Agents

Agents Overview

NativeForm gives AI agents a reliable way to read form data, submit structured responses, and operate with clear authentication boundaries. Use this hub to choose the right integration path for your agent runtime.

New to the API? Start with Get an API Key, then explore the read API and submit API before diving into agent-specific patterns.

Capabilities

Start with the integration surface that matches your agent's job.

GET/api/forms/{formId}/responses

Read submissions

Use the read API to pull normalized form responses into your assistant memory or pipelines.

Open docs
POST/api/forms/{formId}/responses

Submit responses

Let an agent convert free-form user input into structured responses through the submit endpoint.

Open docs
/docs/my-api-keys

Manage authentication

Issue account-level keys, rotate compromised keys, and isolate integrations by key name.

Open docs

Architecture

Recommended production flow for robust agent integrations.

Runtime boundary

Keep NativeForm keys in server runtimes only. Browser clients should call your backend, never NativeForm directly.

Validation layer

Validate both incoming user input and outgoing agent tool calls before forwarding to NativeForm APIs.

Observability

Capture request IDs, response codes, and missing field errors to improve extraction prompts over time.

Fallbacks

Build deterministic fallbacks when the agent cannot infer required form fields with confidence.

Docs Map

Continue with the specialized guide for your stack.

Auth

Secure API keys and server-only access patterns.

Public Fill

Safe patterns for publicly reachable AI-assisted form submission.

CLI

Command-line setup and reproducible local testing.

MCP

Expose tools and context over Model Context Protocol.

Skills

Design reusable capability modules for multi-agent workflows.