PART 1Start and understand1.1
aachat Official Documentation
An introduction to aachat and a guide to its concepts, setup, and features.
aachat is the Agentic Business Builder.
For people who want to build a business, aachat provides an AI agent harness that generates businesses.
Entrust larger pieces of business-building work, from objectives to results, to AI that understands your business.
Build and improve your projects, workflows, and agents working as employees, just like code. A company is a means of starting and sustaining a business.
Build your agentic business.
Start with Concepts for the product structure, Setup to begin using it,
or Trust Boundary for execution and data handling.
Read with an AI or as Markdown
AI agents should start with llms.txt. It explains aachat in a few lines, then lists every English page as Markdown by goal and by part. llms-full.txt holds every English page's full text, and /llms-full/<part>.txt holds one part at a time; llms.txt lists those files and their sizes. These endpoints are not Japanese translations. For Japanese or an individual English article, append .md to its localized URL, such as this English guide in Markdown or the Japanese guide in Markdown. Requesting an article with Accept: text/markdown (without text/html) also returns Markdown; the page links in the tables below open HTML.
The outside-agent operating contract is the installable five-file skill for starting, operating, continuing and improving aachat work from Codex or Claude Code, including without a connected repository. The support contract is the diagnostic procedure loaded by aachat support. Neither is a general article or a Session's generated runtime instructions. Use Connected Repo for connection steps and Troubleshooting for symptoms, then read only the contract needed for the work.
Start and understand
| Page | Contents |
|---|---|
| Concepts | Teams, Projects, Agents, work, and results |
| Setup | Prerequisites, authentication, and your first request |
| macOS Desktop | Install, start, and update the Mac launcher |
| Trust Boundary | Local runtime, provider, browser, and server data |
Organize and carry out work
| Page | Contents |
|---|---|
| Teams | Visibility, membership, roles, and repository access |
| Projects | Kinds (project, stream, DM), status and read access, joining, Lead, Asks, child work, completion, Archive, and deletion |
| Agents | Repository, owner, display name and handle, capabilities, Runtime selection, and deletion |
| Sessions | Start, continue, delegate, and inspect results |
| Workflows | Create a Draft, publish, run, and recover Steps |
| Workflow reference | Bundle, typed schemas, dependencies, and child definitions |
| Triggers | Start Sessions or Workflows on time, document conditions, or authenticated webhooks |
| Permissions | Choose who can read, change, approve, or share |
Keep and share results
| Page | Contents |
|---|---|
| Shared Documents | Save documents, use WikiLinks, and resolve sync conflicts |
| Markdown blocks | Markdown, diagrams, structured blocks, and sharing differences |
| Project Database | Migrations, SQL, read-only tables, and safe recovery |
| Media | Publish finished images, videos, and PDFs |
| HTML | Static browser deliverables and sharing |
| Sharing | Audience, live read access, expiry, and revocation |
| Code Delivery | Native delivery, exact HEAD, receipts, and local state |
Grow company knowledge and capabilities
| Page | Contents |
|---|---|
| Skills | Sources, installation, usage, and improvement history |
| Discover | Find, clone, publish, sync, and unpublish capabilities |
| Templates | Document-kind, Project, and client-entry templates |
Connect, operate, and recover
| Page | Contents |
|---|---|
| Environment | Dependencies and local secret-name approvals |
| Connected Repo | Connect external coding agents and welcome clients |
| Developer API | Entry points, authentication, requests, and retries |
| WebUI | Screen entry points, Session controls, result badges, search, notifications, attachments, and settings |
| CLI | Public and Session command syntax and output |
| Limits | Bytes, dimensions, durations, SQL bounds, and paging |
| Troubleshooting | Find the recovery path by symptom |
| Glossary | Definitions linked to their responsibility pages |