← Guides · 日本語 · Português · 中文

Updated 2026-11-20

On this page
  1. The exemplar
  2. The anatomy of a working outcome prompt
  3. Patterns from the official template marketplace
  4. Multi-bot orgs: prompts that grant authority
  5. Anti-patterns
  6. Drafting yours — the three-line test
  7. Verify it
  8. Pitfalls
  9. Knowledge check
  10. Walkthrough — outcome vs task, side by side, on Devin CLI v3000.14 (swe-2-flash-medium)
  11. Sources

Bot outcome prompts, dissected

Goal: write outcome prompts the way the documented deployments actually did — ownership of an area, not a task list. Level: intermediate · Time: 20 min to draft, a week to calibrate

Every public bot deployment that produced big numbers started with a short prompt assigning an outcome. This guide collects the real ones and reverse-engineers why they work.

The exemplar

"your job is to product manage the android app"

The Android Bot's entire assignment. One sentence produced 44 days of self-directed work: the bot decomposed the outcome into tickets it wrote itself, ran a Devin session per ticket, and shipped 1,134 merged PRs (launch post). Note what the prompt does not contain: no ticket list, no acceptance criteria, no schedule. The outcome itself implies all of them.

The anatomy of a working outcome prompt

Element What it does Example
A role Tells the bot how to behave, not just what to produce "product manage", "own the QA of onboarding flows"
A bounded surface A scope the bot can fully see — an app, a check, a data source "the android app", "layout regressions", "30+ onboarding flows"
An implicit definition of done A state the bot can verify itself against "feature parity with iOS", "no layout-shift regressions", "every flow green"
Standing authority The bot decides when and what next — that's what makes it a bot, not a script "your job is to…", "keep…", "watch for…"

Patterns from the official template marketplace

The 16 marketplace templates all follow the same grammar. Reusable formulations, generalized:

Ownership of a domain — "Find bugs, improvements, performance and refactoring work in a named product area; open one small PR at a time with proof it works." (Software Factory)

Ownership of a check — "Every 3 hours, build production main, simulate first/repeat/deferred visits, and file fixes with before/after videos for any regression you introduce—or find." (Layout Bot pattern)

Ownership of a lifecycle stage — "Take a ticket or an ask to a tested PR and through review." (Product Engineer)

Ownership of a cadence — "Weekly: remove dead code, one safe PR per round." (Code Reaper) — scheduled outcomes are stated as a rhythm, not a trigger.

Ownership of team metabolism — "Watch the channels, post updates, hand work to the right teammate, follow up until done." (Chief of Staff)

Ownership of hygiene — "Old flags, stale deps, CVEs — turned into small safe PRs." (Code Health Engineer)

Multi-bot orgs: prompts that grant authority

In fleets (SuperJennyStack, Frankie, tigsbot) the chief bot's prompt contains the routing contract: which bot owns which surface, and when to escalate upward instead of sideways. The human's real prompt is the roll-up spec: "bring me every open decision in one thread." See Guide 4 for the full org chart.

Anti-patterns

Drafting yours — the three-line test

A good outcome prompt answers, in order:

  1. What is yours? — the surface
  2. What does good look like? — the verifiable state
  3. What do you do about it? — the standing behavior

If a stranger couldn't check line 2's truth from outside, tighten it.

Verify it

Pitfalls

Knowledge check

  1. Why does "own the Android app" work better than "fix Android bugs"? (Ownership implies standing judgment — the Bot decides which bugs matter, not just whether to fix.)
  2. What's wrong with "make the CI fast"? (Not verifiable from outside — no threshold. "CI under 8 minutes" is.)
  3. Which of the three questions does "text me if tests fail" answer? (Standing behavior — it says what the Bot does about the state, nothing about the surface or the goal.)

Walkthrough — outcome vs task, side by side, on Devin CLI v3000.14 (swe-2-flash-medium)

Bots need a Max or Teams plan — but the prompt mechanics this guide teaches are surface-agnostic, so we recorded them on the free SWE-2 CLI tier. Same repo (orders.py with a deliberately thin 2-test suite), two identical checkouts, one prompt each:

Video (64 s, silent): baseline → task run → +6 lines → outcome run → self-decomposed coverage map → +37 lines.

The outcome run's report — 13 tests green, branch coverage enumerated by the agent

1. The task-shaped prompt on the baseline — 2 tests, named items only 1. Task-shaped prompt on the baseline — the agent is given a shopping list

2. Task run finished — exactly the 2 named tests, 4 green, "Nothing committed", then it idles 2. Task run: exactly the listed items, then it stops — a session, not an owner

3. The outcome-shaped prompt on an identical copy — role, surface, verifiable state, no item list 3. Outcome-shaped prompt: role + bounded surface + a definition of good — no checklist

4. The diff the outcome prompt produced — the agent enumerated every branch itself 4. +39 lines written without being told which tests — it named every branch on its own

5. The report is a state, not a checklist — "All 13 tests pass. Branch coverage: …" 5. It verifies against the stated definition of good and reports the coverage map

6. Side by side — task prompt: +6 lines; outcome prompt: +37 lines. Same model, same repo 6. Same model, same repo, different prompt shape: +6 vs +37 — and 4 vs 13 tests

Sources