New agent eval unlocked: awareness of the page you’re currently embedded in 😄 The chatbot on LangChain’s Deep Agents docs page asked me where it could find the Deep Agents documentation. @LangChain this one made me smile :)

lets go

Allright…lets go…checking out @OmarchyLinux @dhh

from @TheEconomist

Prompt engineering asks: how do I get a better response? Loop engineering asks: how does the system know the work is actually done? I just published an introduction to loop engineering, including how it builds on prompt, context, and harness engineering, and what reliable agent loops require in practice. The key idea: the boundary is not model capability. It is verifiability. lnkd.in/dZYNDyq7 #AIEngineering #AgenticAI #LoopEngineering

well…there goes my weekend.

Claude all the way down

Over the last week I put together a 4-part series on Evaluation-Driven Development for LLM systems. It covers why spot-checking and brittle tests mislead, why your golden dataset becomes the real spec, a practical toolbox for grading outputs without spending a fortune, and how to run regression tests when you change prompts. ➡️ Part 1: Build LLM Evals You Can Trust <- anup.io/why-your-llm-app-tes… ➡️ Part 2: Your Golden Dataset is worth more than your Prompts <- anup.io/your-golden-dataset-… ➡️ Part 3: Four ways to grade an LLM (without going broke) <- anup.io/four-ways-to-grade-a… ➡️ Part 4: Ship Prompts like Software <- anup.io/ship-prompts-like-so… If you’re shipping LLM features, I hope it gives you a more repeatable workflow than “try a few prompts and ship”, and I’d be keen to hear what’s working for you.

Reading time: 2–4 days. Which, to be fair, is still faster than fine-tuning. huggingface.co/spaces/Huggin…

I love how Claude is so wholesome that it literally tells me to use a competitor’s product. 😂 Peak confidence. Peak alignment.