theAIcatchup
Large Language Models AI Tools AI Research Robotics
Computer Vision AI Hardware AI Business AI Ethics
AI Tools

#AI coding agents

Graph showing LangChain skills performance jump from 25% to 95% on Claude Code evals
AI Hardware

LangChain's 'Skills' Turn AI Coders from 29% Duds to 95% Champs – Skeptical Take

Claude Code couldn't hack basic LangChain agents at 29%. These new 'skills' flip it to 95%. But who's really winning here?

3 min read 2 weeks ago
AI agent terminal interface displaying LangSmith traces and evaluation metrics
AI Hardware

LangSmith CLI: AI Agents Now Debug Themselves Like Pros

Picture this: your AI coding agent, once stumbling blindly, now traces bugs, builds tests, and evaluates itself—all from the terminal. LangSmith's CLI and skills make it real, slashing dev time for everyone building agents.

3 min read 2 weeks ago
← Newer Page 2 of 2
theAIcatchup

AI news that actually matters.

Categories

  • Large Language Models
  • AI Tools
  • AI Research
  • Robotics
  • Computer Vision
  • AI Hardware
  • AI Business
  • AI Ethics

More

  • RSS Feed
  • Sitemap
  • About
  • AI Tools
  • Advertise

Legal

  • Privacy
  • Terms
  • Work With Us

© 2026 theAIcatchup. All rights reserved.

📬

Stay in the loop

The week's most important stories from theAIcatchup, delivered once a week.

No spam. Unsubscribe any time.