Tool router
Pick the right tool for a request without an LLM tool-calling round trip.
Maps a request to one tool from your list, with confidence. Ambiguous requests get a clarifying question, and anything that sends, deletes or changes something on the user's behalf asks for confirmation first. Edit the options to match your own tools.
Try it live
Real calls to Jev. Pick an example or paste your own.
Pick an example or paste your own input, then run it.
Under the hood
Every question and rule, in the open. Fork it to change any of them.
What it asks
Reads request, then asks 2 questions in one call.
- Q1ToolPick one
Which tool should handle the
request?Web searchCalendarEmailKnowledge baseCalculatorNo toolUnclear - Q2Changes somethingYes / no
Would fulfilling the
requestsend, delete, buy or change something on the user's behalf?
How it decides
Rules run in code, top to bottom. The first one that matches gives the verdict.
- 1If Tool: confidence < 0.5Ask to clarify
- 2If Tool is UnclearAsk to clarify
- 3If Changes something ≥ 0.7Confirm first
- 4Otherwisethe answer to “Tool”
- ·DefaultAsk to clarify
Call it from your code
Every template runs as-is with an API key, no setup: POST /api/v1/judges/tool-router/run.
curl -X POST https://tryevally.com/api/v1/judges/tool-router/run \ -H "Authorization: Bearer $EVALLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "request": "Move my 3pm with Priya to tomorrow morning" }}'Seen in the wild
Community builds on Jev that use this pattern. Not affiliated with Evally.
More in Agents
- Agents
Tool-call firewall
Judge every agent tool call before it touches your machine: allow, ask a human, or deny.
AllowAsk a humanDeny10 questions - Agents
Is the task done?
Don't trust an agent's "done". Check the transcript for proof, open errors and skipped work.
DoneDone, but unprovenNot done5 questions - Agents
Agent loop & drift detector
Spot an agent that's stuck in a loop, drifting off-goal, or blocked, and stop wasting tokens.
ContinueNudge: change approachStop and escalate4 questions - Agents
Model router
Send each prompt to the cheapest model that can handle it.
Small modelMid-size modelFrontier model+14 questions - Agents
Context relevance filter
Decide what an agent keeps in context: keep, compress or drop each chunk.
KeepCompressDrop3 questions - Agents
Memory gate
Decide which messages in an agent's chat are worth remembering next session, and which change what it already knows.
Save itReplace a lineSkip4 questions