poddub turns what your company ships into a short podcast episode.
Paste release notes, a memo or an agent's summary, approve the script, and your team hears it in the app or any podcast app.
Evaluating LLM output by eyeballing it works... until it doesn’t.
Pipevals is an open-source pipeline builder for AI evaluation.
Trigger it with a single HTTP POST from your existing code, piping data through AI judges, scoring, and human review.
Every run executes durably, with step-by-step results. Dashboards automatically track trends, distributions, and pass rates.
Compare models, test prompts, and catch regressions.
Self-hosted. MIT-licensed.
