Free local tool
Experiment Protocol Builder
Build an exportable LLM experiment protocol and results-table template for testing Claude prompts, variants, fixtures, and success criteria.
Key facts
Cite factsFact
Browser-only protocol
The builder runs entirely in the browser. The prompt variants and criteria you type are not uploaded.
Fact
Evidence table included
The export includes fixture, variant, model, timestamp, score, notes, and raw-output fields.
Fact
Controls before claims
The generated card asks you to lock model, source state, tools, fixtures, and scoring before reading outputs.
Interactive builder
Generate an experiment card
Protocol output
Results table template
| fixture_id | variant | run | model | score | notes | raw_output_ref |
|---|
How to Use This Tool
- Define the behavior question. Write the narrow Claude behavior you want to test and choose the surface being tested.
- Add prompt variants and criteria. Paste two or more variants, set the number of runs per fixture, and define measurable success criteria.
- Export the protocol. Copy or download the generated Markdown protocol and results table before running the experiment.
Tool FAQ
Does the builder run Claude?
No. It creates the protocol and results table. You run the experiment in your chosen Claude surface and paste raw evidence into your own records.
Can I use it for non-Claude LLMs?
Yes. The tool is written for Curious Claude readers, but the protocol fields work for any LLM if you record the model, surface, and source state.
What should I do before publishing a result?
Preserve the exact prompt, fixtures, model ID, date, source state, scoring rule, raw output, and scorer notes. Without those fields, publish it as a protocol note, not a result.
Internal links