Playground

Run flows in the browser.

Write a PrismPath flow in Markdown, script the worker outcomes, and watch the JS kernel parse, check, and route through your graph. It runs entirely client-side, the same module our cross-language conformance vectors certify. Nothing you type leaves this page.

Build a flow, hit Share, and send the link. The entire flow is compressed into the URL; no account, no server storage, nothing to sign up for. Anyone with the link sees exactly what you see.

Write a flow, click Share; the entire flow is compressed into the URL. No server, no account, no storage. Send the link to anyone.

Consumed in visit order; {"__raise__": "msg"} throws an error.

P0every reachable edge is decidable: zero ML, runs anywhere (this page is the proof)

Targets · one flow, where it runs

✓
Python reference
✓
Portable · JS / Rust / Go
✓
Level M hardware · FPGA / eBPF

✓ predicates safe & parseable

nodeedgetiercondition
classify→ human_reviewdeterministicwhen category == "billing_dispute" and amount > 500
classify→ billingdeterministicwhen category in ("billing", "billing_dispute")
classify→ outagedeterministicwhen category == "outage"
classify→ retentiondeterministicwhen sentiment == "angry"
classify→ generaldeterministicelse
human_reviewterminal
billingterminal
outageterminal
retentionterminal
generalterminal

Pick a node and press ◇ Prove reachability. Proven client-side, no model, no server.

Press ▶ Run to replay the scripted outcomes.

P1

Semantic routing, locked

This support router has no when predicates; it routes on meaning. The condition vectors are pre-baked into a lockfile, so the engine only embeds the incoming message and compares. The scripted messages below run the real routing with zero model download. Load the full embedder to route your own text.

Try a customer message

0.22

If the top score falls below this, the engine escalates to a human instead of guessing.

Pick a message above to watch the router score every desk and choose.

Route your own text

Downloads the MiniLM model (~30 MB, one-time) and runs it in your browser via ONNX Runtime Web. Still nothing leaves your machine; the model comes to you.

To see what a policy like this costs on the wire, the Facet page has the estimator and the measurements.