Notable verbatim quotes

Line numbers refer to approximate position in transcript.md. Quotes preserve speech-to-text artifacts; bracketed annotations are clarifications, not edits.

On the core thesis

• [Section 1, ~lines 12–14] "The distinction here is between write the code. And building the machine that writes the code." — tag: thesis
• [Section 4, ~line 88] "This is not for us documentation. This is actually executable constraints." — tag: claude-md, executable-constraints
• [Section 12, ~line 330] "intent is the new architecture (...) context is the new code." — tag: intent, architecture

On stopping writing code

• [Section 1, ~line 3] "Line of code am I written since? I don't know, maybe end of end of January." — tag: no-code
• [Section 4, ~line 92] "we violent[ly] handwriting code (...) we can't send a pull request. When it's written by us. It'll be (...) literally just deleted as a pull request. It's not a guideline. It's not a preference. It is literally how we do things." — tag: no-prs, policy
• [Section 4, ~line 98] "Agents write every single line of code." — tag: no-code

On vibes don't scale

• [Section 4, ~line 82] "If you're via coda [vibe-coding] and there's no idea of what you're trying to do, can you give it a single line prompt? You're going to get somewhere. Is it going to be the most secure, the most useful tool over time? Probably not." — tag: vibes-dont-scale

On supply-chain integrity / no external PRs

• [Section 5, ~line 115] "it's not because I don't trust your code. I absolutely do not. But what I'm trying to do is I am trying to maintain the integrity of our supply chain." — tag: supply-chain, oss
• [Section 5, ~line 122] "AI will generate really plausible wealth [well-]format test and code at scale. And if we have to author and look at that code, we're never going to be able to distinguish what is a supply chain attack. Versus what is actually a change in the code itself." — tag: supply-chain

On the adversarial reviewer

• [Section 6, ~line 148] "a very grumby [grumpy] adversarial review that says you don't trust any code in the world. You have to prove that it's secure. You have to prove that it has no injection attacks. You have to prove that it's architecturally complete as to the guidelines." — tag: adversarial-review

On the five-loop human-arbiter cap

• [Section 6, ~line 154] "We get to five. Okay. We'll only ever allow five loops. Before it steps [stops]. And it says, hey, we can't agree in this. You have to be the arbiter of what's going on." — tag: human-in-the-loop

On CLAUDE.md

• [Section 7, ~line 178] "It is an executable contract. It is literally the center of gravity in our entire system." — tag: claude-md
• [Section 7, ~line 184] "TypeScript. It must be strict. No pennies [anys] because any's aren't the devil. They must be named exports. No defaults. It has the agplyright [AGPL header] on the top of every file. No fire forget promises." — tag: claude-md, constraints
• [Section 7, ~line 192] "if you hit a non-obvious problem during a session that's going to trip up future users, future cloud sessions, future agent sessions, record it and propose an update." — tag: claude-md, self-improving

On UAT as source of truth

• [Section 9, ~line 263] "tests are the source of Truth. Don't change the test. Always feel the right [fix the code] if it's a regression." — tag: uat, tests
• [Section 8, ~line 218] "The user is your best user. Your best QA of your entire system." — tag: uat, quality

On the numbers

• [Section 9, ~lines 268–276] "in the last 30 days (...) 295 issues have been opened (...) I ship[ped] 217 of them. I closed 81 (...) median time to triage (...) is 4.6 hours. And from triage the whole way through the ship (...) is 1.6 hours." — tag: metrics
• [Section 9, ~line 280] "there's five people the company I work at. Each of us has a claw code. Max Pro, which is 200. And then we spend about 1500 to two thousand dollars per month. On the whole CI review process." — tag: cost, metrics

On getting started

• [Section 11, ~line 308] "turn your conventions into constraints." — tag: getting-started
• [Section 11, ~line 315] "Encode that one thing. That only one person in the organization (...) knows (...). Run that loop once. End to end. Figure out where it breaks. And that's the next constraint that you have to go." — tag: getting-started, incremental

On the bottleneck (Q&A)

• [Section 14, ~line 378] "Our bottleneck is my thinking. Thinking through what is important for our users." — tag: bottleneck, qa

On juniors

• [Section 17, ~line 445] "a junior has become really important. (...) juniors really can learn architecture constraints of the system. They don't need to care about the syntax of the code anymore." — tag: juniors, org-design

On honeymoon

• [Section 18, ~line 468] "This is the honeymoon period. Absolutely. 100. Am I going to be like this in four months time? I probably have redesigned the system four times in the [interim]." — tag: honesty, caveats