Treat prompts like the code they really are: version control, evals on every change, staged rollouts, one-click rollback, and per-prompt observability. Call any prompt by stable ID — swap models without redeploying.
Every edit is an immutable version. Diff, branch, merge, tag. Pin a version to production while you iterate on staging.
Define test cases once. Every change runs the suite. Regressions block the merge — same workflow as your code repo.
Call any prompt with prompsy.run('my-prompt'). TypeScript and Python SDKs with full type-safety on variables.
Conditional branches, retries with backoff, human approval gates, webhook fan-out. Versioned and observable end-to-end.
Every run logged with model, latency, tokens, and output. Tail in real time, query historical, ship to Datadog or OTel.
Bring your own keys. Per-prompt PII redaction. Configurable retention. Audit log of every read, write, and run.
Write the prompt in Prompsy. Define typed variables and structured output schema.
Add test cases. Run on every change. Set regression thresholds for ship gates.
Promote to staging via tag. Bakeoff models, dial latency vs. cost vs. quality.
Pin the version to prod. Stream traces. Roll back in one click if anything dips.
We were managing prompts in YAML files in a monorepo. Every model change was a deploy. With Prompsy we ship a prompt update without touching our codebase — and we can prove it was tested.
Enterprise plans support BYOC (bring your own cloud) on AWS, GCP, or Azure. The runtime, eval workers, and database all run in your VPC.
Every promoted version stays immutable. Rollback is a single API call (or a click) that swaps the prod pin to the previous version. New requests pick it up within seconds across our edge cache.
Built-in semantic + exact-match caching with TTL controls. Per-prompt and per-org rate limits. Costs are tracked per call and rolled up by team and prompt.
Yes. The Prompsy GitHub action runs your eval suite on every PR that touches a prompt and posts results inline. Configure ship gates for required pass rates.
OpenAI, Anthropic, Google, Mistral, Together, Replicate, plus any OpenAI-compatible endpoint. Add your private model with a base URL and an API key.