Docs
OfficialJev Practices & Patterns
Pattern: Confidence-Gated Routing
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.
- Format
- Docs
- Reading time
- 2 min
- Published by
- TypeSafe AI
- Last verified
- Sep 2026
Highlights
- Any intent below 0.6 confidence routes to a support agent before the action is considered.
- check_balance is safe at 0.6 because the worst case is a wrong read-out.
- approve_transfer needs more than 0.85, otherwise the user confirms first.
- Thresholds are set per action by the consequences of a wrong classification.
Quickstart
python
if action.confidence < 0.6:
route_to_support_agent(account_id)
elif action.choice == "check_balance":
show_balance(account_id)
elif action.choice == "approve_transfer":
if action.confidence > 0.85:
approve_transfer(account_id)
else:
ask_user_to_confirm("Just to confirm: you would like to approve this transfer?")Watch out
Confidence is not permission: a high-confidence answer can still be wrong, so keep hard limits next to the model for irreversible actions.
Questions about this entry
Short answers drawn from the linked project or page.
Because the cost of being wrong differs. The voice-banking example allows check_balance at 0.6 — the worst case is a wrong read-out — but requires more than 0.85 before approving a transfer, and routes anything below 0.6 to a support agent.
No. The caveat says confidence is not permission: a high-confidence answer can still be wrong, so irreversible actions should keep hard limits in code beside the model rather than trusting the number alone.
The answer tells you what to do and the confidence tells you whether to act, so confidence becomes a second axis alongside the classification.
A 0.6 floor routes to a human when confidence is below it, catching anything the model is genuinely uncertain about before per-action thresholds apply.
The worst case of a wrong balance read is the user hearing it out, while a wrong transfer is high stakes, so approving needs above 0.85 confidence or the system asks the user to confirm.
Ask the user to confirm intent first, as the example does before approving a transfer, rather than acting automatically or dropping straight to an agent.
Systems that must be both reliable and safe, where each action type gets its own threshold based on the consequences of acting on a wrong classification.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: OpenRouter Decision Model Rankings
X: herdr + jev, an agent router
X: A group chat bot with decision room routing
More Jev resources like this
Classify intent with a Choice and complexity with a Score, then send each branch to deterministic code, a specialist model, or a person, with a 0.5 intent-confidence floor.
Jev Practices & PatternsDocs#official#patterns#routing
Official
Ask everything the system might need in one request, then let code throw away what it does not use. The ticket-triage example sends a category plus four speculative questions in parallel.
Jev Practices & PatternsDocs#official#patterns#batching
Official
The yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is needed. True and false criteria pin down subtle boundaries.
Jev Practices & PatternsDocs#official#primitives#noul
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
Architectural patterns for System One systems: speculative fan-out, confidence-gated routing, composite scoring, and intent routing.
Jev Practices & PatternsDocs#official#patterns#architecture
Official
An independent calibration study of Jev against a frontier fallback on Banking77 and Web of Science, packaged as the janus-decide tool that measures a routing threshold on your own data instead of shipping a default one.
Jev Practices & Patterns#community#python#routing
Community
FirasSX914/JanusPython
FirasSX914/JanusPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.