Research desk router
Send each item in a research feed to the right desk: papers, repos or market news.
The routing step of an AI research team. One closed question decides which specialist agent reads each item, with a way out for anything no desk covers, so nothing gets forced into the wrong desk. Edit the desks to match your own agents.
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 title, text and source, then asks 1 question in one call.
- Q1DeskPick one
Which desk should read this item, judging by its
title, itstextand itssource?Papers deskRepos deskMarket deskNo desk
How it decides
Rules run in code, top to bottom. The first one that matches gives the verdict.
- 1If Desk: confidence ≥ 0.55the answer to “Desk”
- ·DefaultNo desk
Call it from your code
Every template runs as-is with an API key, no setup: POST /api/v1/judges/research-desk-router/run.
curl -X POST https://tryevally.com/api/v1/judges/research-desk-router/run \ -H "Authorization: Bearer $EVALLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "title": "Calibrated decision models beat LLM judges on 14 eval benchmarks", "text": "We introduce a System One model that answers typed questions with calibrated probabilities…", "source": "arxiv" }}'Seen in the wild
Community builds on Jev that use this pattern. Not affiliated with Evally.
- Jev + Claude agent team
- World Monitor
More in Research & data
- Research & data
Survey response coder
Code open-ended survey answers into themes and sentiment, thousands at a time.
PositiveNegativeMixed+18 questions - Research & data
Systematic review screener
Screen abstracts against your inclusion and exclusion criteria, one criterion at a time.
IncludeFull-text reviewExclude5 questions - Research & data
Sentiment & emotion
Sentiment, the dominant emotion, its intensity, and whether it's sarcastic.
Very negativeNegativeNeutral+24 questions - Research & data
Record matcher (dedupe)
Do these two records describe the same person, company or product?
MatchPossible matchDifferent4 questions - Research & data
News & event severity
Rate headlines by severity, topic and region, and alert on the ones that matter.
AlertWatchLog4 questions - Research & data
Novelty check: new, update or duplicate?
Check a fresh note against what you already know: new, an update, or a duplicate.
NewUpdateDuplicate1 questions