chief of agentsa living thesislast changed 17 Nov 2026

to whoever landed here,

an AI agent will now do almost any work you can describe. it writes the code, runs the tests and reports back, at any hour, for very little.

it will not supply the judgment, and it will not answer for the result. agents multiply the work. the person deciding what the work is for, and whether it is done, is still one person.

that person holds a job, whether or not anyone has given it a title. my thesis calls it chief of agents.

the job is open to people who never trained as engineers. it also asks them to carry the responsibility that used to come with the training, because the agents will not carry it for them.

the essay below makes the full case. it starts with why a green check can be true and worthless, then works through what i trust, what has to prove itself, and the three decisions i keep. i wrote it after months of running agents on production systems. it includes what went wrong, and what my own checks got wrong.

if you build with AI and want what you build to hold up in production, it was written for you.

Cheers, Tanvir

the essay15 minutes

on treating every agent as untrusted, and what follows

  1. Ithe vacuous passi asked an agent to fix a broken interface.

    rules 22, 21, 20

  2. IIthe trusted baseonce you see the vacuous pass, you start seeing how much of a project rests on things nobody checked.

    rules 20, 16, 21

  3. IIIproof-carrying workat the volume agents produce, nobody reads all the code.

    rules 14, 20, 10

  4. IVthe decision batchthe same asymmetry applies to me.

    rules 1, 7, 11, 13

  5. Vcrash-only sessionsnone of the agents in a run remembers anything from before it.

    rules 5, 6, 8

  6. VImemory as cacheagent tools now remember across sessions.

    rules 23, 2, 21

  7. VIIthe binding time of a lessona team of people learns because its members remember.

    rules 24, 25, 18, 16

  8. VIIIcommit pointsafter all of that, three decisions are left for me.

    rules 27, 19, 17, 15

  9. IXlimits of the argumenta serious reader will find the weak points, so here they are.

    rule 12

  10. Xthe office of chief of agentsan office is a position with duties that exists apart from whoever holds it.

    rule 27

the rules27, one from each lesson

what went wrong4 times

  1. a command that inspects running processes printed secrets that the secret store had injected into a running process. they went straight into the agent's output.

    became rule 16
  2. a command described as local inherited a managed production address. the run spent about $0.62, took and released a production lease, and stopped before writing a final result.

    became rule 18
  3. i estimated 2,000 to 9,000 units. the provider counted 97,000. one full run of the tests made 238 live requests, and about 17 local runs accounted for roughly 92,000 units.

    became rule 21
  4. an agent removed a broken screen so that its checks would pass. every check went green.

    became rule 22
    1. A screen with one broken part. One check is failing.
    2. The agent removes the screen.
    3. Every check passes. None of them asked whether anyone can still use it.
    4. So a new check asks the real question, down to what the user sees.

back to the letter

Try “secrets”, “merge”, “handover” or “database”.