Topic
Everything filed under AI Agents, newest first.
RSS · JSON · All topics
I gave an agent a lakehouse and control of my garden
Javier de la Torre describes wiring sensors, weather forecasts and a data lakehouse to an AI agent that plans and adjusts watering for his two-square-metre vegetable garden every morning, and explains why it produces a €60 lettuce.
24 min · 5,580 words
Chatbots wait for a message. An always-on agent is single-threaded, proactive and situationally aware. Here's how Rubric designs agents like Grok Bot, Muse and Instinct — and what models still lack.
7 min · 1,667 words
How AI agents run insurance's back office
Harper Engineering describes ambient agents that continuously handle insurance back-office work—reacting to events, drafting actions, and keeping humans in the loop for 6,000+ small businesses.
7 min · 1,508 words
LangChain argues agent systems are shifting to async subagents so a main agent can stay responsive to users while background work continues—covering the design, APIs, and product implications in Deep Agents.
4 min · 929 words
Agents aren’t humans (but they kinda are)
Cloudflare frames the problem of AI agents acting on the web for millions of users while servers mostly see intermediaries—and outlines a collaborative approach to identify, allow, and manage trusted agent delegation traffic safely.
16 min · 3,596 words
The AI that builds your AI. Now for agents.
Oumi’s November update extends FAiE (Frontier AI Engineer) from models to full agents: build/evaluate/train agents, Bring Your Own Harness, DPO plus GRPO private preview, multi-stage training, and clearer cost visibility—so teams can automate agent improvement while owning the weights.
3 min · 678 words
Cursor Cloud Agents can now scaffold a web app, provision Postgres and auth, run security checks, and deploy to a shareable live URL—so prototypes leave localhost without extra accounts or config. Available on paid plans with cloud agents.
2 min · 441 words
Your Agent Shouldn't Need Your Laptop
Most of us met AI agents as something we open. You type, the agent works, you close the tab, and the agent stops existing. That is fine for a coding session or a quick question. It does not work for what people actually want from an assistant: something that notices the contract that came in overnight, sees that CI failed after you left, and has a draft response ready before you ask. That kind of agent is *proactive*. And a proactive agent has a problem a chat window never had: it has to be somewhere when you are not.
8 min · 1,835 words
I was journalling on my supernote eink the other morning and contemplating what it's like "writing" code these days with the advent of the LLMs, and I have a new term for it. There have been lots of neologisms around coding with LLMs lately -
7 min · 1,692 words
FrontierPhysics: Evaluating Agents for End-to-End Physics Research
BenchFlow’s FrontierPhysics v0.1 benchmarks AI agents on 56 end-to-end physics research tasks written by 42 physicists; frontier models struggle most on rigorous reasoning and expert intuition.
4 min · 838 words
Your AI Agent Has Amnesia. Mine Keeps Receipts.
A practical write-up of months of shared memory across Claude, Codex, and Antigravity: versioned receipts, retractions, and why append-only logs beat vibe memory for agents.
20 min · 4,572 words
How TinyResearch works: inside the research loop
A walkthrough of TinyResearch’s research agent loop—planning, searching, reading, and self-checking before writing a report—and why not everything should go through an LLM.
11 min · 2,502 words
OCAP Bounded Authority: Edera's Managed Approach to Object Capabilities
Ariadne Conill of Edera explains why AI agents make ambient authority dangerous and how Edera applies object-capability security with bounded, managed authority so agents and MCP servers get only the capabilities they need.
12 min · 2,687 words
Inside Replit's New Sandbox Engine, Part 1: The Path to MicroVMs
How Replit rebuilt its sandbox engine with microVMs for stronger isolation, bottomless storage, and fast startup across hundreds of millions of projects.
10 min · 2,275 words
You’ll need nerves of steel to work with AI agents
A hands-on account of the frustrations of coding with Composer 2.5 in Cursor, from ignored rules and unwanted edits to usage-limit tradeoffs versus GPT subscriptions, and why the author ends up recommending newer frontier models.
9 min · 1,966 words
Indie game development with AI
Sandro Maglione answers 'if AI implements everything, what's left for me?' for indie game development: choosing a game is choosing your bottleneck, and art, characters, taste and design remain hard even when agents write the code.
14 min · 3,188 words
How Figma manages sandboxes at scale
Figma built Nimbus to manage tens of thousands of AI sandboxes across providers: namespace configs, warm pools, read/write network policy, and GetOrCreate lifecycle APIs.
10 min · 2,355 words
Render introduces Sandboxes, isolated computers for AI agents that can run code, install tools, and keep state across steps, aimed at safer agentic workflows on Render’s platform.
6 min · 1,394 words
Engram shows that a short reinforcement-learning phase on top of fixed text notes improves agent accuracy by about 7–20 points across workspaces, often cuts inference tokens, and remains useful even after millions of tokens of note edits because models learn note-use strategies rather than memorizing contents.
16 min · 3,790 words
Letting users trust their own MCP clients, without opening a phishing hole
Alexander Loginov of Stream Vessel explains why MCP servers using OAuth dynamic client registration either refuse custom clients' redirect URIs or open a phishing hole, and describes a design where each user decides at sign-in which redirect URIs they trust.
10 min · 2,358 words