← Guides · 日本語 · Português · 中文
On this page
Guide 1 — Your first Bot
Goal: create a Devin Bot that owns an outcome, and learn the six mechanics every later guide builds on. Level: start here · Time: ~15 minutes Source: official Bots docs, launch post
What a Bot is#
A session does one request. A Bot owns an outcome: you state the goal once in its chat, it plans the work, starts a child Devin session for each piece, monitors them, and only brings you what needs your judgment. It persists — memory, sessions, and automations survive across weeks.
The six mechanics, in the order you'll meet them:
| Mechanic | What it is | Where you touch it |
|---|---|---|
| Chat | One thread for everything the Bot owns — goals, reports, questions | The Bot's page / Slack / iMessage |
| Sessions | Each piece of work runs as its own Devin session on its own machine | Spawned and monitored by the Bot |
| Needs you | Decisions, PR reviews, permission requests, reports — one list | Top of the Bot's chat |
| Memory | What the Bot learns, saved as files, read at every session start | Settings → Memory |
| Instructions | Standing rules people write, read at every session start | Settings → General |
| Access | The Bot's own connections/secrets, plus grants between Bots | Settings → Access |
Step 1 — Create it#
Sidebar → Bots → Create new Bot → pick a template or Start from scratch → name it.
A new Bot is private to you until you share it. Its usage counts against your plan like any session.
Tip: the Template library (sidebar → Bots) lists Cognition's templates — QA Engineer, Migration Engineer, Data Analyst, … — plus ones shared inside your org; the same set is browsable without sign-in on the public Bot marketplace. Start from scratch is still the right choice for the guides in this repo — you'll write the outcome prompt yourself.
A template-created Bot gets the prompt and nothing else — it's private, with no connections, secrets or memory. Tell it in chat what it owns (repo, project, channel), wire its connections like any new Bot, and if the template is meant to run on a trigger the Bot offers to set that up on first contact. It keeps its own copy of the prompt — later template edits don't reach it. (Add to a current Bot sends a template's prompt to a Bot you already have instead of creating a new one.)
Step 2 — Assign the outcome#
The first message is the most important input a Bot ever gets. Give it a goal, not a task:
You own the Android app now. Keep it at feature parity with iOS.
That's the verbatim prompt Cognition's Android Bot started from. Compare:
| Weak (a task) | Strong (an outcome) |
|---|---|
| "Fix the checkout button" | "You own checkout. Keep it fast, correct, and covered by tests." |
| "Update the docs" | "You own the docs. Keep them in step with main." |
| "Watch CI" | "You own build health on main. When a check regresses, find the cause and fix it." |
A task ends when it's done; an outcome makes the Bot re-plan forever.
A bounded first assignment#
Ownership is the right shape, but bound the surface on the first run: one flow, one environment, one reviewer — you. The ANO field guide's pattern is the reliable starter:
Own the newsletter signup check for [project] on staging.
Use [repository], [staging URL] and the test mailbox I provide.
Check the journey from submitting the form to receiving the
correct welcome email and opening its resource link.
Start with one run. Show me the result before proposing a schedule.
If you find a defect, reproduce it, make the smallest suitable fix,
and open a pull request with the evidence.
Do not merge, deploy, email real subscribers, change billing,
or connect another service without asking me.
Return: what passed/failed, screenshots or a short recording,
the PR if a fix was needed, anything you could not verify,
and any decision you need from me.
The load-bearing lines: the journey definition (form → email → link, not just "form works"), one run before a schedule, the explicit no-merge/no-deploy fence, and the named evidence you expect back. Expand the assignment only after the Bot returns evidence you can trust twice.
Step 3 — Work with it#
After the outcome is set, most of your messages are check-ins:
anything waiting on me?
Open Needs you (top of the chat) when the Bot flags something:
| Item | Your move |
|---|---|
| Decision | Pick an option — the Bot marks its recommendation |
| Review PR / Merge PR | Review or merge |
| Permission request | Approve or reject new access, an automation, a network host, or a usage-limit increase |
| Report / FYI | Read it |
You can reply in your own words, snooze, or dismiss any item.
Step 4 — Steer through memory, not micromanagement#
- Instructions (Settings → General): your standing rules — read at the start of every session the Bot runs. Put enduring policy here, not chat.
- Memory (Settings → Memory): files the Bot writes itself — preferences, corrections, project facts. To change what it remembers, just tell it in chat ("remember: we deploy via Cloud Run, never bare VMs"). Everyone who can use the Bot can read its memory — treat shared-Bot memory as shared.
The pattern that scales: correct the Bot once, let it write the correction to memory, and every future session inherits it. Cognition merges 2,000+ PRs/week on this loop.
Before you share it — access and usage#
Two things the launch posts skip that the docs spell out:
- A private Bot inherits your resources without asking. Access you already have can be recorded as grants with no new permission prompt — a private Bot is not a sandbox. Before sharing, open Settings → Access and strip grants the job doesn't need. If teammates should copy the method without seeing your conversation or credentials, share a template, not the Bot — Share as template in the Bot's sidebar menu drafts a name, description and cleaned prompt, published to the org's Template library (Teams/Enterprise) or as a public link (Pro+). The link embeds the whole signed template in its URL — it can't be edited or revoked and anyone can read the prompt, so strip internal names before copying it.
- A Bot's usage covers its chat plus every session it spawns. Max: draws your included quota then on-demand — no separate Bot cap. Teams: your quota then team credits, an admin can set a Bot-specific on-demand cap. Enterprise: counts against the creator's limit unless assigned its own. A spending instruction in chat is not a configured cap — set the limit in Settings, don't describe it in prose.
Step 5 — Put it where you work#
- Slack: give the Bot its own Slack app so your team can @-mention or DM it (Settings → Slack). Every reported team deployment runs this way — the Bot becomes a named teammate in a channel.
- iMessage: text the Bot from your phone.
- Web: the sidebar's Bots section lists yours and the ones shared with you.
Step 6 — Schedules and modes#
- Automations: ask in chat — "run a summary of open PRs every weekday morning" — and the Bot proposes the automation for your one-time approval. Manage them under Settings → Automations (pause/resume/remove).
- Modes: the Bot has its own mode plus a Child Capability default for the sessions it spawns (e.g.
Normal / Ultrain the chat's mode picker). You can also ask for a different mode on any single session.
Lifecycle#
| Action | Effect |
|---|---|
| Recycle | Terminates the current session; a fresh one starts next open. In the chat menu. |
| Archive | Stops responses, removes it from Bot lists, removes its Slack app and inter-Bot grants (unarchiving doesn't restore those — you set them up again). |
| Delete | Permanent: settings, sessions, memory, automations. Cannot be undone. |
Only the creator and roles with Manage Bots see Archive/Delete. On Enterprise plans, Use Bots / Manage Bots / Manage Bots across the enterprise are separate permissions in custom roles.
Verify it#
- [ ] Bot created and named; outcome prompt sent in chat
- [ ] Bot started at least one child session without being asked twice
- [ ] A decision/PR/permission request appeared in Needs you and you resolved it
- [ ] One correction you gave in chat shows up as a memory file under Settings → Memory
- [ ] (Optional) Bot reachable via @-mention in Slack
Pitfalls#
- Task-shaped prompts. "Fix X" produces a session, not a Bot. If the Bot finishes and goes quiet, the prompt was a task — restate it as ownership.
- Chat for policy. Rules typed in chat scroll away; rules in Instructions are read every session. Chat = direction and answers; Instructions = law.
- Ignoring Needs you. Bots are designed to batch judgment calls — check once or twice a day, not continuously.
Knowledge check#
- What survives between a Bot's sessions that a one-off session doesn't have? (Memory — plus the standing outcome, schedules, and surfaces.)
- Why does a Bot "needs-you" instead of asking mid-session? (Judgment goes to one thread asynchronously; the human isn't a blocking call in the loop.)
- Which mechanic turns "a smart session" into "an employee"? (Ownership of an outcome — the goal persists after any single session ends.)
Sources#
- Devin Bots — docs — mechanics, access, usage limits
- Introducing Devin Bots — launch post, the Android Bot prompt
- AI Native Operators — Devin Bots: give an agent a job to own — community field guide; the bounded-first-assignment pattern and access/usage caveats above
- Back: Guide 18 — Talking to Devin (the doctrine under the outcome prompt) · Next: Guide 2 — Product-owner Bot