Glossary¶
Preview
Framework v2 is not yet available to all accounts.
| Term | Meaning |
|---|---|
| Agent | A representative of your business that talks to people on messaging channels; made of a Brief, Capabilities, and Channels. |
| Brief | The one document you write to describe an agent: Identity, Personality, Guardrails, Objectives, Playbooks, Content. Shown as the Definition page. |
| Capability | Something the agent can do beyond talking, which you switch on and configure: Scheduling, Knowledge, People, Notifications, Custom integrations. |
| Channel | Where the agent speaks: RCS, Apple Messages for Business, WhatsApp, SMS, Webchat. |
| Channel line | The one-line description of the current channel the agent reads each turn (rich or plain, how many chips, cards or not). |
| Custom integration | A capability backed by your own HTTP endpoint, described in your words. |
| Default Playbook | The Playbook that is active when no other fits; where the agent returns when a task is done. |
| Deterministic path | The panel on the Playbooks page that shows a Playbook's Flow and generates, regenerates, or removes it; also a synonym for the Flow itself. |
| Evaluation | An example conversation with checks, attached to a Playbook, Flow, or Objective, run before going live and after changes. |
| Flow | A fixed path carried by a Playbook: steps the platform walks in order, with the agent filling in each step's blanks. |
| Guardrail | A rule in the Brief the agent reads and follows with judgment. |
| Lint | The check that runs on every save and reports inconsistencies in the Brief, with severity and a fix where possible. |
| Message template | Exact copy you have reviewed, sent verbatim with placeholders filled in. |
| Objective | What a successful conversation achieves, ranked, with an outcome that proves it. |
| Outcome | The recorded event that shows an Objective was reached or a Flow finished, such as a call being booked. |
| Person | The record the agent keeps of one human it talks to; the People capability manages these. |
| Playbook | What the agent does in one kind of situation: name, when-to-use, body, and the capabilities it uses. |
| Policy | A rule the platform enforces before or after the agent's turn; the agent never sees it and cannot override it. |
| Readiness | Whether a capability, and so each Playbook that uses it, is set up and available; one answer shared by the console and the runtime. |
| Runtime | The engine that runs an agent's turns: Generic (the current runtime) or v2 preview; switched per agent from the Overview page. |
| Turn inspector | The console view, opened with Inspect turns on a conversation, that lists the conversation's turn records. |
| Turn record | What Anychat keeps for every turn: what fired, what was read, which Playbook was chosen, what the agent did and said, and what was sent. |
| Uses | The list of capabilities a Playbook relies on; sets what the agent may do while that Playbook is active. |