Databricks built a RAG agent it says can handle every kind of enterprise search

Databricks' KARL agent uses reinforcement learning to generalize across six enterprise search behaviors — the problem that breaks most RAG pipelines.

Agent Skills vs RAG : Why Procedural Workflows Are Replacing Long Prompts

Agent skills shift AI agents toward procedural tasks with skill.md steps; progressive disclosure reduces context window bloat in real use.

OpenAI’s new GPT-5.4 model is a big step toward autonomous agents

While OpenAI is bringing GPT-5.4 to its API and its AI-powered coding tool, Codex, it’s rolling out its reasoning model, ...
InfoQ

So You’ve Decided To Do a Technical Migration

Sophie Koonin discusses the realities of large-scale technical migrations, using Monzo’s shift to TypeScript as a roadmap. She explains how to handle "bends in the road," from documentation and ...
eWeek

GPT-5.4 Clicks, Types, and Probably Outperforms You

Hillman highlights Teradata’s interoperability with AWS, Python-in-SQL, minimal data movement, open table formats, feature ...
The Next Web

OpenAI’s GPT-5.4 sets new records on professional benchmarks

OpenAI released GPT-5.4 today with native computer use, a 1M-token context window, and new professional benchmarks. Find what ...
Communications of the ACM

Proposed Framework Evaluates the Accuracy of Agentic Systems

Traditional machine learning emphasized predictive accuracy. Generative systems required attention to hallucination mitigation and grounding. Agentic systems shift the challenge again. They do not ...

OpenAI, in Desperate Need of a Win, Launches GPT-5.4

GPT-5.4 is rolling out starting today and will be available in ChatGPT, Codex, and OpenAI’s API. GPT-5.4 Thinking will be available for Plus, Teams, and Pro users, and GPT-5.4 Pro will be available ...