The Simple Validation System That Saved Our AI Project

We were three weeks from launch when we discovered our AI wasn’t actually intelligent—it was just confidently wrong. The marketing site promised “AI-powered document analysis that understands context and delivers accurate insights.” Our demos looked flawless. The investors were excited. The sales team had already started taking pre-orders. Then a customer uploaded a standard employment […]

11 mins read

2025: The year in LLMs

2025: The year in LLMs 31st December 2025 This is the third in my annual series reviewing everything that happened in the LLM space over the past 12 months. For previous years see Stuff we figured out about AI in 2023 and Things we learned about LLMs in 2024. It’s been a year filled with […]

46 mins read

The Allure And Danger Of Pure Vibe Coding In Enterprise UX (Part 1) — Smashing Magazine

Yegor Gilyov examines the problem of over-reliance on static high-fidelity mockups, which often leave the conceptual model and user flows dangerously underdeveloped. He then explores whether AI-powered prototyping is the answer, questioning whether the path forward is the popular “vibe coding” approach or a more structured, intent-driven approach. There is a spectrum of opinions on […]

18 mins read

Building an internal agent: Subagent support

Most of the extensions to our internal agent have been the direct result of running into a problem that I couldn’t elegantly solve within our current framework. Evals, compaction, large-file handling all fit into that category. Subagents, allowing an agent to initiate other agents, are in a different category: I’ve frequently thought that we needed […]

3 mins read