The AI Software Development Lifecycle

Two weeks, four times a year, built around one question: how do you hand real work to an agent and trust what comes back?

From prompting to loops that finish the work

You can already get a good answer out of a model. That is not what is slowing you down. What slows you down is everything around the answer: deciding what to hand over, bounding it so it cannot wander, and knowing the result is right without reading every line yourself.

That judgement is the job now, and it is the part no release note covers. Anthropic and OpenAI ship features. Nobody ships the decision about when a loop is worth building, and when you should just write the code.

Here is the shape of it. Generating code got roughly free. Checking it did not. So the constraint moved: every hour you save on writing arrives at the same queue, which is you, reading. Teams that have felt this describe it the same way each time. Throughput up, review load up more, and nobody quite able to say whether the codebase got better or just bigger.

You do not fix that with a faster model. You fix it by moving the checking off your desk, which means specifying so the work can be checked, constraining so most of it never needs to be, and building something that can say wrong without you in the room.

So this is not a tour of a tool. The Course does that, and it does it thoroughly. This is two weeks on the part that has no documentation.

How it runs

Live hours are a submitted-question session rather than an open mic, which is what lets the room stay uncapped.

  • Four times a year

    One cohort per quarter, and each one runs across two weeks. Not a rolling course you join whenever.

  • Six to ten live hours

    Live sessions spread across the run, plus lessons you work through on your own time between them.

  • Questions are submitted and voted on

    You post questions in advance and upvote other people's. The most wanted ones get answered in the live hours.

  • No seat cap

    Nobody is turned away to keep the room small. The submitted-question format is what makes an uncapped room work.

What the two weeks cover

Six stages, in the order the work moves through them. Each one hands to the next, and the last one hands back to the first. That loop is the lifecycle the programme is named after, and it is the thing most agentic coding material skips straight past on its way to the tips.

  • 01

    Specify

    How much spec to write, and when. A throwaway prototype and a payments change do not want the same document, and most of the pain comes from writing one when you needed the other. Then attacking your own spec with a second agent before a line is written, because the cheapest bug to fix is the one still in a sentence.

  • 02

    Constrain

    Where to put the guard rails so the agent cannot reach the bad outcome, rather than catching it afterwards. Pushing your standing instructions down into linters, types and static analysis, where a machine enforces them every run, instead of leaving them in prose the agent may or may not read this time.

  • 03

    Build in loops

    The loop that runs the work: what starts it, what stops it, and what it does when a step fails. Back-pressure, so a failure reaches the thing that caused it instead of piling up for you at the end. And the honest version of when a loop is worth building at all, and when you should just write the code.

  • 04

    Verify

    Verification is the bottleneck, and everything else you speed up runs into it. Splitting the work so one part produces and another part checks. Telling a real check from a rubber stamp. Fuzzing and property tests against agent output, which is where generated code fails differently from code you wrote.

  • 05

    Review

    Review at agent scale, when the volume of change is no longer something a person can read end to end. Separating the thing that proposes from the thing that judges, and why a model that agrees with you is worth less than one that does not.

  • 06

    Govern

    The autonomy dial: how much you hand over, on what, and who is accountable when it ships. Decision surfaces, so the choices that need a human reach one and the rest do not. This is the stage almost nobody teaches, and it is the one that decides whether any of the five above survive contact with a team.

And two things that run through all six

  • Context engineering

    Deciding what the agent needs to know, getting it there, and keeping it across sessions. Including the failure almost everyone inflicts on themselves: several competing sources of truth in one context, which the model averages into something that follows none of them.

  • Multi-agent orchestration

    More than one agent on one problem: how the work is split, how results come back, and the cases where a second agent makes the answer worse rather than better.

Plus that quarter’s delta: what actually changed in the tools since the last cohort, and which of it is worth your attention. That part is different every time, which is why it is not in the grid above.

Who this is for

  • This is for you if

    • You already ship real work with an agent, most weeks
    • Your review queue grew faster than your output did
    • You are the person who decides how your team uses these tools, or you are about to be
    • You want the reasoning, not a list of settings that will be wrong in a quarter
  • This is not for you if

    • You are still learning to drive the tool itself
    • You want to be told the one correct setup rather than how to choose one
    • You want a recording to work through alone. Half of this is the room, and the questions other people bring to it
    • You want the complete reference to work through. The class is that, and it is a good one

Before you join the list

How is this different from the self-paced class?

The class teaches the tools and the techniques, thoroughly, and it is maintained as those tools change. This is two weeks on the judgement around them: what to hand over, how to bound it, and how to know the result is right. That part has no documentation, and it is worth working through with other people rather than alone, which is why it runs as a cohort rather than sitting in a catalogue.

Do I need the class first?

No, but you do need to already be shipping with an agent. This starts from the assumption that you can drive the tool and are stuck on everything around it. If you are not there yet, start with the class instead. It builds the foundation this assumes you have.

What if I cannot make the live hours?

The live hours are recorded, and the lessons are yours to work through whenever suits you. The one thing you cannot catch up on is asking your own question, which is why questions are submitted in advance rather than shouted into a call: you can post yours, and upvote someone else's, without being in the room.

What does joining the waitlist commit me to?

Nothing. It is an email address. The date and the price are announced to the waitlist before anywhere else, so the list is where you find out first, not where you get pushed.