AI/ML●Mid
A Claude Code skill that scopes problems like Peter Naur
Naur's 1985 theory applied to AI agents, but it's just a prompt template.
Big BrainNiche Gem
spinchange
2014d ago
Back to browse
GitHub Repository
Find what your AI agent gets wrong — before you have a rubric. Qualitative eval for PMs.
3 starsPython
GEDD – Find what your AI agent gets wrong (before your users do)
by balasvce19855·May 31, 2026·2 points·0 comments
AI Analysis
●●SolidBig BrainSolve My Problem
Grounded theory methodology for AI evals before you have rubrics.
Strengths
- •Discovers failure modes you didn't anticipate through open coding
- •Two-persona workflow separates domain expertise from ML engineering
- •Tests against real deployed endpoint with latency and IAM included
Weaknesses
- •AWS sample repo, not a standalone product with ongoing support
- •Tied to Bedrock AgentCore and SageMaker, limits portability
Category
Target Audience
Product managers and ML engineers evaluating AI agents
Similar To
LangSmith · Arize Phoenix · Braintrust
Similar Projects
Data●●Solid
A skill to audit your dbt project for what an AI agent will get wrong
Catches AI-breaking dbt issues like conflicting revenue metrics and YAML/SQL mismatches.
Niche GemSolve My Problem
matthieu_bl
302d ago
Security●●Solid
Agent Skill Based on "Open Source Security at Astral"
Automates Astral's security framework into an agent skill that produces HTML reports.
Niche GemBig Brain
ramoz
302mo ago
Developer Tools●Mid
Agent-evals – Claude skill to build your own evals
Claude Skill for agent evals, but LangSmith and Arize already own this.
Solve My Problem
sauercrowd
911mo ago
Productivity●●Solid
Skill for structured deep research with Claude Code and Obsidian
Zettelkasten automation for Obsidian—compounds research sessions, fills gaps automatically.
Niche GemShip ItBig Brain
alvdef
113mo ago
AI/ML●Mid
Skills for spec-driven AI software development
Curated skill collection for spec-driven AI development, competing with other prompt libraries.
Niche Gem
puristajs
2016d ago