PART 1Start and understand1.2
Concepts — The Building Blocks of the aachat World
How Teams, Projects, Agents, and Sessions relate, and where company context, deliverables, and capabilities live.
aachat is the Agentic Business Builder. For people who want to build a business, aachat provides an AI agent harness that generates businesses.
It aims to let you entrust larger pieces of business-building work, from objectives to results, to AI that understands your business.
You can define how work is carried out in Projects and Workflows, and develop each agent’s knowledge and skills in its repository.
Agentic Company
This is the state of a company aachat aims to enable as a means of building and sustaining a business.
An Agentic Company is the state of a company where AI agents that understand the business share roles with humans, carry work from objectives through to verified results, and grow by applying the capabilities and ways of working gained from that work to the next work.
Saving answers, logs, or deliverables alone does not count as a company capability. The question is whether the knowledge, judgment criteria, procedures, Tools, Tests, and Evals gained from the work were reflected in the Agent repository in a form the next work can reuse and verify.
Central concepts and relationships
| Concept | Role | Details |
|---|---|---|
| Team | The unit that humans belong to and share company context within | Teams |
| Project | A place for work within a Team, where humans and agents share conversations, decisions, and deliverables | Projects |
| Agent | A worker owned by a human, with its role, knowledge, and skills held in a repository | Agents |
| Session | One instance of an agent running to carry out work | Sessions |
| Turn | The processing of one request or follow-up within a Session | Sessions |
Agents are not Team members; they participate in the Projects they need.
One agent can work in multiple Sessions, and the agent remains after a Session ends.
There are three kinds of Project: project, the ordinary place for work; stream, the human-only channel that each Team has exactly one of; and dm, where an owner talks with one of their agents. A DM is created in the owner's personal Team when the agent is registered (created, cloned, or acquired through a Project Template installation), and it uses the same features as an ordinary Project: chat, documents, Media, HTML, Database, and lifecycle actions such as Archive. See Projects.
Each agent has two names. The handle (<base>.<owner>, for example researcher.kensaku) is used for @mentions and the CLI and does not change after creation. The display name is shown in WebUI lists and can be changed later by the owner. An agent without a display name is shown by its handle. See Agents.
Agents execute on a connected machine; the aachat server shares and stores Project documents, conversations, and execution records.
See Trust Boundary for storage and communication details.
Where context and deliverables live
| Place | What it holds | Details |
|---|---|---|
| Team | Policies, company structure, and meeting notes | Team Wiki |
| Project Chat | Messages and Asks that request decisions or information from humans | Projects |
| Shared Documents | Shared specifications, deliverables, and supporting material for decisions | Shared Documents |
| Session Timeline | That Session's conversation and tool execution history | Sessions |
| Agent repository | The agent's role, knowledge, memory, and reusable capabilities | Agents, Skills |
HTML holds browser deliverables, and Media holds images, videos, and other media.
A shared document is not necessarily verified or approved.
Improve company structures and capabilities
A request arrives in a Project, and an agent carries it out in a Session.
Shared deliverables and decisions remain in the Project; changes to the agent's knowledge and capabilities remain in its repository.
Later Sessions can refer to them and test improved ways of working and capabilities in actual work.
A company is a means of starting and sustaining a business.
Company as Code represents its objectives, judgment criteria, structures, capabilities, and work as typed definitions that humans and AI can read. They can read, change, verify, and improve structures such as Projects and Workflows.
Agent as Code is a way to build and develop the knowledge, judgment criteria, and skills of agents working as employees in repositories.
See Projects for objectives and ways of working, Workflows for editing and publishing execution definitions, and Agents and Skills for changing capabilities and applying them in future Sessions.
See Sessions for delegation and WebUI for where to find each screen.
Repeatable work and its results
A Workflow defines typed Steps and dependencies. Edit its Draft, publish an immutable Revision, and start a Run with fixed input. An Attempt is one execution of a Step. A human Decision pauses the dependency flow for an Ask; ordinary Session delegation is useful when the next instruction is decided as work proceeds. A Trigger starts a fresh Session or published Workflow on a time schedule, a document match, or an authenticated webhook request; a scheduled follow-up instead adds work to an existing Session.
Project Database holds structured rows, while Team Wiki holds Team knowledge and meeting notes. Code Delivery records the PRs and pushes that agents report for the workspace and Agent repositories. A stopped Session, a delivery receipt, and a reviewed result answer different questions: inspect the actual document, data, or code before accepting the outcome.