Meeting Select — AI Powerhouse · Day One Block 1 · Frame  01 / 12
← → navigate · T lab clock
Meeting Select · The Living Factory

AI Powerhouse

Hackathon Kickoff — day one of the track

One day. One real ticket from our backlog. You will run the whole lifecycle — Specify → Generate → Comprehend — with an agent doing the typing.

The rule of the day: short talks, long labs. If I speak for more than fifteen minutes, something has gone wrong.
The shape of the day

Five labs. Six short talks. One sandwich.

Timeboxes are hard; done-when beats done-everything. Whatever state your lab is in when time runs out, that's what we debrief.

Morning

09:30talkFrame — the sandwich, the day, the spotter's card
09:55talkDrive — the Claude Code driving lesson
10:05labLab 1 · First contact — calibrate on our own codebase
10:40talkDebrief — the agentic loop · coffee
10:55talkSpecify — prompting, grilling, checkable done
11:10labLab 2 · Plan & grill — your ticket becomes a plan
11:55talkDebrief — the seam
12:10breakLunch

Afternoon

13:00talkGenerate — let it run, when to step in
13:10labLab 3 · Build it — the agent types, you supervise
14:10breakDebrief + coffee — who intervened, and why
14:30talkComprehend — expectation-first review
14:40labLab 4 · Prove it, then review it — evidence, diff, cross-review
15:30labLab 5 · Teach the factory — CLAUDE.md, today's lessons kept
16:00labDemo circle — show the catch, not just the ship
16:40talkClose — the factory · the road ahead
Block 1 · Frame — the model

Introducing the AI sandwich.

Every piece of work is a sandwich. You are the bread on both ends; the AI is the filling — the only loop you follow today.

  • Specify — you say what you want and what the rules are. A clear spec means less guessing.
  • Generate — the agent does the work. It writes code, tests, and edits.
  • Comprehend — you read it back, ask questions, and decide. This is where quality is set.
  • Skip Comprehend and you did not save time. You just pushed the work to later.

Metaphor: Dan Shipper, from Every's podcast AI & I, with Kieran Klaassen. The Specify → Generate → Comprehend framing is this engagement's own adaptation.

What changes for you

Your time moves to the two ends.

Before
Specify
writing code
Review
→
Toward
Specify
code
Comprehend

You write less and less code over time. The time does not vanish — it moves to the two human ends.

!
Comprehension debt
Code that ships, but nobody understands. The cost hits the first time it breaks.
!
Orchestration ceiling
One reviewer behind many agents. Past your limit, quality quietly drops.
Block 3 / 6 · the front of the sandwich

SPECIFY

Agree the what before anything builds.

Vague in, vague out — judgment goes in here, while changing your mind is still cheap. Unclear requirements are this company's single biggest source of delay; this block is the antidote.

Block 2 · Drive — the driving lesson

Claude Code, in the terminal.

Your tool for the day: a session, your repo, and control over what it may do.

  • Start it in the repo root. Now it can see your real code.
  • Permissions: it asks before acting, until you choose to let it run.
  • Talk to it in plain language. Point at real files. No magic words.
  • Esc interrupts at any time. You are always the one in charge.
meetingselect — claude
Lab 2 · hands on45 min

Plan & grill

Your ticket becomes a plan so clear someone else could build it.

Make it interview youpaste the grill prompt; answer at least five rounds
Get the plan + done-when list3–5 checks that can pass or fail
Swap plans with your pairmark every spot where you'd have to guess
Fix the vague spotsuntil your pair signs off
You're done when
Your pair says: "I could build this without asking you anything"
Hold point: nobody builds before lunch. That urge you feel right now is what today is about.
Lab clock · 45:00 on the line
45:00
T start / pause  ·  R reset
⏸ Debrief — what you just watched

That was the agentic loop.

It read, it ran, it looked at the result, and it went again. That loop is the difference between an agent and a chatbot.

  • Each step is a tool call. The result decides the next step.
  • It acts — it doesn't just answer. That's what makes it wave 2.
  • The loop stops when the goal is met, or when it needs you.
↻
Prompt
Tool call
Result
Repeat
⏸ Intermezzo — taught when it happens

Someone just hit the dumb zone.

Long session, many files — and the answers went vague. The context window is nearly full. This is normal; now you know its name.

  • The agent's short-term memory has a hard limit. Old details fall off or blur.
  • The fix: compact the session, start fresh, or write the state to a file first.
  • Long runs are managed, not endured. This is half of what supervision means.
Context window62%
quality nominal
The model, at scale

The factory is many sandwiches at once.

Many agents can work at the same time. But only one person reviews. That is the slow part.

Agents spread out. Many tasks generate at the same time.
Human review is the one slow step. It sets how fast the factory really goes.
Run more agents than you can read and you do not go faster. You just approve without checking.
The road ahead

Today was the whole sandwich, fast.
The next sessions slow it down.

Each session takes one station you ran today and builds it properly — with homework on real tickets in between.

S1 — Planning & refining

The front of the sandwich, done right: codebase archaeology, codifying tacit knowledge, the grill, the seam.

S2 — Building the machine

Parallel agents, autonomous routines, self-reviewing pipelines, guardrails — the factory itself.

S3 — Reviewing code

Keeping your grip as volume rises: architectural review, agents in the browser, blocking the rubber stamp.

S4 — Orchestration & judgment

The capstone: your parallel ceiling, backpressure, and the judgment no agent replaces.

Block 6 · Compound & close

You ran the whole sandwich. On a real ticket.

Everyone drove an agent through Specify → Generate → Comprehend on our own code — and the lessons you wrote into CLAUDE.md are still here tomorrow. That loop, repeated, is the factory.

The harder parts — many agents at once, autonomous routines, real review at volume — come in the next sessions. We are not learning a tool. We are building a factory the team owns. Today was day one.

TIME
Hands off the keyboard — done-when beats done-everything.
press T to dismiss