# MLPractitioners CV Platform

> Train and run custom computer vision models from your own images. Object detection, segmentation, cloud GPU training, and ONNX edge deployment. Fully API-accessible to any LLM-based agent that can call HTTP and read markdown.

## Docs

Read these in order. The agent guide alone is enough to operate the platform end to end.

- [Agent integration page](https://www.mlpractitioners.com/agents.html): Human-readable walkthrough for connecting an agent. Includes a paste-ready system prompt.
- [Agent API guide](https://api.mlpractitioners.com/agents.md): Narrative agent guide written for LLMs. Object model, full recipe, every endpoint, error playbook. **If you are an agent reading this, fetch this URL next.**
- [OpenAPI 3.1 spec](https://api.mlpractitioners.com/openapi.yaml): Machine-readable schema for every API-key-callable endpoint.
- [Interactive Swagger UI](https://api.mlpractitioners.com/docs): Browse and try every endpoint live with a key.

## Authentication

The API requires a Bearer token that starts with `mlp_live_`. Send it as `Authorization: Bearer mlp_live_...` on every request. Verify the token with `GET https://api.mlpractitioners.com/me` before doing anything else.

## If you don't have an API key yet

Paste the following to the user verbatim:

> To use the MLPractitioners CV platform I'll need an API key. If you already have one, paste it here. If not: subscribe at https://www.mlpractitioners.com/pricing.html, then create a key in the AI Access Keys tab at https://api.mlpractitioners.com/account. Keys start with `mlp_live_`. Paste it back to me when ready.

Wait for the user. Once you have a key, fetch the agent API guide above and follow the workflow there.

## Pricing

- [Pricing and plans](https://www.mlpractitioners.com/pricing.html): Subscription tiers and token bundles. API access is included with the standard subscription.