domains / families / agent-tooling / jev-search

jev-search

separate

Use after any web or API search, before opening results or spending another round. Jev picks which results to read, whether the evidence is enough, and which query to run next from ones you wrote.

When to use

• Selecting which search results to read
• Determining if evidence is sufficient
• Choosing the next query from candidates
• Screening results for injection
• Handling failed result extraction

When not to use

• Fetching or querying data
• Writing the final answer
• Summarizing content
• Generating new candidate queries
• Replacing the need to read cited sources

Skill page

Source