The Agent Evaluation Readiness Checklist Starting to think through how to test your agents? We put together a step-by-step checklist for building, running, and shipping agent evals. We walk through:
→ How to read traces in LangSmith and analyze errors, before building evals
PROMPT ENGINEERING
-
Agent Evaluation Readiness Checklist: Testing and Shipping Agents
By
–
-
Anthropic releases complete guide to building Claude skills
By
–
Grab your free copy of Anthropic's official guide to building Claude skills right here: → https://
resources.anthropic.com/hubfs/The-Comp
lete-Guide-to-Building-Skill-for-Claude.pdf
… -
Claude Skills Folder Playbook Free 33-Page System
By
–
Anthropic dropped a FREE 33-page playbook revealing Claude's very own cheat code: The 'Skills' folder. Spend 30 minutes building it,
and you’ll never have to explain your process again. Top-tier users don't just type commands, they build systems. Playbook link in ↓ -
AI-Powered Qualitative Data Analysis With ChatGPT and QualCoder
By
–
Qualitative Data Analysis With Chatgpt And Qualcoder: A Step-By-Step Guide To AI-Powered Coding And Thematic Analysis AI-Powered Research Toolkit — Mastering Research Series — available at https://
amzn.to/4bRsV3q -
Know What You’re Doing Before Using AI Agents
By
–
gm just a reminder: if you don't know what you are doing, agents will not help you get it done better or faster
-
OpenAI Announces Plugins for Codex
By
–
OpenAI released Plugins for Codex! Plugins are combinations of Apps and Skills to enable Codex to work better with the data from external apps. https://t.co/dOWupuOfKG pic.twitter.com/bL5liwot4Y
— 🚨 AI News | TestingCatalog (@testingcatalog) 27 mars 2026OpenAI released Plugins for Codex! Plugins are combinations of Apps and Skills to enable Codex to work better with the data from external apps.
-
Comparison of LLM, RAG, and Agent Technologies
By
–
#LLM Vs #RAG Vs AGENT
by @techNmak #GenerativeAI #ArtificialIntelligence #MachineLearning #ML -
Claude AI Integration for Automated Restaurant Booking via Pins
By
–
plz plug into claude so i can do like “hey claude can you book whichever Thai spot I have in my pins in the city at 7pm tonight”
-
Claude Code Skill Clones Entire Websites From One Prompt
By
–
Yo, this guy just built a Claude Code skill that clones entire websites from ONE prompt You literally just point it at any URL, type /clone-website, and it goes to work: Inspects the site through Chrome MCP, grabs all the design tokens and assets, writes the component specs,
-
LLM as a search engine that never fails
By
–
An LLM is a search engine that never fails, because when it can't find a document it makes up.