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

# Agents Overview

> Build, deploy, and operate Claude agents that use agntdata APIs, integrations, and your workspace database as tools.

agntdata Agents lets you ship a working Claude agent without writing any infrastructure. You describe what you want in plain English; a meta-agent ("the Builder") configures and deploys it; the deployed agent runs on Anthropic's managed runtime and pulls every tool it needs through agntdata's MCP gateway.

## Two surfaces, one workspace

<CardGroup cols={2}>
  <Card title="The Builder" icon="sparkles" href="/agents/builder">
    A meta-agent that interviews you in natural language, proposes a configuration, and applies it after your approval. Lives at **`/dashboard/chat`** in the dashboard.
  </Card>

  <Card title="Deployed Agents" icon="robot">
    Production agents you can chat with from the dashboard, fire on a schedule, route through Slack, or wake up via an inbound webhook.
  </Card>
</CardGroup>

## What an agent gets

Every deployed agent fetches its tools through agntdata's MCP gateway:

```
https://api.agntdata.dev/runtime/agents/{deployed_agent_id}/mcp
```

When the runtime calls `tools/list`, the gateway emits:

* **Data API tools** (`data_<source>_<op>`) — every enabled data API in your workspace.
* **Connection tools** (`connection_<vendor>_<op>`) — your configured BYOK + OAuth proxies.
* **Workspace database tools** (`agnt_db_*`) — optional, gated by config.
* **Utility tools** (`agnt_credits_*`, `agnt_usage_*`, `agnt_webhooks_*`, `escalate_to_human`).
* **Skill tools** (`agnt_typescript_run_skill`, `agnt_skill_manifest`) — if the agent has skills attached.
* **Workspace files** (`agnt_files_*`) — read and upload files scoped to the workspace.
* **Memory tools** (`agnt_memory_*`) — opt-in per-agent durable memory.
* **Observability tools** (`agnt_observability_*`) — opt-in, for monitor and nightly-report agents.

See [Tools](/agents/tools) for the full registry and what each family does.

## The agent lifecycle

```
            (you describe → Builder proposes → you approve)
   draft ───────────────────────────────────────────────────► deployed
                                                                 │
       chat in dashboard ◄────┬──── deployed agent ────┬──────► Slack threads
                              │                        │
              schedule fires ─┘                        └─ webhook deliveries
                              │
                              └─────► agent_session ───► event stream + audit
                                                                 │
                                                                 ▼
                                           usage_logs + agent_compute_usage
```

Every conversation — dashboard chat, Slack thread, scheduled fire, webhook delivery — runs inside an **[agent session](/agents/sessions)**. Sessions get a full event history and per-turn cost attribution.

## Core concepts

* **System prompt** — the agent's persistent role and rules. Edited via the Builder's `propose_agent_patch` tool (with your approval) rather than direct DB writes.
* **Tools** — discrete capabilities the agent can call. Each invocation is logged to `usage_logs` (data wallet) and `agent_compute_usage` (AI wallet).
* **Sessions** — every conversation gets an `agent_sessions` row pointing at Anthropic's canonical event history.
* **Triggers** — schedules, inbound webhooks, and the coming-soon queue. See [Triggers](/agents/triggers).
* **Permissions** — mark sensitive tools as `always_ask` so the agent has to call `escalate_to_human` before using them.
* **Escalations** — the agent asks a human via `escalate_to_human`; the question lands in your **Inbox** (and a Slack channel, if connected).
* **Folders** — sidebar organization for when you've built more than a handful of agents.
* **Memory** — optional pgvector-backed memory so the agent learns across sessions.

## How it works end to end

<Steps>
  <Step title="Describe the agent">
    Open **Agents → Build with AI** and tell the Builder what you want. It pulls in your workspace profile and recent design memories so you don't repeat yourself.
  </Step>

  <Step title="Approve a proposal">
    The Builder drafts the system prompt and tool list and surfaces a proposal card with Approve / Reject.
  </Step>

  <Step title="Deploy">
    On approve, agntdata mints an agent-scoped API key, registers the agent with Anthropic's runtime, and exposes the MCP gateway URL the runtime uses.
  </Step>

  <Step title="Talk to it">
    Chat with it from the dashboard, mention it from Slack, fire it on a cron, or POST to a webhook.
  </Step>

  <Step title="Iterate">
    Open the Builder for the same agent any time and ask for changes. The Builder reads recent sessions and proposes patches with diffs.
  </Step>
</Steps>

## Next steps

<CardGroup cols={3}>
  <Card title="The Builder" icon="sparkles" href="/agents/builder">
    How the meta-agent designs and ships agents.
  </Card>

  <Card title="Triggers" icon="bolt" href="/agents/triggers">
    Schedules, webhooks, and the queue.
  </Card>

  <Card title="Sessions" icon="messages" href="/agents/sessions">
    Lifecycle and audit.
  </Card>

  <Card title="Tools" icon="screwdriver-wrench" href="/agents/tools">
    The full tool registry.
  </Card>

  <Card title="Workspace database" icon="database" href="/agents/workspace-database">
    Durable state for agents.
  </Card>

  <Card title="Permissions" icon="shield" href="/agents/permissions">
    Human-in-the-loop control.
  </Card>

  <Card title="Folders" icon="folder" href="/agents/folders">
    Sidebar organization.
  </Card>

  <Card title="Slack" icon="slack" href="/agents/slack">
    Route Slack DMs and channels to agents.
  </Card>
</CardGroup>