Prompt guidance

Prompting ACP is different from prompting a stateless chatbot. Agents can work inside projects, continue threads, inspect persistent computers, create tickets, review work, use files, and deploy resources. Strong prompts give the agent an operational goal, the project context it should use, and a clear definition of done.

Start from the operational goal

Lead with the outcome the agent should create. This helps the agent select the right tools, level of autonomy, and validation path.

Start from the operational goal
Lead with the deliverableStart with the thing that should exist at the end: web app, report, database, function, presentation, migration, analysis, or fix.
Define observable doneSay what the agent should verify before stopping. Examples: app deployed, tests pass, report saved, screenshots attached, or review comments resolved.
Use operational verbsPrefer build, deploy, audit, migrate, research, compare, summarize, update, refactor, validate, or monitor over vague instructions like help with.
Name the user outcomeTell the agent who the work is for and what decision or workflow it should support, so it can choose the right level of detail.
Better than a vague request
Loading...

Use project context for real work

Projects give agents strategy, releases, tickets, comments, reviewers, files, and resources. Use them whenever the work should survive beyond one chat.

Use project context for real work
Use projects for multi-step workIf the goal needs planning, tickets, resources, reviews, or several agents, ask mission control to turn the goal into a project plan first.
Reference releases and ticketsTell the agent which release, ticket, or backlog area it should operate in. This keeps implementation work attached to the right project context.
Describe review expectationsState whether a ticket should go to review, who reviews it, and what evidence the reviewer should inspect before accepting or requesting changes.
Mention adjacent workCall out previous tickets, next tickets, dependencies, blockers, and human-owned tasks so the agent can avoid duplicate or out-of-order work.

Mission control

Use it when the goal needs strategy, releases, ticket cleanup, backlog planning, or a reset of what the project should do next.

Tickets

Use tickets when work has a clear owner, status, reviewer, subtasks, dependencies, and acceptance criteria.

Resources

Use resources when agents should deploy or manage web apps, functions, databases, auth, secrets, or runtimes as part of the project.

Reviews

Use reviews when the agent should not mark the ticket done until a human or reviewer agent has inspected the result.

Project planning prompt
Loading...

Be explicit about state

ACP agents can continue from a real computer and thread history. Tell them whether to preserve, inspect, fork, or reset that state.

Be explicit about state
Continue or start freshSay whether the agent should continue from the current thread and computer state, inspect an existing workspace, or create a new clean environment.
Inspect before editingWhen state already exists, tell the agent to inspect files, deployments, logs, tickets, and resources before changing anything.
Keep scope visibleName the computer, project, repository, resource, branch, or directory the agent should stay inside.
Choose the safety pathIf the current state is fragile, ask the agent to fork, create a new branch, draft a plan, or ask for approval before destructive changes.
State-aware fix
Loading...

Name artifacts and checks

Concrete outputs are easier to inspect, review, reuse, and continue. Name the artifact, where it should live, and how the agent should verify it.

Name artifacts and checks
Files and reportsName the expected files and formats: markdown report, spreadsheet, deck, JSON export, screenshots, diagrams, or a folder of generated assets.
Product resourcesIf the output should be live, say which resource to create or update: web app, function, database, auth module, secret vault, or agent runtime.
Acceptance checksAsk the agent to validate the output with tests, smoke checks, screenshots, API calls, database reads, or deployment logs before it stops.
Handoff summaryRequest a concise final summary with what changed, where to find it, how it was verified, and what remains blocked or risky.
Research artifact prompt
Loading...

Set boundaries before tools run

Agents can browse, edit, deploy, and operate cloud resources. Good prompts make the allowed surface area visible before execution starts.

Set boundaries before tools run
Allowed toolsSay whether the agent may browse, install packages, call APIs, use skills, edit files, deploy resources, or create new computers.
Security boundariesIdentify secrets, private data, customer data, production resources, or compliance constraints that should not be exposed or modified casually.
Design and quality barDescribe product design constraints, tone, accessibility expectations, browser support, performance targets, or documentation standards.
Budget and runtimeFor large work, state whether the agent should optimize for speed, quality, cost, or an approval checkpoint before spending more time.
Constrained deployment prompt
Loading...

Prompt for iterative execution

Large work should not be compressed into one giant instruction blob. Use planning, tickets, reviews, and follow-up runs to keep quality high.

Prompt for iterative execution
Plan first when ambiguousAsk for a short plan before execution when the agent needs to choose architecture, resource boundaries, or a multi-ticket breakdown.
Let agents exploreDo not paste every detail into the prompt. Tell the agent where the context lives and what to inspect: project strategy, tasks, files, logs, or comments.
Use review loopsFor important tickets, ask the implementation agent to move work into review and the reviewer to either accept or request specific changes.
Keep the next step clearEnd prompts with the next concrete objective, especially when work should continue across several threads or agents.
Implementation plus review prompt
Loading...

Prompt examples

Use these as starting points for common ACP workflows. Replace project names, tickets, resources, and acceptance checks with your own context.

Build a project resource
Loading...
Run a reviewer agent
Loading...
Ask for human-owned inputs
Loading...
Recurring operations prompt
Loading...