- Home
- AI Prompt Generators
- GEPAzilla
On the recordRead 10 Oct 202617 facts
GEPAzilla
On the record
- API key requirement
- The project README says an AI Gateway API key is required for GEPA runs, scorer previews, and model discovery.github.com · read 10 Oct 2026
- Built-in latency metric
- GEPA optimizes request latency internally, and the Results tab always includes a latency metric.gepazilla.com · read 10 Oct 2026
- Data handling
- The README says telemetry stays in the browser, telemetry events are not sent to a remote service, and run data is not exfiltrated.github.com · read 10 Oct 2026
- Data import limit
- Dataset tools currently support copying or pasting JSON payloads from the clipboard.github.com · read 4 Oct 2026
- Dataset format limit
- Dataset tools currently support copying or pasting JSON payloads from the clipboard.github.com · read 10 Oct 2026
- Dataset input
- Users can load their own rows or start with the sample dataset.gepazilla.com · read 10 Oct 2026
- Deployment
- The README describes the application as a standard Next.js project that can be built and started locally.github.com · read 10 Oct 2026
- Diagnostics
- Results include scorer failure rates, averages, and common notes, alongside candidate prompts and iteration trends.github.com · read 4 Oct 2026
- Gateway integration
- The README specifies a Vercel AI Gateway credential for the required API key.github.com · read 10 Oct 2026
- Intended users
- The maker describes the console as a way for curious builders to experiment with prompt optimization using their own API key.github.com · read 4 Oct 2026
- License
- The repository states that GEPAzilla is released under the MIT License.github.com · read 10 Oct 2026
- Model access
- The project requires users to supply an AI Gateway API key for GEPA runs, scorer previews, and model discovery; its README specifies Vercel AI Gateway.github.com · read 4 Oct 2026
- Purpose
- GEPAzilla is an open-source GEPA prompt optimizer that uses datasets and custom metrics to find stronger prompts.gepazilla.com · read 10 Oct 2026
- Scoring
- It supports combining deterministic checks with LLM judges and weighting or duplicating scorers.gepazilla.com · read 10 Oct 2026
- Telemetry
- The maker says telemetry stays local and includes tokens, routing, costs, and errors for inspection.gepazilla.com · read 10 Oct 2026
- Validation
- Validation rows are kept out of reflection and used to rank candidate prompts on the Pareto frontier.gepazilla.com · read 4 Oct 2026
- Validation data
- Validation rows are kept untouched during reflection and used to rank candidates on the Pareto frontier.gepazilla.com · read 10 Oct 2026
