# Roboflow AI integration on Definable

> Build and use computer vision models fast with Roboflow.

## What this connects

Build and use computer vision models fast with Roboflow. Train, deploy, and run inference on object detection, classification, and segmentation models.

Vendor: https://roboflow.com/

## Tools available

**7** tools available. First 7:

- `ROBOFLOW_DESCRIBE_WORKFLOW_INTERFACE` — Describe Workflow Interface — Tool to describe the interface of a workflow specification. Use when you need to understand the inputs, outputs, and types for a Roboflow workflow definition.
- `ROBOFLOW_GET_EXECUTION_ENGINE_VERSIONS` — Get Execution Engine Versions — Tool to retrieve available Execution Engine versions from Roboflow workflows API. Use when you need to check which execution engine versions are supported for workflow processing.
- `ROBOFLOW_GET_SERVER_INFO` — Get Server Info — Tool to retrieve information about the Roboflow inference server. Use when you need to check the server version, name, or unique identifier.
- `ROBOFLOW_GET_SERVER_METRICS` — Get Server Metrics — Tool to retrieve Prometheus metrics from the Roboflow inference server. Use when monitoring server performance, tracking inference statistics, or debugging server health issues.
- `ROBOFLOW_GET_WORKFLOW_SCHEMA` — Get Workflow Schema — Tool to fetch the workflows block schema from Roboflow. Use when you need to retrieve the complete schema definition for workflow blocks.
- `ROBOFLOW_RUN_WORKFLOW` — Run Workflow — Tool to run a workflow specification with provided inputs. Use when you need to execute a custom Roboflow workflow pipeline for image processing, model inference, or other computer vision tasks.
- `ROBOFLOW_VALIDATE_WORKFLOW` — Validate Workflow — Tool to validate a Roboflow workflow specification before execution. Use this to check if your workflow definition is syntactically correct and properly structured.

## Auth

Auth schemes: `API_KEY`.

## How agents use Roboflow

Inside a Definable workflow, Roboflow is one of the tools the **Distributor specialist** can call. Example coordination patterns:

- **Researcher → Roboflow** — the Researcher (GPT-5.5) pulls context from Roboflow (records, threads, documents), synthesises findings, and briefs the rest of the team.
- **Writer → Distributor → Roboflow** — the Writer (Claude Opus 4.7) drafts copy in brand voice, the Verifier passes it, then the Distributor writes the result into Roboflow (create record, post message, draft email).
- **Designer / Engineer → Distributor → Roboflow** — the Designer ships an asset or the Engineer ships a code change, the Distributor delivers it via Roboflow (attach file, open PR comment, post status).

The Verifier checks every Roboflow call. On rate limit, schema drift, or auth refresh it self-heals and retries — the workflow completes without manual intervention.

## Categories

- artificial intelligence — https://definable.ai/apps/category/artificial-intelligence/
- ai models — https://definable.ai/apps/category/ai-models/

## Related

- HTML page: https://definable.ai/apps/roboflow/
- Same category (artificial intelligence): https://definable.ai/apps/category/artificial-intelligence/
- All integrations: https://definable.ai/apps/
- Workflow (multi-agent loop): https://definable.ai/workflow/
- Apps llms.txt index: https://definable.ai/llms-apps.txt