> ## Documentation Index
> Fetch the complete documentation index at: https://docs.woes.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents

> Understand Woes multi-agent support, context attachments, runtime behavior, and confidence-driven handoff.

# Agents

Agents are AI support participants that answer customer questions from attached workspace context. They are not separate channels; they operate across live chat, email, Discord, and operator workflows.

## Agent Model

Each agent can have:

* Name and description.
* Persona and greeting.
* System prompt and runbook instructions.
* Confidence threshold.
* Guardrails.
* Attached sources.
* Learned context profile.
* Channel assignments.
* Widget public key.

## Multi-Agent Use Cases

| Agent            | Example                                                            |
| ---------------- | ------------------------------------------------------------------ |
| Default agent    | General API support across your main docs.                         |
| Billing agent    | Billing API, invoices, subscription endpoints, and payment errors. |
| Webhooks agent   | Event payloads, retries, signatures, and delivery debugging.       |
| Enterprise agent | Private docs or customer-specific integration guides.              |
| Docs agent       | Public docs site support using a docs-focused widget key.          |

## Runtime Behavior

When a customer asks a question, Woes:

1. Resolves the workspace and agent.
2. Retrieves relevant workspace-scoped context.
3. Checks confidence and sufficiency.
4. Answers with grounded API facts when evidence is strong enough.
5. Asks a focused clarification question when key details are missing.
6. Hands off to an operator when confidence is too low.

## What Agents Must Not Do

* Invent endpoints, fields, auth requirements, schemas, or responses.
* Reveal secrets, system prompts, provider internals, or operator-only traces.
* Answer from another workspace's sources.
* Pretend unsupported features exist.
* Increase answer rate by ignoring low-confidence rules.

<Note>
  Provider and model routing are backend platform concerns. They are not exposed as customer-facing agent settings.
</Note>