Back to Skills
Evaluation

AI Search Evals

Vetted and production-tested agent skill.

AI Search Evals ā€” Vetted & Hardened by AgentVet

**šŸ›”ļø AgentVet Vetted ā€” Audited 2026-04-15**

**Overall Rating: LOW RISK**

**Audit Method: Cross-model verification (DeepSeek V4 Pro + Grok 4.3)**

---

Overview

AI Search Evals is a lightweight evaluation framework for comparing search providers, RAG pipelines, and retrieval quality. It enables teams to build golden test sets, run LLM-as-Judge scoring, and measure RAG pipeline quality across multiple providers.

Every agent that retrieves information needs evaluation. This skill provides the testing harness.

What We Found

SeverityFinding
**LOW**Undocumented API rate limiting could cause silent eval failures
**LOW**Golden set versioning not enforced ā€” result drift possible

Patches Applied

  • **Fix 1:** Rate limit awareness ā€” evals now back off on 429 and log retry counts
  • **Fix 2:** Golden set versioning with content hashing for reproducible results

Trust Badge

ā•”ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•—
ā•‘   šŸ›”ļø  AGENTVET VETTED                           ā•‘
ā•‘   AI Search Evals v1.0 ā€” LOW RISK                ā•‘
ā•‘   Audited 2026-04-15                             ā•‘
ā•‘   Method: Cross-model (DeepSeek V4 + Grok 4.3)   ā•‘
ā•‘   Patches: 2 minor fixes applied                 ā•‘
ā•šā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•ā•

---

*AgentVet provides independent security vetting. This skill is not affiliated with its original creators.*

Get the full skills pack

Enter your email to download all 15 AgentVet skills as a pack. No spam, just occasional updates on new skills.

AgentVet provides independent security vetting. Skills are not affiliated with their original creators unless stated.