Topic
Everything filed under AI Agents, newest first.
RSS · JSON · All topics
The dawn of the Data Intelligence Engineer
MotherDuck's Jordan Tigani argues that AI agents now handle much of traditional data-team work, and proposes a new role, the Data Intelligence Engineer, who owns the data model, curates context, and makes sure the numbers agents produce are right.
10 min · 2,271 words
A2UI 1.0: Build delightful, fast, reliable, agentic experiences
Google releases A2UI 1.0, the first stable version of its open protocol for generative UI, letting AI agents answer with interactive screens such as forms and charts, with renderer SDKs for web, Android and iOS and agent SDKs for Python, TypeScript and Dart.
6 min · 1,493 words
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
Google DeepMind introduces AlphaProof Code, a multi-LLM agentic framework that, with human experts writing specifications, produced millions of lines of Lean proof formally verifying key security properties of the actual Signal protocol implementation; artifacts are being open-sourced.
4 min · 992 words
Gemini 4 Carbon is now available
Google makes Gemini 4 Carbon, its strongest model, available to developers, enterprises, scientists and consumers, citing frontier cybersecurity capabilities, long-horizon agentic coding, scientific reasoning and safety work.
10 min · 2,229 words
Fable 5.2 One-Shotted My Nephew's Dream Game
Lex Toumbourou describes how Claude Fable 5.2 built a complete, fun multi-level game from his nephew's drawings in one shot, covering play testing, how the drawings became the game, and the final token tally.
8 min · 1,761 words
Locating the source of a mysterious beep with Claude
Simon Willison had Claude Code build Beep Locator, a web app that turns several phones, tablets and laptops into networked microphones to locate an intermittent beep in a room full of unpacked boxes, and reflects on letting agents perceive the world.
9 min · 1,990 words
Hide your slop PR descriptions behind <details><summary>
Simon Willison's tip for agent-written pull requests: keep a short human-written description visible and tuck the comprehensive Claude Code or Codex write-up inside a collapsible <details><summary> block on GitHub, so reviewers get editorial judgement without losing the detail.
4 min · 962 words
Amazon saves millions by replacing Sonnet 4.6 with Strands Decider
Two Amazon engineers replaced Claude Sonnet 4.6 with Strands Decider, an open decision model, for ticket labeling in one of the world's largest internal ticketing systems; it performed as well at about 98% less cost, and they explain running both models side by side on real traffic before switching.
4 min · 1,011 words
David Andrews and Chao Zhang describe pointing AI agents at CPython to rewrite its C functions line by line in Lean: 613,318 lines of machine-checked Lean, each piece differentially tested against real Python, with 418 bug reports in Python surfaced along the way.
12 min · 2,866 words
The future of Software Engineering is boring
Alex Pliutau argues that AI coding has turned much of software engineering into caretaking code nobody fully understands, and that the work may get more boring before it gets better, with human-authored code eventually reserved for hobbies or high-criticality systems.
6 min · 1,269 words
How I'm fighting the AI Brain Fry
Sergey Kuhne describes the exhaustion of juggling many parallel Claude Code and Codex sessions and his fix: treating work as a priority queue kept in git, with every ticket a markdown file next to the code so sequencing and context live in the repo rather than in chat windows or his head.
2 min · 573 words
Next-Level Benchmarking Overfitting
Thomas Neumann follows up on the database benchmarking crisis, showing how AI-driven tuning can overfit a single benchmark so aggressively that results become useless and would fall off a cliff in a real production system.
3 min · 629 words
Agent memory needs its OpenTelemetry moment
Every agent tool stores memory in its own shape, and none of them can read the others. Mads Thines compares today's agent-memory formats to pre-OpenTelemetry observability and sketches what a shared record, address, and contract could look like.
8 min · 1,934 words
Introduction to Harness Engineering for Vulnerability Research
Graham Helton and Ryan Basden introduce harness engineering for vulnerability research: why model capability alone is not enough, and how target-specific harnesses improve authorized investigations.
1 min · 203 words
Meta Research explains the security and safety approach behind Muse, covering how agent capabilities are constrained and how safety was designed into the product.
17 min · 4,013 words
Creating Custom Agents: Inside Bronto's Alert Investigation Agent
Bronto details how its open-source alert investigation agent was built with LangGraph and LangChain, and how custom agents pair with observability tools for faster incident response.
10 min · 2,252 words
20 Prompt Injection Test Cases for AI Agents
A copyable prompt injection testing set for agents that read documents, email and web pages, grouped by where hostile text hides, each with its safe behaviour.
7 min · 1,597 words
Basic Memory agents (beta) do the upkeep your notes need — filing, linking, cleanup, briefings — and show every change in a review queue you can undo. Each agent is a plain Markdown note you can read and edit.
4 min · 1,013 words
The components of agent memory
For Claude to learn from experience, it has to decide what's worth remembering before it knows what's next. Here's how "dreaming" helps agents correct mistakes, organize what they've learned, and find it in future sessions.
16 min · 3,628 words
Docker Sandboxes vs. Containers: Key Differences
Docker explains how Sandboxes differ from containers: microVMs with their own kernel and private Docker Engine, and when to use each for isolating AI agents.
13 min · 3,098 words