On the the engineering challenges and lessons learned from building Claude's Research system
OK, I'm sold on multi-agent LLM systems now. I've been pretty skeptical of these until recently: why make your life more complicated by running multiple different prompts in parallel when …
Plus reviews of two new papers about prompt injection, and Anthropic's tips on building multi-agent LLM systems
AI has entered an era similar to the internet near the end of 1996. Basic use cases were solid, advanced use cases were not, and money was flushed down the toilet.
A comprehensive, research-backed guide to mastering the evolution from traditional prompt engineering to context engineering, with detailed implementation examples and production-ready frameworks.
By 2026, the real job in modern AI systems is not writing a clever prompt. It is deciding what the model sees, when it sees it, and how that context is struc...
Will update this as I find more. Building effective agents: Anthropic says the most reliable agents come from simple, composable patterns with clear tool ...
6 tactics for fixing your context and shipping better agents. As Karpathy says, building LLM-powered apps means learning to ‘pack the context windows just right’—smartly deploying tools, managing information, and maintaining context hygiene.
Patterns for managing agent context.
The Bitter Lesson in AI Engineering.
19 posts tagged ‘agent-definitions’. I collect definitions of "agents".
Discussing topics on web development, data architecture, software architecture and much more.
68 posts tagged ‘llm-tool-use’. Tool use is when an LLM is instructed to occasionally request that an external tool be run on its behalf, with the result passed back to the model for further …
That’s right.
AI superpower = strategic amnesia. Letta caches memory like a CPU, Anthropic spreads it across agent swarms, Cognition warns of chaos. Curious how forgetting makes machines smarter? Dive in.