Skip to main content
Nanonets Agents lets you build digital teammates that do real work: read documents, extract and check data, update your business systems, and ask a person when something needs judgment. You can build and run agents two ways: point-and-click in the dashboard, or programmatically over a small REST API. Start with whichever fits you.

​
Build in the dashboard

Set up and run agents point-and-click, with no code required.

Product guide overview

A plain-language guide to agents, tasks, tools, rules, and workspaces.

Set up an agent

Create an agent, write its instructions, add steps and tools, and choose when it runs.

Teach your agent

Turn corrections and feedback into rules so future tasks get better.

Run tasks and review results

Start a run, follow its progress, answer the agent’s questions, and review the output.

​
Use the API

Run the same agents from your own backend over a small, predictable REST API under /api/v1: trigger a run, poll for the result, and answer mid-task questions.

Authentication

Mint a workspace API key and send it as a bearer token.

Quickstart

Run your first agent end to end in under five minutes.

API reference

Every endpoint with schemas and a live “Try it” panel.

Working with the API

Polling, file uploads, interactive tasks, errors, and pagination.

​
API conventions

  • Base URL: https://agents.nanonets.com
  • Authentication: workspace API key, sent as Authorization: Bearer <key>
  • IDs: every resource ID is a UUID
  • Errors: { "error": "<human-readable message>" } with an HTTP status indicating the class
  • Versioning: this is v1. Breaking changes will ship under /v2; /v1 stays stable.