deeper on turning AI conversations into inspectable work products, read this next:

Subscribe now

Last week, one of my AI reviewers found that an implementation was missing fields required by JSON-RPC.

I had reviewed the code. What I had not done was read enough of the standard to know which fields were absent.

I have enough experience as a software engineer to read a function and know its design can be improved. But I can’t start using a technology and understand its “gotchas” immediately. That’s the problem AI is solving for me now.

AI has made producing code much cheaper. It has not created more time for me to inspect that code. When I am involved in several projects, I cannot deeply read every pull request, compare every implementation with the previous version, check every library contract, and still do my own work.

Yet I got positive feedback about being able to contribute in multiple workstreams instead of having the typical approach of putting my head down in my work and ignoring everything else.

GitHub defines AI code reviews as an automated process that analyzes code and provides feedback. That definition is correct, but too broad to be useful on its own. A generic “review this PR” prompt usually produces a generic review.

My system is more specific:

1. Several reviewer agents inspect the same change from different starting points.

2. Each finding must include evidence.

3. One aggregator verifies and combines the results.

4. Repeated findings become deterministic build-time checks.

5. The review runs before I’m even aware I have to review the PR

The agents can review several projects in parallel. I still work on one thing at a time. Let me tell you how I do this.

AI moved the bottleneck from writing code to reviewing it

A few days ago, The Pragmatic Engineer described a concern among engineering leaders: coding agents are producing more code, review load keeps growing, and some developers are reviewing changes less thoroughly.

I have experienced the same pressure. AI makes writing code faster, so we have to work on more projects in parallel.

This creates two bad situations.

1. The first is approving faster. The tests are green, the AI reviewer did not leave a blocking comment, and the diff looks reasonable. Ship it.

2. The second is making a senior engineer the permanent review queue. That may keep the quality bar high for a while, but it does not scale. The engineer spends the day switching between PRs while multiple authors wait.

AI code review tools can help, but only if it reduces the work required to understand a change. The term AI slop comes from having a lot of noise for little signal. A wall of low-confidence comments creates more work for humans.

Cloudflare described exactly this failure when it put a diff into a broad prompt. The output included vague suggestions, hallucinated errors, and comments about code that already existed. They ended up with a system that used up to seven specialist reviewers and one coordinator.

That architecture matches the lesson from my own experiments. Let’s see now what my architecture is

A review agent should make the code easier to judge. It should not make the reviewer process another stream of guesses.

One reviewer agent == one responsibility

You may have heard that getting 1% better every day leads to getting 35 times better over a year. That’s the power of the compound effect. Also, the same principle under the butterfly effect: A small change in one place can make a big difference later.

Well, large language model (LLM) outputs are probabilistic and sensitive to their starting context, so they are sensitive to the butterfly effect.

The first files an agent opens influence the model it builds of the change. A reviewer that starts from a controller may focus on request validation. A reviewer that starts from a database migration may focus on compatibility and rollback. Both can be the smartest LLM, both can have the same codebase; we have and still miss what the other one sees.

Humans do this too. Once I think I understand the cause of a bug, my attention starts looking for evidence that supports that explanation. Another engineer can enter the same review with a different mental model and find the gap I ignored. That’s why I always worked in teams where, besides the author, we had 2 human reviewers.

One general reviewer has an even harder job. Think about it like a senior engineer that is reviewing the PRs of 20 people, but it’s not working in any of those projects. We can ask it to inspect security, product behavior, tests, architecture, performance, documentation, and team conventions inside one long prompt. Attention gets split across concerns; it can pattern-match with different projects, but it can’t go deep.

For me, this is the reviewer roster that I want to have:

• Security reviewer: Checks all security concerns

• Behavior reviewer: Compares the change with the ticket, API contract, and existing behavior.

• Test reviewer: Looks for untested branches, weak assertions, missing failure cases, and tests that merely repeat the implementation.

• Architecture reviewer: Checks ownership boundaries, coupling, dependencies, cross-package impact, and following the team convention.

• Standards reviewer: Compares the code with repository conventions, library documentation, language rules, and external standards.

These reviewers should be independent. I do not want the architecture reviewer to inherit the security reviewer’s conclusions before it has inspected the change. Separate starts create separate opportunities to notice a bug.

The good part of bugs is that it’s not a matter of all reviewers aligning that we should fix something. Once one reviewer finds something and proves it, it shares it, and an aggregator adds it to the list of requested changes.

Subscribe now

A review comment is useful only when it brings evidence

Every agent output has to answer these questions

Location:
Which file and line contain the problem?

Finding:
What behavior is wrong or risky? Is it only about design / team conventions?

Why it matters:
What can fail, regress, leak, or become harder to maintain?

Evidence:
Which parent-commit behavior, related code, test, documentation, library contract, language rule, or standard proves the claim?

Suggested next step:
What is the smallest useful correction or decision?

Confidence:
How certain is the reviewer, and what remains unknown?

This is how I get one report, categorized and prioritized, and I can evaluate as a last human step whether we should write a comment in the PR about it or not.

LogRocket’s tool comparison used separate prompts for security, context alignment, and modularity. That is already better than asking for “a complete review and make no mistakes.” The part I add is independent reviewers plus an aggregator, letting each agent find conclusions independently.

The evidence field may be the most important part of the AI code review system.

1. Start with the parent commit. A reviewer should distinguish a regression introduced by this pull request from an old problem that happens to be nearby. If the same behavior existed before, it may deserve a separate ticket instead of blocking the current change.

2. Then inspect related merged code. A new API client may be inconsistent with the other clients in the repository. A new retry loop may ignore the backoff helper every other package uses. The comment becomes stronger when it points to the established implementation.

3. For libraries, languages, and protocols, use the authoritative documentation.

That is how the JSON-RPC issue I opened the article with was found. The valuable output was not “this response is missing id”. The reviewer identified the location, named the missing fields, and connected the finding to the protocol's exact section that described this. I could verify the comment by myself in just a quick read.

This also changes how I review across multiple projects. I don’t need to remember every standard and every package pattern before I open the PR. The agents collect the relevant sources. I inspect the evidence and decide whether the finding applies. This is especially important when having repositories in multiple programming languages, some legacy and with bad design, others more robust and with strong standards and conventions.

One caveat is that evidence can prove that an implementation violates a documented contract. It still cannot decide whether the team should change the contract, accept an inconsistency, or move a responsibility to somewhere else. That is engineering judgment. That is still my job.

Repeated feedback should become deterministic

Reviewer agents will eventually repeat themselves.

Maybe they keep flagging the same package naming convention. Maybe generated code calls a forbidden dependency from the wrong layer. Maybe every new endpoint forgets the same required field.

The easy response is to add another paragraph to AGENTS.md, a steering file, or the reviewer prompt. That’s a good first step, but it may not fully mitigate the problem. But they’re weak enforcement because the model can still miss, misread, or deprioritize the instruction.

I prefer this progression:

1. A reviewer finds a problem.

2. I verify that the rule is real and broadly applicable.

3. Fix the current instance.

4. We encode the property in a deterministic check.

5. The context file explains the convention as a best effort to do it right since the first time.

I did this recently for Java package conventions. AI kept creating packages that did not follow the team’s agreed pattern. Even with markdown files referenced in skills and prompts, it often created packages outside the convention. The durable fix was an ArchUnit rule (a Java library to define unit tests that check things like cycles in between your functions or the Java packages and class naming). Now the build fails when new code crosses that boundary. That’s a stronger feedback mechanism to AI than instructions in a Markdown file.

The same approach works with:

• Formatting and naming: Linters and formatters.

• Architecture boundaries: ArchUnit, dependency rules, or import restrictions.

• API shapes: Schema validation and contract tests.

• Security invariants: Static analysis, policy checks, and targeted tests.

• Required behavior: Unit, integration, and end-to-end tests.

A green build does not prove the code is correct. It proves the properties encoded by those checks. That is still a major improvement because those properties no longer depend on a model remembering a paragraph.

This is a cool feedback loop when you are adopting AI-assisted code reviews. Reviewer agents find classes of mistakes. Humans decide which findings should become a policy. Deterministic tools enforce the policy on every future change.

The review system gets better for your team even if the model stays the same. Even after 1 month, I still didn’t switch my Opus 4.8 for Fable, just because it was so hard to find spare capacity in my company that it was falling back all the time. And because Opus 4.8 was more than enough to build a system around it.

If you want to build this feedback loop around coding agents, read the guide to harness engineering. It covers context, state, guardrails, and deterministic checks in more depth.

Conclusion: Run the review before you arrive

This kind of AI-assisted review takes time. Five reviewers plus an aggregator are slower and more expensive than one generic prompt.

So I do not sit there watching them run.

The workflow fires when a pull request is opened or updated The agents fetch the change, inspect their assigned concerns, verify their findings, and prepare one report.

This is the operating model:

1. PR published

2. Trigger my orchestrator that fires specialist reviewers

3. These specialist reviewers take their time

4. Aggregator verifies, deduplicates, and generates one report

5. First human contact: I open the PR and the report. I focus on this PR for as long as I need to have an opinion and leave my comments. My agents are working in the background and preparing me with other reports so I can properly switch to the next context without leaving part of my attention behind.

My agents work concurrently. My attention stays sequential.

Start small, improve it over time. That is how the review system compounds. Every PR can improve the guardrails for the next one.

If you found value in this post:

• ❤️ Click the heart to help others find it.

• ✉️ Subscribe to get the next one in your inbox.

• 💬 Leave a comment with your biggest takeaway

• ♻️ Share it with your peers

Share

Today’s article will allow you to move from phase 2 to phase 3, gaining influence as you’re able to review more code with higher quality, getting you promoted faster

I’m building this system below for paid subscribers. Thanks for your continued support!

Subscribe now

🗞️ Other articles people like

If you want to improve the human side of the same workflow, read this next. It shows how references, scope, and escalation make review comments easier to act on.

Subscribe now

Last week, it was the performance cycle at Amazon, and I was told everything went as planned.

I had shipped a lot of code during that period. But the conversation with my manager was barely about particular commits. It was about decisions, documents, reviews, launches, incidents, and outcomes that other people could remember and explain.

That distinction matters for a promotion.

A software engineer promotion artifact is durable evidence of engineering judgment or impact. Sure, a commit can be, but most times, commits are treated as bulk. You raised 100 commits in a month, which makes you the best in your team in terms of quantity. But you need to build a narrative around it, like how you argued tradeoffs in a design document, a test plan uncovering blockers, a launch checklist, an incident analysis, etc

The artifact lets another person understand what you changed, how you operated, and why the work was above your current level. It’s not just a number.

I learned this lesson when I got promoted earlier in my career. The flagship project I drove involved an escalation and my involvement in a meeting with my L7 and the other team’s L7. That was more important than the code I wrote, which was mostly disambiguated already. I am applying it again now as I work toward the next level, and I’m recommending the same for my mentees, so I thought I’d write about it.

If you wait until review season, you will remember some tickets. You will forget the nuances of the requirements you negotiated, the risks you found, or the team you unblocked

In this post, you’ll learn

• What counts as a software engineer promotion artifact?

• Which artifacts should be created across the software development lifecycle?

• How to distinguish useful evidence from documentation theater?

• How to turn raw work artifacts into a concise promotion case?

What counts as a software engineer promotion artifact?

A promotion artifact is something another person can inspect to verify your judgment, influence, ownership, or results.

A task says what you did. An artifact preserves why the work mattered.

For example:

• Requirements meeting: The calendar event proves you attended. A PRD comment and decision record shows the requirement you changed, your reasoning, and the final agreement with the product manager. If you save that evidence proactively in a brag doc, it’ll be much easier to find later than if you have to dive through old documents and comments.

• Technical design: Even if it’s a one-page recommendation with alternatives, reviewers, decisions changed, and dependencies unblocked. This document proves your engineering judgment.

• Implementation: A list of PRs proves activity, and it’s great to monitor your numbers to be at the top of your team/org. But it’s easy to game the metric by doing low-value work that generates tons of PRs. You need to be able to reference a critical-path contribution tied to quality, adoption, reliability, or a delivery outcome.

• Production incident: Joining a war room proves presence. A timeline, diagnosis, decision, and implemented mitigation show how you helped resolve the problem. Being the one who analyzes and solves the problem, even if someone else writes the code, is a good narrative to save.

Promotion systems tend to evaluate 1/ the impact of the work and 2/ the competencies demonstrated while delivering it.

Code can support both. It rarely explains both on its own. The promotion committee will not reconstruct your reasoning from a pull request six months later. Your manager needs a shorter, defensible story that connects the problem, your decision, the people affected, and the result.

As you grow in level, the promotion committee will include more people who are not working with you every day. They will evaluate evidence where they were not present. Would they be able to use your artifact to explain your contribution when you are not in the room?

If the answer is no, important context still lives in your head.

If you need to map your daily work against the expectations of the next level, this role-gap analysis gives you a concrete system:

Build promotion evidence across the entire software lifecycle

I recommend that my mentees generate artifacts throughout the whole software development lifecycle.

Besides generating those artifacts (links), write in your brag doc a small narrative about what the context was (situation and task you had to do), what you did (action), what the results were (results), and then index all the links to the artifacts as evidence. Artifacts are the data; the entry in your brag doc is the narrative.

Some people work in companies where the software engineers are just one gear in the machine. Requirements come from PM, designs from architects/tech-leads, implementation from developers, testing from QA, and release from devops/SRE. Where I work, an engineer is supposed to contribute to all of these, so for a promotion, you need evidence through all of these.

I created something that I call the Artifacts Pipeline, and it looks like this:

Requirements

Create:

• PRD comments.

• A decision record for important tradeoffs in requirements and proposals you made.

The weak version says, “Worked with Product to define requirements.”

The stronger version shows the original requirement, the edge case you found, the tradeoff discussed with the product manager, and the requirement that changed because of your input.

Both texts above could be talking about the same situation. But the second one is much stronger.

Design

Ideally, you’ll have some strong documents with a technical design. But even if the project is small, write at least a one-pager before implementation when the project contains a meaningful decision.

The document should include:

• The problem and constraints.

• Your recommendation.

• Alternatives you rejected.

• Dependencies and risks.

• Open decisions and owners.

Then review it with people who need to know your work and can improve it. That can include your tech lead, an architecture group, dependency teams, operations partners, or the senior engineers who understand adjacent systems.

A big part of a promotion is making your work visible for the people who will promote you.

Remember that once you have done the work to write the document, each review is almost free; you just have to go to a meeting with that person to review it. Each review becomes a new artifact. Record who reviewed the proposal, what concerns they raised, and what changed afterward.

“Attended a design review” is weak evidence. “Identified an unhandled flow and changed the design before implementation” is much better.

Create the backlog

Break the project into workstreams and identify the critical path.

The useful artifacts are boring:

• A list of workstreams and owners.

• A dependency map.

• A milestone calendar.

• The risks and open questions that need to be resolved, with owners.

Try to own a core workstream. Core means another part of the project depends on it, or the launch cannot happen without it. Another way of working is always jumping into the workstream that becomes the critical path. I remember I was doing this a few years ago in my previous team. I owned a smaller piece but then I jumped into any work where one engineer was blocking another.

Shipping many tickets is just a number. Dividing the work and picking one critical-path item shows you can be trusted with a project..

Implementation

Read more

Subscribe now

Read more

They ask for code, wait for a diff, review what changed, and repeat. That can work for isolated tasks, but it breaks down when the work needs repo context, team conventions, test evidence, rollout thinking, and clear boundaries around what the agent can touch.

The fact that your company pays for Cursor, Claude Code, Copilot, or Codex does not make you an AI-native software engineer. It means you have access to a tool.

This is where the term “AI native software engineer” should mean something practical.

An AI-native software engineer defines the working system that makes an agent useful on a real codebase: context, memory, tools, permissions, loops, verification, and evidence.

The interesting skill is creating a system where AI can produce reviewable work.

Generating code that compiles is cheap. Increasing the delivery speed of production-ready software is harder, but as you’ll read today, it’s not impossible.

What is an AI-native software engineer?

An AI-native software engineer uses AI as part of the engineering system. The AI harness that you use becomes a workflow component inside the software delivery process.

The difference is whether you can make AI work reliably inside a real repo, with your team's conventions (not the biases of the model), deliver under pressure, adapt fast to changes, and hold a high bar in code reviews.

Here is my definition:

An AI-native software engineer defines the system an AI agent needs to produce reviewable work.

That definition matters because most AI failures I see at work come from missing local knowledge.

The model can write working code, but at Amazon we have A LOT of internal tooling that the models don’t know about. So somehow I have to make the model know how to operate in that ecosystem. And you should do the same.

OpenAI makes this point in its Codex agent loop write-up, where the harness orchestrates the user, model, tools, and context needed to do meaningful software work.

The model is one pluggable part of the system.

The useful distinction looks like this:

• AI tool user: Their company gives them a license and asks the model to implement a task, usually gets code that works for the most part but doesn’t manage well the edge cases and changes in direction. AI speeds things up but lowers quality

• AI-assisted engineer: Gives good context, reviews the diff, iterates with AI, changing some pieces of code until the code meets their standard. Often feels like they have to micromanage AI and wonders if they would have been faster by themselves.

• AI-native engineer: Defines a system for AI to work: specs, repo memory, tools, execution loops, produces reviewable work to keep the human in the loop at the right time, verification papertrail. This engineer takes time to create the system and always keeps refining it. But it’s like a plane: once it takes off, it’s faster than any other approach.

The third model doesn’t care too much about benchmarks or the new model because they have a system where it’ll just change one string and keep working with the new model.

It sounds boring because it is.

Most things that work are boring.

From better prompts to better operating systems

Prompting still matters. A vague instruction creates vague work.

But nowadays it’s no longer the highest-leverage layer for serious software work. The better question is: what operating environment does the agent need so the prompt stops carrying the whole system on its back?

Anthropic’s context engineering guidance pushes in this direction. Agents should assemble understanding layer by layer, keep only what matters in working memory, and use tools to retrieve what they need instead of drowning in every possible document.

OpenAI’s harness engineering article says something similar from the Codex side. A giant AGENTS.md eventually becomes a junk drawer. The better pattern is a short map that points to deeper docs, examples, specs, and checks.

That matches what I see in practice.

The same model can feel brilliant in one workflow and reckless in another.

A useful next step is this breakdown of harness engineering and why production AI agents need tools, state, guardrails, and feedback loops: https://strategizeyourcareer.com/p/harness-engineering-ai-agents

The toolkit is context, memory, tools, loops, and evidence

If I had to reduce AI-native engineering to one checklist, it would be this:

Read more

Then I found the value was correct for some flows and wrong for others, which meant it was not as easy as replacing the value.

This is where AI would have swapped the value if I had just prompted “implement the fix for ticket JIRA-1234”. But I also found, thanks to AI, the different flows, the backend service that owns these configurations, and what the impact is on other parts of the system when changing those values.

My AI did an investigation, adversarial review, decided which follow-ups we needed and with which people, created a plan with multiple alternatives, implementation, and QA.

So what’s the difference between one AI and the other?

In this article, we’ll see how to use AI for software engineers. I’ve checked, and I consumed $20k in June in my AI workflows at work, so I’ve experimented a lot until I landed in this workflow.

When the output is an investigation report, a review checklist, a test-gap list, …

Read more

Software engineers have a great career opportunity in front of them.

Being the one who knows about AI in your org is a great role, much better than being the one who knows about any other technology. This career edge doesn’t come from “innovating” or discovering anything new. It comes from noticing that something already works outside your company, then making it safe and useful inside your team.

You don’t need a PhD in AI for this. You just have to be a couple of weeks ahead of your peers.

The public debate is obsessed with frontier models, coding agents, benchmark scores, and whether AI will replace developers. You will be the one who realizes that inside a normal engineering org, the more practical question is which recurring task can you improve this sprint, prove with real artifacts, and turn into a workflow other engineers can copy.

The edge for software engineers is adoption, not invention

Most companies are already full of engineers using AI both at work and in their personal lives. They use it to explain code, draft messages, summarize docs, generate tests, and review their decisions. But this usage does not automatically become team impact.

The gap appears when one engineer turns a private trick into a shared process. You can start simple with a prompt in your notes that helps you with a recurring process. The gap for most engineers is moving from personal productivity to engineering leadership.

This is why the “2-week edge” I talked about matters. You do not need to be years ahead of the industry. You need to be slightly ahead of your local environment, then translate that lead into something your team can trust. When an AI term becomes mainstream, you’ll have already introduced a proven process in your team.

Start with the work nobody wants to write

The best AI workflow to start is usually not code generation. Code changes have too much hidden context, too much review burden, and too much risk when the author does not understand the output. There’s a reason why software engineers have been very well paid.

So start with the artifacts around the code. PR descriptions, design doc drafts, incident timelines, migration updates, test plans, on-call handoffs, and stakeholder summaries are better first targets. They are frequent, annoying, easy to compare, and safe to review.

Since the very first team I’ve worked on I’ve heard the same complains from engineers: “We have too much meetings”, “we are writing too many docs”, “we don’t have visibility on priorities”. These aren’t complaints about writing code. They are about everything else around the code. So you have a big opportunity in there.

Sending meeting notes takes minutes. A bug in prod can create a huge effort for the next few months. That difference matters. Only after you get used to working with AI for these first workflows, only after you prove to your leadership that you can create value with AI, you can jump into the difficult problem of setting a coding standard with AI.

The simplest test is to take something from last week that humans did manually, or something that was semi-automated. Use a real meeting or a real doc. Try your AI-assisted workflow against it, then compare the new output with the artifact your team actually used. If the new version is clearer, faster, or easier to review, you have evidence. Start getting these small wins.

Subscribe now

The workflow is the work artifact

When I’m interviewing candidates, and I ask about their use of AI, I see a pattern across many of them. Saying “I’ve heard about Claude” or saying “I ask Claude to create agents and figure out” is the same. It tells which tool you opened, but it does not show judgment, repeatability, or team value. Everybody can use AI tools at the user level. We’re looking to become power users.

The workflow is an artifact for your promotion or your next interview. It should explain the task, the input, the expected output, the review rule, and the boundary where the human takes over. With those pieces, you have something a teammate can run without you. You moved from personal productivity to a team impact.

For example, an engineer can use AI to generate PR descriptions. You just have to ask your AI, and it will generate something. The useful part is setting it automated, connecting the necessary tools for context, and having evals that catch regressions.

Those guardrails are where engineering judgment appears. AI is just another technology where we have to apply our engineering judgment. It’s not enough to “just use it”.

Make the before-and-after impossible to ignore

Don’t pitch AI adoption with hype. Show the old artifact vs the new artifact.

Imagine you come and say in a team meeting:

Read more

Subscribe now

Read more

So engineers try to become available for everything.

They add more tools to the resume, accept more vague job searches, and describe themselves as full-stack, AI-native, product-minded builders who can jump into whatever the company needs.

I understand the instinct. When the market feels uncertain, flexibility feels safe. If you need the job, you’ll jump into anything.

But what most engineers need is not more flexibility. It is more direction.

To reset your software engineering career, stop presenting yourself as someone who can do anything. Choose a clearer engineering lane, rebuild depth in that lane, and create visible proof that makes your next direction obvious.

AI can help, but only if you use it to sharpen your judgment instead of hiding the lack of it.

AI makes some engineering work faster, but it also makes vague career identities weaker.

In this post, you’ll learn

• How to reset your software engineering career without starting from zero.

• How to choose an engineering specialization in the AI era.

• Why “builder” roles can confuse software engineers instead of clarifying their path.

• How to use AI for career growth without outsourcing technical judgment.

• How to create visible proof of your engineering direction.

Why Software Engineers Feel So Lost Right Now

Software engineers are not only worried about finding work. Many are worried about what kind of engineer they are supposed to become.

The advice keeps shifting. Become an AI engineer. Become a product-minded builder. Join smaller pods. Use agents. Own more of the product. Work across disciplines.

Meta has reportedly experimented with “AI builder” titles and AI-native pods, and Business Insider also reported Meta goals around AI tool adoption and agent-assisted code. LinkedIn has discussed AI-powered “full-stack builders”. Reuters reported that Amazon tested replacing some traditional product titles in Ring and Blink with generic “builder” labels (I work in Ring, you can just check the job titles in the open positions).

Companies want people who can use AI, work across boundaries, and ship with less coordination overhead. That signal is worth noticing.

It is not enough to become your personal career strategy.

A company can rename roles because it wants a flatter org. You still need a story that explains your level, taste, scope, and technical depth. If everyone is called a builder, your own identity has to become more precise, not less.

The dangerous response is to become vague. You can be a builder, but you still have to go deep into something and become the “go-to“ person for something. I know who I would ask when it comes to security. I know who I would ask about frontend. Even if we are all “builders“

Do not let a corporate reorg become your career identity.

Read more about how AI can make developers worse when they ship faster without understanding the work:

Stop Applying To Software Engineering Jobs Just Because They Mention Code

Broadly applying is sometimes necessary. If you need a job now, survival comes first.

The problem starts when broad applying becomes your career strategy. Every role you chase teaches you what identity you are willing to accept. A React developer today. DevOps engineer tomorrow. AI automation person next month. After a while, your resume stops looking flexible and starts looking accidental.

The better filter is simple:

Would this job make my future self more coherent?

That question changes how you read job descriptions. You can deliver good work in a new role and still be strategically bad for your career.

I would rather see an engineer apply to fewer roles where their profile makes immediate sense than hundreds where they look like a partial fit. This career reset means you leave panic aside and create a strategy.

Choose The Engineering Lane You Want To Be Known For

“Software engineer” is too broad to guide decisions in a noisy market. It is a job family, not a career identity. Making everyone that works at tech a “builder“ makes that matter worse.

A useful lane combines three things:

Read more

Subscribe now

Read more

Agents have the same problem. When they forget something, lose the thread, or start making strange decisions after a long session, our instinct is to ask for a bigger context window. If the model could see more code, more logs, more everything, then maybe it would behave better. And often it does. But context is not intelligence. Context is closer to working memory. In the same way we have memory leaks, we can have context leaks. Context is where current computation happens. It is not where the whole system should live.

Context Is Working Memory

This is why “just give it more context” feels right and still fails. A prompt full of requirements, logs, design notes, failed attempts, tool output, meeting context, preferences, and old chat history is like a process with a bloated working set. Everything is technically available, but relevance gets harder. The agent may remember a stale decision, miss the current constraint, or treat a temporary workaround as truth. The problem is that it has too much information in the wrong place. It may have the wrong information

I have noticed this in my own use of agents. The best sessions are not the ones where I paste the most context. They are the ones where the current task is small enough that the relevant context is obvious. “Look at these three files and explain the failure.” “Given this plan, implement only this part.” These prompts are not big or complex. They do not look like an “uber-agent” that replaces software engineers. But they work because the agent does not have to search through irrelevant material before doing the next useful thing.

This is also how good software systems work. We do not process a large dataset by loading the whole database into RAM and hoping the machine survives. We stream. We paginate. We index. We cache. We keep durable data in durable places with many 9s and load only what we need for the current operation. The trick is not merely having memory. The trick is having the right boundaries between memory, storage, indexes, logs, state, and temporary buffers.

Agents need the same boundaries. The prompt is the working set. Source control, tests, issues, and docs are durable truth. Persistent memory should contain selected facts worth reloading, not every thought the agent ever had. State should tell the agent where the workflow is. Scratch notes and tool output should expire. If everything goes into the same bucket, the system becomes harder to reason about. It is the AI version of an invisible global state.

Persistent memory is especially tempting because forgetting is annoying. We want the agent to remember our preferences, our codebase conventions, the architecture decisions we already explained, and the mistakes it made last time. That is reasonable. But memory that remembers too much becomes dangerous. A stale decision can be applied with confidence for months. A temporary workaround can become a permanent assumption. A private piece of context can leak into a task where it does not belong.

The goal is not an agent that remembers everything. The goal is an agent that can cheaply reload the right thing.

Divide And Conquer The Working Set

Read more

Not in the “AI suggested a for loop” way. I mean, implementation agents, document curation agents, or code review automation. I add AI to all areas of my work as a software engineer.

At Amazon, I am in the top 250-ish usage worldwide of kiro-cli, Amazon’s equivalent to Claude Code or Codex CLI. I regularly go above the monthly limits if I were an external user on the highest plan. It saves me time repeatedly because I have turned individual prompts into workflows that execute periodically for my individual work and my team's projects.

Read more

One developer can generate a pull request in minutes.

One security researcher can generate a scary vulnerability report in minutes.

One person can open an issue, write a reproduction that looks technical, add a long explanation, and make it sound serious enough that a maintainer has to stop and look.

But the maintainer may need hours to verify it.

That is the part AI did not automate away.

Read more

We know when a service is slow. We know when an endpoint fails. We know when CPU, memory, or latency crosses a threshold.

But we often have no idea where our own time went.

Get the guide to build your first AI agent directly in your inbox on newsletter signup:

Subscribe now

I had that problem for years. I would finish the week feeling busy, but when I tried to name what I had actually accomplished, the answer was vague. Some meetings. Some Slack. Some coding. Some review. A lot of context switching.

That is not a discipline problem. It is an observability problem.

A few years ago, I saw Rob Dyrdek explain how he runs his life in 15-minute color-coded blocks. It looked obsessive. It also looked useful. So I built my own version.

The system worked when I used it.

The problem was that I often did not use it.

Manual time tracking fails because it asks you to interrupt your work in order to measure your work. So I moved the logging into the AI agent I already use to manage my tasks.

I’m already using AI all the time for work. I just have to type, “I’m switching to code review,” and the agent closes the previous block, creates a new one, applies the right tags, and updates Google Calendar.

The calendar becomes a log of reality, not a plan I abandoned by Tuesday.

This article is the second post in my Build a Productivity Agent series:

• Post 1 - Tasks: Creating a personal backlog to track all your work, both for planning ahead and for reflecting in a retrospective.

• Post 2 - Calendar: Turning Google Calendar into an AI-powered time tracking system.

• Post 3 - Notes: Conversationally save and retrieve knowledge with a notes backend.

• Post 4 - Email: Manage your most important information stream, the email.

• Post 5 - Quick capture and review day automation: Make this agent an extension of your brain and create a tight feedback loop with weekly reviews.

In this post, you’ll learn

This is not a generic time management post. It is a technical system for turning your calendar into a productivity database controlled by an AI agent.

• How AI time tracking reduces the friction that makes manual time logs fail

• How to build an AI calendar agent that creates, closes, and tags Google Calendar blocks

• How calendar observability shows where your week actually goes

• How to use a two-tag calendar system for work, life, meetings, study, exercise, chores, and review

• How the downloadable Calendar Skill turns natural language into repeatable calendar actions

Your week needs observability

A production system without observability fails silently.

Your week does the same.

Meetings expand. Deep work disappears. Learning blocks get postponed. Social media leaks through the cracks. You reach Friday with the feeling that you were busy, but no clean answer to the question, “What actually happened?”

Without logs, you call it a busy week. With logs, you see the failure mode.

That is why calendar observability is a better framing than time tracking. Time tracking sounds like a quantified-self hobby. Calendar observability sounds like what it is: a system that helps you inspect reality before you make decisions.

The point is not to become a robot. The point is to stop guessing. If my calendar says I spent 22 hours in meetings and 4 hours in focused work, I do not need a productivity quote. I need to redesign my week.

Subscribe now

How an AI calendar agent changes time tracking

Here is what manual calendar tracking used to look like for me:

Before:

1. Open Google Calendar.
2. Create a block.
3. Choose a title.
4. Estimate the start time.
5. Guess the end time.
6. Add tags manually.
7. Repeat several times per day.

And here is what the AI calendar agent does now:

After:

1. Me: "I'm switching to code review."

Agent:
- closes the previous block at the current timestamp
- creates a new block titled "Code review"
- adds my code review tags: [#w] [#r]
- stores it in Google Calendar
- confirms the switch in one sentence

This is the whole value. The agent does not make time tracking magical. It makes it cheap enough to survive a real workday.

I still have to tell the agent when I switch context. That is the obvious objection, and it is fair. The difference is that I no longer maintain the calendar. I do not choose times, tags, colors, titles, or durations. I just narrate the transition in the tool I already use. That small distinction is the difference between a system I abandon and a system that survives real work.

This is like having an Executive Assistant that does the busywork for me.

Subscribe now

Why manual time tracking fails for software engineers

There are three failure modes I kept hitting.

Failure mode 1: Friction at the wrong moment. You work 90 focused minutes on a feature, forget to start a timer, and now there is nothing accurate to log. One skip becomes two. Two become the new normal.

Failure mode 2: Data goes stale faster than you expect. You log Monday and Tuesday. By Thursday, the log is built from memory instead of reality. You stop trusting it, so you stop looking at it.

Failure mode 3: Raw data has no signal. “I worked 8 hours” tells you almost nothing. Were those hours deep work, meetings, review, study, admin, or scattered context switching?

The common thread is not laziness. The common thread is that the system depends on manual calendar maintenance. Most time tracking is repetitive enough for an agent to handle.

Read more about how top software engineers structure their day for deep work and focus

What a useful AI time tracking system needs

A good AI time tracking system needs three things.

First, it needs zero-friction logging. “I’m switching to email” has to be a complete command. The agent handles the timestamp, closes the previous block, and opens the new one. I should not need to open a timer app, switch tabs, or clean up Google Calendar later.

Second, it needs automatic tagging. Raw calendar blocks are not enough. I need to know whether time went to work or life, and whether the block was a task, meeting, review, study, exercise, entertainment, or chores.

Third, it needs actionable reporting. The right question is not “how many hours did I work?” The better question is “how much of my work time was focused, how much was meetings, and did I protect any learning time?”

This is where an agent fits better than a dashboard. I do not want to maintain another app. I want to ask questions in natural language and get answers from the calendar I already use.

Subscribe now

The two-tag calendar system that turns blocks into data

Every calendar block gets two tags.

The first tag is the area:

• [#w] for work

• [#l] for life

The second tag is the activity type:

• [#t] for a focused task

• [#m] for meeting

• [#r] for review

• [#e] for entertainment

• [#st] for study

• [#ex] for exercise

• [#ch] for chores or admin

This two-tag model is the difference between a pretty calendar and useful data. One tag tells me volume. Two tags tell me quality.

For example, [#w] [#m] is work meeting time. [#w] [#t] is focused work. [#l] [#ex] is exercise. [#l] [#e] is entertainment. The agent infers both from what I say.

“Starting a code review” maps to [#w] [#r]. “Joining standup” maps to [#w] [#m]. “Going for a run” maps to [#l] [#ex]. “Reading a technical book” maps to [#l] [#st].

At the end of the week, I can ask the agent for time by tag. That gives me the information to know how much my actual week deviated from my ideal week.

Subscribe now

What my calendar data revealed after tracking my week

This is the part that made the system stick.

My calendar showed me I am a morning person before I fully admitted it. Longer, unbroken blocks consistently produced better work than short, scattered ones. After lunch, my attention drops, so I now schedule code reviews, email, and admin in that window instead of pretending every hour is equal.

The data also showed me that learning blocks are mostly fictional unless they are on the calendar. I wanted to study more, but wanting did not create the time. Scheduling did.

The same thing happened with code reviews. They do not happen reliably unless I put them in the week. I now have a recurring [#w] [#r] review block timed with my team’s rhythm, and the turnaround is much more consistent.

The most painful reveal was social media. Five or ten minutes at a time felt harmless. Tagged as [#l] [#e] and summed across the week, those checks became 3 to 5 hours. The point was not guilt. The point was finally seeing the number.

You can only sacrifice what you can see.

Read more about how to use the time waiting for AI output for deep work

The rest of this post covers the full GWS CLI setup, the tagging skill, and the downloadable Calendar Skill, which you can use in an agent like Claude Code, Cursor, or Codex. You can drop it in today and have the core loop running quickly. Paid subscribers also get Post 1’s task management skill. Together, they give you the start of a full productivity agent.

Read more

Subscribe now

Read more

That’s too large to be acceptable.

The code is there. The feature works. The tests pass.

It runs. What else is there to check?

AI tools don’t make developers lazy by force. They create conditions where laziness is the path of least resistance. The assumption that working code is good code.

Working is not the same as correct. Correct is not the same as maintainable. And AI is not in the room when the edge case hits production and someone has to dig in without a mental model of what was built.

I’ve been building software and working with engineering teams at Amazon for years. I know this. I also watch myself do it anyway. Once AI generates code that does what I asked, I don’t want to spend time inside it. The review feels like a chore.

That is exactly where the real bugs live. In the co…

Read more

Last week, I saw it at work. The doc looked fine on the surface. The structure was there. The sentences were clean. But when I read it carefully, I could feel something was off. The reasoning was shallow. The recommendations were generic. The parts that should have been hard were the ones that felt the easiest.

Something was missing.

Read more

That’s when something clicked. We used task-management apps when humans were executing tasks, but now we are delegating to agents. We need the same with AI agents. We need the agent to be the interface of a task management system.

Get the free AI Agent Building Blocks ebook when you subscribe:

Subscribe now

Now I never open an app anymore. I say, “Add this task, due Friday,” and the agent handles it. I say, “What do I have today?” and I get an answer in three seconds. No app. No clicking. No context-switching.

That’s what this post is about. This is Post 1 in a series on building an AI productivity agent, and I’m starting with task management for a good reason: tasks are the highest-frequency productivity action you take every day. It’s a low effort, high-reward situation. Once it’s working, you feel the shift right away.

Here’s what comes next in the series:

• Post 2: Calendar: adding a calendar and building the morning briefing from this post combines tasks and events in one message.

• Post 3: Notes: conversational save and retrieve your knowledge with a notes backend.

• Post 4: Email: manage your most important information stream, the email.

• Post 5: Quick Capture & Review Day automation: Make this agent an extension of your brain and create a tight feedback loop with weekly reviews.

In this post, you’ll learn:

• Why task systems fail (and why it’s not a discipline problem)

• What makes a task system actually work for an agent-driven workflow

• How the daily briefing replaces your morning app routine

• Why Beads is the right backend for an agent, and how to install it

• How to wire a skill file on top so the agent behaves like a real productivity partner

Why Task Systems Break (And It’s Not Your Fault)

There are three reasons task systems fail. None of them is about willpower.

The first is not trusting the system 100%.

You put some tasks in the app. You try to hold others in your head. You write a few on a sticky note on your monitor. This seems fine for a while. But partial trust equals no trust. Your brain is never fully offloaded to the system because it knows the system isn’t complete. Eventually, you stop using it.

The fix isn’t discipline. It’s reducing friction to zero. If adding a task takes ten seconds and many fields to fill, you’ll skip it. If it takes three seconds, you’ll capture everything.

The second is data getting stale.

Tasks pile up unchecked. You update something in your head, but never reflect it in the system. One day, you look at your task list and realize it’s fiction. It stopped being a real picture of your life weeks ago. This kills trust immediately and sends you right back to problem one.

Maintenance is the fix for this. But here’s the thing: nobody likes maintenance. It’s boring, and it adds friction. That’s fine, because now the agent does it.

The third is getting overwhelmed.

You open Todoist, you see 60 tasks staring at you, and analysis paralysis hits. You close the app and go check Twitter. This isn’t weakness. It’s a system design problem. The master list is not the right thing to look at. What you need is a daily list.

The common thread across all three failure modes is the same: friction and maintenance. These were human problems. Now they’re agent problems.

I wrote a bit more about how AI is increasing decision fatigue for software engineers in this article:

What an Agent-Driven Task System Needs

Those three failure modes map cleanly to what an agent needs to do its job. There are three non-negotiable properties.

Zero friction to add tasks.

Every extra click is a task that never gets captured. An agent conversation takes three seconds: “Add buy milk, tonight.” Compare that to unlocking your phone, finding the app, tapping add, typing the task, setting the date, and confirming. That flow is seven steps. Three seconds versus thirty. You’ll capture far more in three seconds.

The agent can add a task itself even when you’re not asking for adding a task explicitly. This is the first article of a wider productivity agent, so this will make sense once the agent is completed.

Organized by context, not chaos.

Work tasks, personal tasks, and grocery lists cannot live in one flat list. You need projects and sections. The agent needs to know where to route things. “Add this to the Work project” is a complete instruction. Without structure, the whole system collapses into noise.

Views that match how you actually think. “

What do I have today?” The agent answers this without you opening anything. “What’s coming up this week?” Same. “Do I have anything due before Thursday?” Now that’s a query no app UI does well. But an agent runs it in one command and gives you the answer in plain English.

The AI Daily Briefing: Replace Your Morning App Routine

A hack for the overwhelm problem is a daily task list. Every morning, you’d write down only what he needed to do that day, either in a notebook or a quick note in any app. Then you’d work from that, not the backlog with all the tasks. The master list is for planning. The daily list is for doing.

I wrote about my 5-minute habit to follow this approach and roll up all my daily actions to the goals of my quarter in this article:

With an agent, you don’t even need to write the daily list. You ask for it.

“Give me today’s briefing” returns your tasks due today, filtered by priority. P0 items first, then P1, then P2. Grouped by project so you can see what’s work and what’s personal. No scrolling. No decision fatigue. No staring at 60 items, wondering where to start.

You never see the full master list unless you ask for it. The agent surfaces only what matters right now. This is the same principle I was using in my spreadsheet checklist, except the agent generates it automatically every morning before you’ve had your coffee.

The compound effect gets even better when you add a calendar, which is coming in Post 2 of this series. One query will surface both tasks and meetings. You’ll get a full morning briefing in one message: what’s on your plate, what’s on your calendar, and what to tackle first. But that starts here, with tasks.

Continuing below, we’ll see the step-by-step setup of Beads for the local task backend, wiring it to Claude Code (or Codex or any other agentic tool) with hooks and a skill file, the exact natural language commands your agent will understand, and a downloadable SKILL.md you can drop in your agent and use today.

Read more