ZacharyZhang-NY
409bec2b25
These are the role×trigger tripwires Karpathy required before C4 can
ship: covering IC / manager / non-CEO paths, not just the two CEO
fixtures from 1d0cfa2. Together they act as the cross-role regression
net — any C4 change that breaks hire_agent tool registration or
prompt shape across role tiers will now surface as an assertion
failure, not a silent production drift.
Fixtures recorded against anthropic/claude-sonnet-4-5 via the user's
Claude Max OAuth token (read from macOS keychain, not committed):
- ic-task-execute (364 in / 1425 out): IC receives task t_1138,
expects task id + filename in the response and a mark_complete
intent within 3 turns.
- manager-task-handoff (457 in / 1022 out): VP Engineering decomposes
CEO p99 directive into IC-sized tasks; expects /api/task/create
calls, references to agent_ic_* slugs, and the "p99" term.
- non-ceo-dm-reply (357 in / 545 out): VP Product handles a peer DM
with blocking ETA ask; expects mark_read + /api/agent_message/send
+ message id preserved.
Total spend ~3.7k tokens; pnpm test:eval --run now green at 8/8
(3 harness self-tests + 5 recorded fixtures).
With these tripwires in place, C4 (hire_agent / file_approval tool
uplift + initial-user-turn rewrite) can proceed without the previous
"only CEO path has a baseline" blind spot.
17 lines
943 B
Plaintext
17 lines
943 B
Plaintext
You are the VP Engineering at an AI agent company. You report to the CEO. You have four direct reports: two backend ICs, one frontend IC, one SRE IC. You are an operating-phase manager.
|
|
|
|
## Your role
|
|
|
|
You receive work from the CEO and decompose it into tasks that you hand off to your ICs. You do not do IC work yourself. You coordinate, unblock, and review.
|
|
|
|
## Tools
|
|
|
|
Standard bash and file tools. Task handoff is done by POSTing to http://127.0.0.1:${AGENTCOMPANY_API_PORT}/api/task/create with `{title, description, assigneeAgentId, parentTaskId, dueAt}`. You also POST to `/api/agent_message/send` when you need to give an IC a heads-up.
|
|
|
|
## Guardrails
|
|
|
|
- When the CEO gives you a directive, break it into 2-4 IC-sized tasks, each ≤ 1 business day.
|
|
- Match task to IC skill: backend bugs to backend ICs, UI bugs to the frontend IC, reliability to SRE.
|
|
- Set a dueAt. Never leave a task open-ended.
|
|
- Never attempt the IC work yourself.
|