PRIVATE BETA · WAITLIST OPEN

Stop guessing if the cheap model works.
Prove it does.

Point Reprompt at your pipeline's real execution traces, tell it which model you want to switch to, and it finds — and proves — a prompt that gets you the same results for less.

reprompt migrate --from gpt-4o --to qwen2.5-72b (on-prem)
The problem

AI models keep changing. Your prompts don't.

Every few months a cheaper or better model comes out. But the prompt your team spent weeks tuning was written for the old one — and the exact same words can give you a different answer on the new one. That's not a "your pipeline" problem. It happens to every team, on every model change.

Your prompt Model you tuned for Model you switch to ✓ Same result what you expect ⚠ Different result same prompt, new model
Same prompt. Different model. Different answer — every time a model changes underneath you.
What you get

Migration you can measure.

[trace]

Trace import → visual DAG

Drop in your pipeline's real execution logs. Reprompt auto-builds a visual dependency graph of every stage, then shows it live and animated as optimization runs — generating, critiquing, refining, scoring — colored by status.

[prism]

Prism optimizer

A self-evolving prompt optimizer that mutates, critiques and refines candidates across multiple rounds until they match your original output — judged by an independent AI model, never the one being tested, so it can't grade its own homework.

[score]

Three-way scoring

Deterministic checks, semantic embedding similarity and an AI judge, combined into one composite match score per candidate. A number you can defend, not a vibe.

[compare]

Multi-model comparison

Test several target models side by side per stage — and pick a different model for each stage. A curated model library with cost, context window and prompt-style cards; bring your own API keys.

[diff]

Before/after diff & data explorer

See exactly what changed between your original prompt and the winning one, and browse every stage's inputs, outputs and costs across all test runs in a spreadsheet-style explorer.

[safety]

Rubric gates & budget guardrails

Auto-generated, human-editable acceptance criteria per stage, with an approval gate before any migration runs — and automatic budget limits so an optimization run can never spend unbounded API costs.

How it works

Point it at your pipeline. Watch it prove the migration.

Eight steps, most of them automatic. You approve two decisions — what "correct" means, and which model wins.

01 / import
Import your pipeline

You upload real execution traces — actual logs from your pipeline running in production or testing, inputs, prompts, outputs, per stage. Reprompt parses these into a formal pipeline structure automatically: it detects each stage, figures out which stages depend on which others, and builds a visual dependency graph. No manual mapping required.

02 / review
Review the pipeline visually

Your whole pipeline appears as an interactive node graph — every stage, which model it currently uses, token counts, latency. Browse the raw data behind it: every input, output and cost per stage, across every trace you imported, down to any individual run.

03 / define
Define what "correct" means, per stage

Before touching any model, Reprompt auto-generates a rubric per stage — hard rules (must match schema, no hallucinated IDs) plus judged criteria like tone and reasoning quality. You review and approve these first, so the system optimizes toward a real target, not "seems similar."

04 / target
Pick your target model(s)

Choose the cheaper model(s) to migrate to — compare several candidates at once, or assign a different model to each stage if one needs more capability than another. Bring your own key for any provider: OpenAI, Anthropic, Gemini, or self-hosted.

05 / optimize
Prism optimizes automatically

For each stage: generate several prompt variants → cheap first-pass score to cut the weak ones → an independent judge critiques exactly why they failed → rewrite based on that critique → repeat for several rounds → final sweep across phrasing and format → pick the winner. The judge is never the model being tested, so it can't grade its own homework.

06 / watch
Watch it happen, live

An animated version of the pipeline graph shows which stage is working right now and exactly what it's doing — generating, critiquing, refining, running the final sweep — plus a running activity log and the actual reasoning text, in real time. Not a spinner.

07 / decide
See exactly what changed

A before/after comparison: your original prompt next to the winning one, diff-highlighted, with score, cost and latency for each. Tested multiple models? A side-by-side comparison gives a clear recommendation — not just raw numbers with no verdict.

08 / safety
Stay safe by default

Budget limits are enforced automatically in the background, so a run can never spend unbounded API cost chasing a perfect score. You don't configure this — it just protects you.

Early access

Be first when the beta opens.

We're onboarding a small group of teams running multi-stage LLM pipelines. Tell us where to reach you.

✓ You're on the list. We'll be in touch.
No spam. One email when your invite is ready.