See it in action

Each demo is standalone. No API keys required. Run in the browser or locally.

End-to-End

The full workflow

Version, bundle, promote, attribute, and analyze — the complete pipeline. 5 customer requests, two prompt versions, one behavioral divergence.

Watch the demo →
PromptOps

Version your prompts in 60 seconds

A code review agent evolves through four prompt versions. PATCH, MINOR, and MAJOR bumps — all auto-detected. Zero manual tagging.

Watch the demo →
ReleaseOps

Bundle, promote, and rollback

A sales qualification agent flows through dev, staging, and prod. One threshold change floods the pipeline — instant rollback with full audit trail.

Watch the demo →
ReleaseOps

Quality gates that block bad releases

A fintech loan agent auto-approves a $500K mortgage that should go to underwriting. The eval gate catches the compliance violation before staging.

Watch the demo →
ReleaseOps

Which prompt line changed the behavior?

A recruiting agent screens the same candidate differently across two versions. Attribution traces the decision to Line 7, where the experience threshold changed.

Watch the demo →
ReleaseOps

What changed between versions?

An IT helpdesk agent handles tickets two ways: conservative (route to humans) vs autonomous (self-resolve). Analytics quantifies the behavioral shift.

Watch the demo →

Try it yourself

All demos run locally with no API keys.

pip install llmhq-promptops llmhq-releaseops
git clone https://github.com/llmhq-hub/releaseops
cd releaseops/examples
python demo.py