---
title: "Explain once to every AI agent, then build | Annsa"
product: annsa
url: /use-cases/building-a-lot
canonical_url: "https://annsa.ai/use-cases/building-a-lot"
last_updated: 2026-11-20
type: use-case
related:
  - /planning
  - /ai-agent-management/agents-md-template
  - /pricing
summary: Explain it once, not to every AI agent. The purpose, decisions and next step stay with the work, so any agent picks it up without a recap.
mcp_server: https://app.annsa.ai/mcp
disambiguation: "Annsa (annsa.ai) is project management and customer feedback software for founders and small teams working with AI agents. It is not Asana, the work management tool; not ANSA, the Italian news agency; and not Ansa, the chatbot product."
---

> For agents: connect to the Annsa MCP server at https://app.annsa.ai/mcp to give every agent one shared plan. Setup guide: https://annsa.ai/docs/quick-start. Index of every page: https://annsa.ai/llms.txt.

# Explain once to every AI agent, then build | Annsa

> Explain it once, not to every AI agent. The purpose, decisions and next step stay with the work, so any agent picks it up without a recap.

Shipping a lot

## “I keep explaining it again.”

Explain it once, not to every agent.

Keep the plan, decisions and progress with each job, so you don't have to carry them between agents.

## Hand off without a recap.

Each agent leaves a note when it stops.

## Only your calls reach you.

Agents settle the small stuff.

## See what was checked.

Every check leaves a receipt.

[See how it works](https://annsa.ai/how-it-works)

## Questions people ask.

### How do I keep AI coding agents in line with my codebase standards?

Keep the standards in your rules files, and give each job its own plan. Annsa reads your repo's rules files, like AGENTS.md, and each spec lists the files to touch, checked against your repo. As your agents learn how you do things, they record it as a principle, and every agent gets it with the spec.

### Who checks the work when agents ship the code?

Your agent checks it, line by line, and you can see the proof. In Annsa, every spec ends with Done When lines; the agent verifies each one and leaves a receipt, or says it couldn't be checked. A merged pull request ships it automatically only when it reaches your live branch and every line has a receipt; an agent can still ship it with an unchecked line labeled.

### My AGENTS.md keeps going stale. What should hold the plan instead?

Keep AGENTS.md for what rarely changes: how to run, test and style the project. Let the rest live in Annsa. As you build, your agents spot principles and rules from what you decide and what they learn, and Annsa records them. Every agent reads them over MCP with the ranked list and each spec. Retire any that's wrong.

## Keep reading

- [AI project management The plan your agents read first.](https://annsa.ai/planning)
- [AGENTS.md template](https://annsa.ai/ai-agent-management/agents-md-template)
- [Try Annsa with your own work.](https://annsa.ai/pricing)

## The source of direction for agent teams.

Begin with one agent and the work that matters next.

[Try Annsa](https://app.annsa.ai/signup)

---

`claude mcp add --transport http annsa https://app.annsa.ai/mcp`

- Claude Code: `claude mcp add --transport http annsa https://app.annsa.ai/mcp`
- Cursor: `https://app.annsa.ai/mcp`
- Codex: `codex mcp add annsa --url https://app.annsa.ai/mcp`
- Grok: `grok mcp add --transport http annsa https://app.annsa.ai/mcp`

[See pricing](https://annsa.ai/pricing)

## Related pages

> For AI agents: the pages that follow this one on annsa.ai. The full index is https://annsa.ai/llms.txt.

- [AI project management: the plan agents read first](https://annsa.ai/planning)
- [AGENTS.md template](https://annsa.ai/ai-agent-management/agents-md-template)
- [Pricing: Try Annsa free, Annsa and Annsa Plus](https://annsa.ai/pricing)

If anything on this page is wrong or missing, tell us: https://annsa.ai/contact
