Agent Flow Bind docs

Getting started

Create an API key, pick a preset, and run your first agent end to end.

Authentication & scopes

Bearer API keys, session cookies, scopes, and the default rate limit.

Runs lifecycle & statuses

The run status machine, endpoints for each stage, and the exact JSON shapes.

Human-in-the-loop

Answering, approving, and reviewing a paused run.

Webhooks

Subscribing to run events and verifying delivery signatures.

Presets & schemas

The built-in document presets, their output schemas, and agent versioning.

Connections

Delivery targets a run's output can be saved to, beyond the default download.

Knowledge

Uploading reference documents an agent can search while running.

Evals

Turning corrected output into regression tests for an agent.

Published apps

Letting an end user run one agent through a branded, no-API-key web app.

Errors & rate limits

The error envelope, common error codes, idempotency, and rate limits.

SDK (TypeScript)

The @agentflowbind/sdk package — every example on this page is SDK (preview).

Data & providers

Which model providers process your data, where, and how it's disclosed.