Skip to main content
Wayfinder
…

A second opinion for every action.

One call turns any text in 100+ languages into a calibrated verdict: act, review, escalate, block.

One call answers every question.

Department, urgency, churn, refund. Scored together, routed by language before the model ever sees it.

Try it in the console
100+

Languages with a router that picks the right checkpoint per request.

33ms

A single decision on one GPU. Batched, about a millisecond each.

act
review
escalate
block

Thresholds you set. ≥ 0.85 moves on its own. Everything else finds a human.

$0

Self-hosted weights, Apache-2.0. Safety stops being a line item.

Calibrated, not merely confident.

Probabilities trained with proper scoring rules, then temperature-fit on held-out data. When the gate says 0.89, it means it.

See live metrics
0.081

Expected calibration error after fitting. Down from 0.466 raw.

45/51

Languages clearing 3× random, routed automatically.

7×

Faster than hosted LLM judges at zero marginal cost.

Confidence you can wire to automation.

From policy to verdict in three moves.

Write the policy

A few typed questions in YAML: choice, score, or yes-or-no. No training, no prompts to babysit.

Make one call

Send any state in any language. The router picks the checkpoint; every question scores in a single forward pass.

Act on the verdict

High confidence moves on its own. Everything else lands in front of a human with the reason attached.

Four policies cover nearly everything.

LLM firewall

Jailbreaks, injections and leaks get blocked before your model sees them.

Verdicts, fresh from the gate.

“Billed twice for March. Refund it today or we cancel.”

act
0.89 · billing, critical, churn risk

Ship calibrated doubt.

One container, one policy file, every stack you already use.