Source

Agent capabilities & guardrails — found from sitemap — Relevance AI

Checked for Relevance AI on 26 Oct 2026

Page: https://relevanceai.com/relevance-academy/quality-control-for-ai-agents
Checked: 26 Oct 2026, 18:46 UTC
How we may use it: Public page, crawling permitted

Technical details

type: page
http status: 200
content hash: sha256:c91c95944ee1c9ce29acde7441726161f80de161e30a42123fa5b6db03eeccb5
permission: robots_ok
screenshot: Screenshot on file (internal exhibit, not published)

Cited by

Knowledge search step Report an error

“Relevance provides a knowledge search step in our tool builder”
Query refinement step Report an error

“Query Refinement: add a LLM step and give it a prompt that asks it to refine a user's free-form query into a more effective search query.”
Vector search Report an error

“Vector Search: Add a knowledge search step where the refined query can be used in a vector search of a knowledge table.”
Result validation step Report an error

“Result Validation and Summarization: Add a final LLM step to process to validate and summarize the search results.”
Vector search always returns Report an error

“it always returns results, even if none are truly relevant”
Hallucination reduction Report an error

“This reduces the risk of irrelevant or hallucinated responses.”
Docs channels Report an error

“Documentation Changelog API & MCP”
API mcp Report an error

“API & MCP”
Custom actions gpts Report an error

“Custom Actions for GPTs”
Multi agent systems Report an error

“AI Agents AI Workforce Multi-Agent Systems AI Tools AI BDR Agent”
Functions Report an error

“Sales Marketing Operations Research Support”
Trust center Report an error

“Trust Center”
Policies Report an error

“Privacy policy Security policy Terms”