Skip to main content

​
What is Bitfab?

Bitfab helps you understand what your AI is doing and iterate on it faster. You capture traces with our SDK, then improve your code and prompts directly from your coding agent — with the web portal available to dive deeper when you need it.
1

Capture

Add the SDK to capture inputs, outputs, errors, and context for every AI call. 1-shot setup with the Claude plugin or MCP — your coding agent reads your codebase, finds AI workflows, instruments them, and creates replay scripts.
2

Improve

Ask your coding agent to find failures, diagnose issues, and fix your code and prompts. Replay production traces through updated code to verify changes work before you ship.

​
Quick Start

Connect your coding agent to get started. There are two ways:

Claude Code Plugin

Install the Bitfab plugin — handles setup, authentication, and instrumentation automatically

MCP (Other Agents)

Connect Cursor, Codex, Windsurf, or any MCP-compatible agent
Or go to the setup page for guided configuration.

​
How It Works

​
Capture

Your coding agent handles the entire setup:
  1. Instrument — Reads your codebase, finds all AI workflows, and adds tracing with minimal diffs
  2. Create replay scripts — Generates scripts so you can regression-test against production data with one command
  3. Get traces — Run your app and traces flow into Bitfab automatically

​
Improve

Once traces are flowing, improve directly from your coding agent:
  1. Find issues — Ask your agent to diagnose failures, search traces, and pinpoint what’s going wrong
  2. Fix code and prompts — Your agent suggests fixes and replays production traces through updated code to verify the changes work
  3. Dive deeper — Use the web portal to inspect individual traces, compare outputs side-by-side, and explore patterns across your data