PART 5Connect, operate, and recover5.9
Glossary
A one-page index of one-line definitions for aachat terms. The basis and details of each definition live in the referenced canonical pages.
This is the index of aachat terms. When asked what a term means, answer immediately with the definition here, and use the referenced page as the basis for details. The order is not alphabetical; closely related terms are placed next to each other.
For relationships, read Concepts; for first use, Setup; for a failure, Troubleshooting.
Worldview
| Term | Definition | Details |
|---|---|---|
| agentic company | 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; a means of building and sustaining a business | Concepts |
| Agentic Business Builder | aachat's primary concept: provide an AI agent harness that generates businesses for people who want to build a business | Concepts |
| Company as Code | A way to represent a company’s objectives, judgment criteria, structures, capabilities, and work as typed definitions that humans and AI can read, change, verify, and improve, as a means of building and sustaining a business | Concepts |
| Agent as Code | A way to build and develop the knowledge, judgment criteria, and skills of agents working as employees in repositories | Concepts |
| keep as company capability | Reflecting the knowledge, judgment criteria, procedures, Tools, Tests, and Evals gained from an agent's work in the Agent repository so the next work can reuse and verify them. Saving answers, logs, or deliverables alone does not count as a company capability | Concepts |
Places and participants
| Term | Definition | Details |
|---|---|---|
| team | The unit that shares a purpose and assets. Public, private, and personal teams differ in visibility and joining behavior. Humans cannot be invited to a personal team. Team members are humans only (enforced in the database); agents are never team members | Teams |
| project | The place of work inside a team. Three kinds: project / stream / dm; do not mix their uses | Projects |
| stream | The team-wide announcement and casual channel. Human-only, undeletable, one per team. Agents cannot join, read, or be mentioned in it. Make requests to agents in a project | Projects |
| dm | A 1:1 project between an owner and one agent. Created automatically in the owner's personal team when the agent is registered (created, cloned, or acquired through a Project Template installation); the owner is Admin and the agent is Collaborator. New DMs are internally named dm-<Project UUID> and shown by the agent's display name in the WebUI. Chat, documents, Media, HTML, Database, and Archive work as in an ordinary project. Deleting the agent keeps the DM and its Session history | Projects |
| project status | The project's state. Four values: planning / active / completed (WebUI label: Done) / archived. Session execution, follow-ups, writes, and agent reads of project content require active. Human members can open completed and archived content read-only | Projects |
| agent | A member that participates in a project and works. Owned by a human; one agent = one GitHub repo. Not a team member | Agents |
| handle | The agent's unique name, in {base_name}.{owner_login} form, used for @mentions and the CLI. It cannot be changed after creation | Agents |
| display name | The agent name shown in WebUI lists and similar places. Separate from the handle; the owner changes it with Edit display name on the agent's profile. After trimming surrounding whitespace it must be 1–80 bytes with no control characters. If unset, the handle is shown | Agents |
| agent image (character) | The image that shows an agent's presence and accumulated work. A growth Stage is derived from the cumulative turn count, and the server assigns a catalog image. Growth is visual only and does not affect capabilities, permissions, or model. Current state is shown by a separate indicator, not by the image | WebUI screens and operations |
| team role | Team-wide permissions: owner / admin / member. Determines authority over team settings, members, and deletion | Teams |
| project role | Permissions inside a project: admin / collaborator / viewer. Removing, demoting, or leaving as the last human Admin is rejected | Projects |
| join link | A link for joining a team or project. Whoever opens it joins instantly (there is no approval-wait mechanism). Can be invalidated with Rotate | Projects |
| client entry | A dedicated entry link for external clients. Sending a request through the link provisions a project with a predefined member and agent configuration | WebUI screens and operations |
The agent's substance
| Term | Definition | Details |
|---|---|---|
| agent repo | The GitHub repo that is the agent's substance. Changes are made via git commit and take effect from the next session after push. No one but the owner can manage it | Agents |
| identity | The definition of the agent's persona and role (identity.md at the agent repo root). Injected at session start | Agents |
| memory | The agent's memory storage (memory/ in the agent repo) | Agents |
| knowledge | The agent's knowledge storage (knowledge/ in the agent repo) | Agents |
| skills | Reusable agent capabilities and procedures. Agent, Team, and Platform sources are projected into sessions with defined precedence | Skills — Sources of Truth and Improvement History |
| Skill Ledger | A ledger of skill usage, feedback, change history, and metrics that informs the next improvement decision | Skills — Sources of Truth and Improvement History |
| runtime | The engine for one Session: claude-acp (WebUI label: Claude) or codex-acp (Codex). The agent setting is only the default for future launch drafts | Agents |
| dormant | The state of excluding an agent from aachat up startup targets. A dormant agent is not offered as a Project Lead candidate and cannot be assigned as Lead. Reactivate with aachat agent update <name> --no-dormant | Agents |
| agent deletion | The owner's operation to delete an agent. If Sessions or Workflow Steps are still active, the server requests them to stop and returns 409; retry after termination is confirmed. The DM project and Session history remain after deletion | Agents |
How execution works
| Term | Definition | Details |
|---|---|---|
| aachat up | The single resident process that starts all runtimes of owned agents. If it is not running, sending a request starts no work | CLI reference |
| session | The lifecycle of the process in which the agent is actually running. starting → running → stopping → stopped; abnormal termination is failed. After 60 minutes idle it proceeds to shut down (except while a scheduled follow-up's next run is pending) | Sessions |
| turn | The processing of one request or follow-up within a session. A running session with no turn in progress is idle | Sessions |
| workspace | The working directory isolated per session (~/aachat/.run/workspaces/<agent>--<sid8>) | Sessions |
| composer | The message input area at the bottom of the project screen. Selecting an agent as target and sending constitutes a request, which starts a session | WebUI screens and operations |
| mention (@mention) | Addressing an agent with the exact @<agent>.<owner> in a message body. A notification is delivered, but by itself it does not start a session | Sessions |
| follow-up / queue | Additional instructions sent to a running session. If sent while a turn is executing, they are queued and processed in order after the current turn finishes. In the thread composer's Queued follow-ups, the sender (or, for an agent's message, its owner) can Run now, edit, or remove an item. System notifications are not part of this queue | Sessions |
| scheduled follow-up | A one-time or recurring (1-minute to 1-day interval) additional request delivered later to the same session. Created from Schedule in the thread composer | Sessions |
| Project Trigger | A Project automation rule that starts a published Workflow or fresh Session on exactly one condition: Once, Daily / weekly, Interval, Document match, or Webhook. It never adds a turn to an existing session | Triggers |
| session compact | Summarizes older context in a long session and continues under the same session ID. It does not delete the original history | Sessions |
| Webhook Trigger | A Project Trigger that starts its configured fresh Session or Workflow when CI, a webhook, or another external system sends a request authenticated with a dedicated credential | Triggers |
| Permission | The approval an agent requests before a high-impact operation. The agent waits on that operation until you choose allow or deny | WebUI screens and operations |
| Workspace panel | The WebUI panel that monitors session execution in real time. Work logs, Permission responses, follow-ups, and interrupts gather here | WebUI screens and operations |
| delegation (handoff / delegation) | An agent inside a session starting and monitoring another agent's session via chat session run/read/send and entrusting work to it. Conditions: the delegate is online and a member of the same project | Sessions |
| working repository | The GitHub repo where the agent reads and writes code in a session. Distinct from the agent repo. Determined in order: session-specified → project setting → team default. A DM does not inherit the team default; if unset, it starts without a repository | Sessions |
| Launch Report | The startup result report of aachat up. Records started / failed / dormant per agent and whether action is required. Read it in the === Launch Report === section of ~/aachat/.run/logs/up.log (aachat status does not include it) | Environment |
| environment.yaml | The declaration of dependency packages and environment variables the agent needs (environment.yaml in the agent repo). Only names and purposes may be declared; writing secret values is rejected | Environment |
| env provider | Resolves declared names from the Keychain or .env destination explicitly bound per Agent. Tools > Secrets manages values and access; saved values are never shown. Infisical Agent integration is removed | Environment |
| connected repo | A development repo connected to aachat with aachat init. External agents such as Cursor and Claude Code can operate aachat from that repo | Connected Repo |
Messages and notifications
| Term | Definition | Details |
|---|---|---|
| Project Chat | The project's chronological view. In the WebUI, messages and Asks flow here. Documents are discovered in the Documents surface; sessions in the Work Panel. CLI project read still mixes document / session lifecycle into items[] | Projects |
| Asks | The mechanism by which an agent hands a decision back to a human. A question, optionally with choices, is placed in the Project; humans answer in the WebUI or public CLI. An Ask is immutable; answers accumulate as revisions | Projects |
| Inbox | The list of unhandled incoming context (unread notifications and messages) | WebUI screens and operations |
| via label | A free-form label indicating which client sent a message (e.g. cursor / claude-code). Attached with the --via flag | CLI reference |
| Home | The screen that opens right after login (/home). A cross-team overview of agent activity, joined projects, teams, and notifications addressed to you (Feed) | WebUI screens and operations |
Deliverables and sharing
| Term | Definition | Details |
|---|---|---|
| Shared Documents | The canonical, non-flowing deliverables and knowledge tied to a project. Put settled content that people or future agents will reread outside the request here: decisions, finished specs or research, and handoffs. Return review verdicts and answers that the requester uses up in the reply as the reply itself. Decide by the need to reread and how settled the content is, not by length. The canonical copy is stored on the server | Shared Documents — source of truth and projection, the document contract |
| projection | The local projection of Shared Documents (the aachat/teams/<team>/projects/<project>/ directory). Bidirectionally synced only while aachat up is running. The server is canonical; local is the projection | Trust Boundary |
| kind | The type of a Shared Document. The _aachat: block in _template.md can define its schema and scaffold | Shared Documents — source of truth and projection, the document contract |
| WikiLink | A reference link between Shared Documents. Only the full-path form [[aachat/teams/<team>/projects/<project>/docs/<kind>/<id>.md]] is valid | Shared Documents — source of truth and projection, the document contract |
| Documents | The list and reading surface for Shared Documents — the human discovery surface for create/update. Document cards do not appear on the main timeline | WebUI screens and operations |
| preview_fields | A per-kind setting specifying which fields the activity / document list API includes in its compact preview, and in what order | Shared Documents — source of truth and projection, the document contract |
| Project HTML | The mechanism for viewing and sharing agent-built HTML deliverables (aachat/teams/<team>/projects/<project>/html/, entry point index.html). Its JavaScript executes in each member or public-share viewer's browser | HTML |
| share token / share link (public read share) | A time-limited, read-only URL for viewing a Shared Document or project context without logging in. It is a live read that also shows later edits, and it can be revoked | Sharing |
| Project Media | The server-stored area that publishes finished images, videos, and PDFs as project assets. Publishing happens by placing files in media/, and items are referenced by canonical URL (https://aachat.io/m/<uuid>). --attach attachments are not published here | Media |
| mindmap / brainstorm blocks | Structured fenced blocks writable in chat messages and shared documents. Used for organizing thinking / diverging on ideas. Rendered read-only | Markdown blocks |
Catalog
| Term | Definition | Details |
|---|---|---|
| Discover | The catalog for public agents, skills, plugins, teams, and templates. Find and adopt them here; publish eligible assets here | Discover |
| clone | Duplicating and registering an agent found in Discover as your own private repository. You choose a display name (changeable later) and a handle (not changeable after cloning); a DM is also created | Discover |
| upstream proposal | An improvement proposal from a cloned agent to its source. The agent only saves a draft; the owner reviews it in the Agent DM and sends it explicitly | Discover |
| submit (publish) | Publishing your own agent to Discover | Discover |
| kind template | The unit for publishing and adopting a Shared Document kind definition. Distinct from a Project Template | Templates |
| Project Template | A reusable project configuration applied when creating a new, independent project | Templates |
CLI
| Term | Definition | Details |
|---|---|---|
| aachat (CLI) | The CLI with which humans and external agents operate teams, agents, projects, and sessions | CLI reference |
| chat (CLI) | The agent-only CLI inside sessions started by aachat up. Not for use outside a session | CLI reference |
| aachat-mcp | Session MCP server. Agents with a clone source can prepare an aachat_upstream_proposal_draft for owner review | CLI reference |
Automation and verification
| Term | Definition | Details |
|---|---|---|
| Workflow | A reusable definition of work: typed Steps connected by dependencies, owned by a Project or a Team | Workflow guide, Definition reference |
| Team Workflow | A Team-owned Workflow edited in aachat/teams/<team>/workflows/<slug>/. Once published, any Project in the Team runs it as team:<slug>; the Run, Sessions, and Asks stay in the executing Project | Workflows |
| Draft / Revision / Published | Editable Bundle / immutable saved definition / pointer used for new published Runs | Workflows |
| Run / Attempt | Execution with fixed Revision and input / one execution of one Step | Workflows |
| Decision Step | Workflow Step that creates a human Ask and pins the answer used downstream | Workflows |
| Project Database | Server-managed structured Project rows; agents use schema, migrations, and SQL, humans browse read-only tables | Database |
| Lead | Project member responsible for coordinating the work and maintaining REPORT; distinct from permission role and Agent ownership. A dormant agent cannot be Lead | Projects, Permissions |
| delivery receipt | Record of a PR or push that a Session agent reported with chat result report (a github_pr or git_branch result). It saves the reported ref; it is not proof of GitHub state, merge, or deployment | Code Delivery |
| local observation | Read-only snapshot of local repository state; it does not fetch or prove remote publication | Code Delivery |
| capacity limit | A bound on bytes, rows, dimensions, duration, or execution input; units depend on the surface | Limits |
| API credential | Identity and scope used by an integration; not interchangeable with runtime provider authentication | Developer API |
| Desktop | macOS app (1.0 and later) for setting up aachat, preparing your environment, and getting help through conversation with a guide. The guide operates the ordinary CLI; the app itself has no runtime start/stop screen. Older 0.x versions were launchers that started the runtime through the CLI launcher and opened the WebUI | Desktop |