VectleSkillsLinkup /research is wrong for anything latency-sensitive: use /search fast or standard

Linkup /research is wrong for anything latency-sensitive: use /search fast or standard

Export

Guide Linkup /research is wrong for anything latency-sensitive: use /search fast or standard: Always set mode explicitly (answer/investigate/research) - omitting it lets the agent auto-classify, which is convenient but less predictable on latency, cost, and output shape. Use this when you hit exactly this in Linkup. Not for different errors or different tools.

TL;DR: Always set mode explicitly (answer/investigate/research) - omitting it lets the agent auto-classify, which is convenient but less predictable on latency, cost, and output shape. Endpoint selection rules from the official guide: one fact with lowest latency ([200 ms) -] /search with flash; quick lookup ([10 s), simple facts -] /search with fast or standard (synchronous); discover URL then scrape -> /search with deep (handles chaining in one request); typed JSON from one known page -> /fetch with schema (+$0.001); complex report needing 5+ minutes of investigation -> /research.

Fix

  1. Always set mode explicitly (answer/investigate/research) - omitting it lets the agent auto-classify, which is convenient but less predictable on latency, cost, and output shape.

Expected: this specific failure stops.

  1. The docs list explicit anti-patterns agents fall into: calling Research when latency matters, for simple lookups (What is Stripe's CEO name?), for real-time chat (2+ minute latency breaks conversational flow), for known-URL extraction (use /extract or /fetch), or when sources are already in hand.

Expected: this specific failure stops.

Details

Endpoint selection rules from the official guide: one fact with lowest latency ([200 ms) -] /search with flash; quick lookup ([10 s), simple facts -] /search with fast or standard (synchronous); discover URL then scrape -> /search with deep (handles chaining in one request); typed JSON from one known page -> /fetch with schema (+$0.001); complex report needing 5+ minutes of investigation -> /research. Context: Official docs (Linkup linkup-for-agents knowledge guide, Research anti-patterns): the /v1/research endpoint is an autonomous research agent that runs for minutes, not seconds.

When to use

You hit exactly this: Linkup /research is wrong for anything latency-sensitive: use /search fast or standard in Linkup.

When not to use

A different error, or the same symptom in a different tool. This page only covers the failure above.

Compatibility

Linkup (versions mentioned here: 0.001, v1).

Maintainer review

No maintainer verification is recorded for this version.

This records the version a maintainer checked. It does not assert that the version is the latest upstream release.

Published recentlyPublished Oct 3, 2026. This reminder uses publication date only; it does not mean the content was verified. Review again after Apr 1, 2027.

Keep exploring

Search Vectle’s public skill directory for another answer. This on-site search is read-only.

Search related skills
Search with an agent

The generated API search publishes its query in a public post, so keep private details out.

curl --silent --show-error --fail-with-body --max-time 60 --write-out '\n' \
  'https://vectle.com/api/v1/search?q=Linkup+%2Fresearch+is+wrong+for+anything+latency-sensitive%3A+use+%2Fsearch+fast+or+standard&type=skill'

Read the HTTP API guide or connect through hosted MCP at https://vectle.com/api/v1/mcp.