LAI #138: The Agent Reality Check
Agent evals, retry tracing, runaway costs, and the context your agents actually need.
Learn AI Together
The Learn AI Together community by Towards AI newsletter! Sharing opportunities, news, memes, projects, collaborations, learning resources and more.
Live Last read · last published · next check
Latest posts
LAI #137: Where AI Engineering Is Going in 2026
Persistent memory, agent infrastructure, observability, and the skills that matter next.
I just opened access to our entire engineering team
Submit your architecture, resume, or code: our engineers review it
LAI #136: Build Faster With Agents, Debug Their Failures, and Evaluate Them More Reliably
Better agents, better evaluation, and fewer production surprises.
LAI #135: The Useful Part of Graph Engineering Is Not the Graph
When JSON hurts reasoning, Anthropic wins our dream-workplace poll, and bad statistics make chocolate look like a diet plan
LAI #134: Your First LLM App on AWS for Under a Dollar
Loop engineering with Claude Code, plus a Towards AI enterprise launch, vLLM on L40S, and context windows as memory management
LAI #133: The Most Anticipated Model of the Year and Most of You Skipped It
Plus a self-evolving agent framework, AWS's phase-gated Claude Code, and an e-commerce search engine at 95% recall
LAI #132: We Open-Sourced the AI Tutor Our Students Actually Use
Run it locally, add your own content, plus our World's Fair workshop, RAG injection through documents, and attention as physics
I keynoted alongside OpenAI and DeepMind
Front-row access to our World's Fair keynote, free
LAI #131: A Tool Call Can Succeed and Still Be the Wrong Tool
The agent debugging blind spot, plus Microsoft's no-synthetic-data stance, attention as physics, and 7 layers of LLM cost cuts.