Skip to main content
Prompt Baking encodes prompt behavior directly into model weights. Fine-tune AI models with the convenience of prompt engineering. You shouldn’t need a PhD to teach your AI what it needs to know or wait for someone else’s model update to give you what you need. With Bread, your model permanently inherits the prompted behavior with zero input tokens at inference time.
The value: After baking, your model can exhibit prompted behavior with zero input tokens. The skills live in the weights, not in runtime prompts.

​
Choose Your Path

  • bgit
  • SDK
  • API

Quickstart

Bake your first model with bgit

How bgit Works

Understand git-based model evolution

Configuration

YAML configuration reference

Workflows

Advanced workflows and patterns
bgit is a git-native interface that makes AI model baking feel like regular software development. Version control your model weights with familiar git commands.
  • One file = One model (YAML configuration)
  • Commits = Model versions
  • Branches = Experiments
  • Git history = Complete audit trail

​
Core Concepts

Repositories

Like GitHub, these repos hold all of a model’s bake data

Prompts

The actual prompts you want to “bake in”

Stim Data

User prompts the prompted model would receive

Rollout Jobs

Responses from the prompted model to the stim data

Targets

The composition of stim & rollout for a given prompt

Bakes

Configuration for your bake with rollout data

​
Full Process: Prompt, Stim, Rollout, Bake

1

Prompt

Specify the prompts to bake in
2

Stim

Run stim jobs to create synthetic dataset
3

Rollout

Run rollout jobs to get model responses to stim
4

Bake

Configure and run bake jobs for model training

​
Need Help?

GitHub Repository

Check out our public repo to start baking today

Understanding Baking

Learn how prompt baking works