# Coolhand — COO for Your Agent Teams

Coolhand is the operational layer for AI teams. It captures human feedback on your AI's outputs and uses that signal to automatically improve your prompts and agents — cutting LLM costs 50–70% and building a quality & data advantage your competitors can't copy. With 2.5B+ tokens analyzed, Coolhand helps engineering teams log LLM requests across providers, collect structured human feedback, and automatically generate pull requests to improve prompt quality over time.

## How It Works

Coolhand operates as a five-stage pipeline that turns raw agentic data into actionable improvements:

1. **Agentic data** — LLM logs, tool outputs, human feedback, and outcome signals are emitted by your AI system
2. **Passively gathered** — the Coolhand API collects this data automatically, with no changes to your core application logic
3. **Expert analyzed** — five investigative agents (Cost analyst, Failure SWAT, Product analyst, AI engineer, Prompt maintainer) run in parallel to examine the data from different angles
4. **Executive reviewed** — findings are synthesized into a prioritized optimization plan
5. **Turned to results** — the plan is executed as agent fixes (pull requests, prompt updates) directly in your codebase

## What Coolhand Does

- **LLM Request Logging**: Capture every request and response from OpenAI, Anthropic, Google, and other providers through a single ingest endpoint. No SDK changes required for structured logging.
- **Human Feedback Collection**: Embed lightweight feedback widgets (thumbs up/down, corrections, ratings) directly in your product. Feedback is linked to the exact LLM request that generated the output.
- **Automated Prompt Improvement**: Coolhand analyzes feedback patterns and opens pull requests with suggested prompt improvements — closing the loop between user signals and model behavior.
- **Prompt Templates**: Manage and version your prompts as named templates. Track which version of a prompt generated which output.
- **Inference API Catalog**: A live, curated table of pricing and context window specs for 100+ LLM models. Updated as providers change their pricing.

## SDKs

Coolhand provides SDKs for the most common backend languages:

- **Ruby** — `gem "coolhand"`
- **Python** — `pip install coolhand`
- **Node.js** — `npm install coolhand`

Each SDK wraps your existing LLM calls with a single line of code and handles logging, feedback collection, and prompt template management.

## Getting Started

1. Sign up at [coolhandlabs.com](https://coolhandlabs.com)
2. Install the SDK for your language
3. Wrap your LLM calls with the Coolhand logger
4. Embed a feedback widget in your UI
5. Review feedback and apply suggested prompt improvements

## API

Coolhand exposes a REST API for all features. The full API reference is available at [coolhandlabs.com/docs](https://coolhandlabs.com/docs). The machine-readable OpenAPI spec is at [coolhandlabs.com/api-docs/v2/coolhand_api.yaml](https://coolhandlabs.com/api-docs/v2/coolhand_api.yaml).

Authentication uses an API key passed via the `X-API-Key` header.

## Pricing

| | Free | Pro | Power User |
|---|---|---|---|
| **Price** | $0 | $199/month | $1/million tokens |
| **Weekly token cap** | 10M tokens/week | 100M tokens/week | None |
| **Dashboard** | Cost insights dashboard | Cost & performance insights | Cost & performance insights |
| **Optimizations** | 5/week | No optimization cap | No optimization cap |
| **Direct code fixes (PRs)** | $2 each | 10/week included, then $1 each | Unlimited |
| **Data retention** | 21 days | 90 days | — |
| **HIPAA compliance** | — | — | ✓ |

Enterprise volume pricing is available — contact us at [coolhandlabs.com](https://coolhandlabs.com).

## MCP Integration

Coolhand exposes a Model Context Protocol (MCP) server at `https://coolhandlabs.com/mcp`. This allows AI coding assistants (Claude Code, Cursor, etc.) to interact directly with your Coolhand workspace — querying logs, managing templates, and reviewing feedback without leaving the assistant.

The public MCP endpoint at `https://coolhandlabs.com/mcp/public` provides access to the inference API catalog without authentication.

## Updates & Announcements

The latest news and incident reports from Coolhand are published at [coolhandlabs.com/updates](https://coolhandlabs.com/updates). Each post is available as rendered HTML and as a raw markdown file (append `.md` to the URL).