Jev glossary
PatternsConfidence routing
Confidence-gated routing
Use the answer to decide what to do and confidence to decide whether to act, with per-action thresholds set by the cost of being wrong.
- Category
- Patterns
- Also known as
- Confidence routing
- Reading time
- 1 min
- Related terms
- 5
- Directory entries
- 37
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The voice-banking example routes any intent below 0.6 confidence to a support agent before the action is considered. Above that, check_balance is safe at 0.6 because the worst case is a wrong read-out, while approve_transfer needs more than 0.85 or the user confirms first.
Confidence is not permission: a high-confidence answer can still be wrong, so irreversible actions keep hard limits in code next to the model.
Tagspatternsconfidencerouting
Related terms
Definitions that connect to this one.
Confidence gateA threshold on confidence that decides whether code acts, confirms first, or escalates to a person or a bigger model.Answers & ConfidenceThresholdThe value your code compares against a score, a Noul probability, or a confidence to turn an answer into an action.Answers & ConfidenceIntent routingClassify intent with a Choice and complexity with a Score, then send each branch to deterministic code, a specialist model, or a person.PatternsConfidence floorA baseline below which code never acts on an answer, regardless of what the answer says.Answers & ConfidenceHuman reviewThe explicit path for uncertain or high-stakes cases: route to a person instead of acting on a low-confidence answer.Patterns
From the Jev directory
Directory entries that go deeper on this term.
Use the answer to decide what to do and confidence to decide whether to act: the voice-banking example routes below 0.6 to a human and needs 0.85 or more to auto-approve a transfer.
Jev Practices & PatternsDocs#official#patterns#confidence
Official
How TypeSafe reports certainty, how it differs from probability, and how to use it architecturally to gate and route decisions.
Jev Practices & PatternsDocs#official#confidence#routing
Official
The Python response models: SystemOneResponse groups answers by id, and records the model name, token usage, and request id.
Jev Repos & SDKsDocs#official#docs#sdk
Official
A 3D robot that understands without generating text: one TypeSafe call per turn with nine typed questions, then code decides whether to act, ask, or shrug.
Jev CookbooksPlayground#community#playground#embodied-agent
Community
CLI that fits a per-question confidence threshold to a target accuracy on your own labeled data, verifies it on a held-out split, estimates how much traffic still needs an LLM, and re-checks locked thresholds in CI. It publishes no Jev results of its own.
Jev Practices & Patterns#community#python#calibration
Community
abhixhek/jevcalPython
abhixhek/jevcalPythonA Ruby client for TypeSafe's System One API that returns typed Noul, Choice, and Score answers, validates obvious input mistakes before spending a request, and pools HTTP connections across threads.
Jev Repos & SDKs#community#ruby#sdk
Community
joshmn/typesafe-sdkRuby
joshmn/typesafe-sdkRuby31 more matching entries in the full directory.
From the Jev AI model community
Posts from builders shipping with Jev right now.