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

# Agents Overview

> Autonomous mapping operators for your workspace — Pro Max only.

An **agent** is a long-running autonomous worker scoped to a slice of your inventory. You give it a goal in plain English, set guardrails, and it runs on its own — triggered by new uploads, finished mapping jobs, mismatch reports, golden-dataset changes, or on a cron schedule. Every action it takes is recorded, reversible for 7 days, and capped by daily spend and hourly rate limits you control.

Agents are available on **Pro Max** and Enterprise plans only.

## When to use an agent

<CardGroup cols={2}>
  <Card title="Always-on inventory hygiene" icon="broom">
    New rows uploaded every day? An agent re-runs mapping jobs automatically and files proposed matches for unmatched rows.
  </Card>

  <Card title="Mismatch triage at scale" icon="filter">
    Hundreds of mismatch reports backing up? An agent groups similar ones, drafts proposed resolutions, and queues them for a human reviewer.
  </Card>

  <Card title="Coverage monitoring" icon="chart-line">
    Want to know the moment supplier coverage drops below 95%? An agent watches, alerts, and posts a weekly digest to Slack.
  </Card>

  <Card title="Inventory in S3 or webhook" icon="cloud-arrow-down">
    Drop CSVs into a bucket on a schedule and the agent pulls them, runs the job, and (optionally) pushes results back to a sink of your choosing.
  </Card>
</CardGroup>

## When NOT to use an agent

* One-off cleanup tasks — use the UI or a one-shot mapping job instead.
* Bulk partner-hotel edits — agents cannot perform these in v1.
* Auto-linking unmatched rows without human review — agents propose, humans approve.
* Confidence-threshold-based auto-approval — see [Rules and decisions](/agents/rules-and-decisions) for the orchestration-first framing in v1.

## How it works (one cycle)

<Steps>
  <Step title="Trigger fires">
    An inventory upload completes, a cron tick lands, a mismatch is reported, or a user asks the agent a question in chat.
  </Step>

  <Step title="Runtime loads context">
    The agent runtime pulls the agent's goal, current rule set, recent memory notes, open pending items, and the trigger payload.
  </Step>

  <Step title="LLM decides">
    Claude (or your BYO model) plans the cycle and calls tools — read-only lookups, mutating actions, and state writes.
  </Step>

  <Step title="Every step is persisted">
    Audit log entries, undo snapshots (for mutating tools), token + cost ledger updates, and notifications fire as configured.
  </Step>

  <Step title="Summary lands">
    The cycle ends with a 1-3 sentence summary written by the agent. Visible in the UI run timeline.
  </Step>
</Steps>

## Trust by design

<CardGroup cols={3}>
  <Card title="7-day undo" icon="rotate-left">
    Every mutating action is reversible for 7 days from the workspace Undo Center.
  </Card>

  <Card title="Hard cost caps" icon="shield-check">
    Daily spend ceiling per agent — never blown by a runaway prompt.
  </Card>

  <Card title="Human-in-the-loop" icon="user-check">
    Match proposals and mismatch resolutions land as pending items, not auto-applied changes.
  </Card>
</CardGroup>

## What's next

* [Getting started](/agents/getting-started) — create your first agent in under 2 minutes.
* [Configuration reference](/agents/configuration-reference) — every field on an agent explained.
* [Rules and decisions](/agents/rules-and-decisions) — how the rule set shapes agent behaviour.

## v1 roadmap (not yet shipped)

<Note>
  The following items are explicitly **out of scope for v1** and will land in later releases. They are documented here so you know what to expect — and what not to expect — at launch.

  * **Generated API reference for agent endpoints.** REST endpoints exist (`/api/v1/agents/*`) but are not yet rendered in the API Reference tab. Use this section's reference pages until generation lands.
  * **Agent template library.** v1 ships with 3 canned starter templates on the create flow. A broader marketplace is a v2 surface.
  * **Multi-agent recipes / handoffs.** Agents run independently in v1. Coordinated multi-agent workflows are deferred.
  * **Customer-defined trigger DSL.** Triggers are limited to the built-in set (inventory upload, mapping job finished, mismatch report, golden-dataset change, cron).
  * **Confidence-threshold auto-approval rules.** v1 is orchestration + triage only; per-row confidence judgement is not configurable yet.
  * **SFTP and GCS data sources/sinks.** S3 and HTTPS webhook only in v1.
</Note>