News · Agents
A shared accessibility standard for AI agents
A July 2026 research paper proposes a single shared route for screen-reader data — the same plumbing AI agents already use to talk to tools — across Windows, Mac, Android and the web.
Beat
Agents
27 pieces on agents — practical workflows, case studies and field notes.
News · Agents
GPT-6 Astra tripled Fable on agent tests
GPT-6 Astra nearly tripled Claude Fable 5.1's score on a year-long simulated vending business and beat the human baseline on every step of flying a surveillance drone — but only on its best attempts, Andon Labs says.
News · Agents
Perplexity's Portable Computer lands on Windows RTX
Perplexity's local AI agent now runs on Windows PCs with NVIDIA RTX graphics cards — keeping files on the machine and only sending hard questions to the cloud.
News · Agents
Five shifts OpenAI just telegraphed
Tibo, OpenAI's product lead for ChatGPT and Codex, laid out five trends in a 44-minute interview. Each one is something a UK operator can probe this afternoon.
Guide · Agents
How to design trust into AI agents
Wrapping a chat prompt around a rigid workflow does not make it an agent. Here is a shop metaphor — cashier, handbook, till, manager — for designing agentic systems a team will actually trust.
News · Agents
Caveman 2 cuts input tokens by 33%
Caveman 2, a free add-on for Claude Code, Codex and 30+ agents, shrinks what they read by a third on a pinned benchmark. A separate training effort teaches smaller models to reason terse by default. The skill is yours this afternoon.
News · Agents
Agenta ships an open-source AI coworker
An open-source workspace you can self-host on your own hardware for building AI agents — model calls route to your existing Claude or ChatGPT subscription, or to a self-hosted model via Ollama. A real alternative to Anthropic's desktop AI agent tool.
News · Agents
OpenAI open-sources its security agent
Codex Security CLI is now open-source under Apache 2.0 — a small but deliberate move from OpenAI, and a signal of where the AI-driven security tooling race is heading.
News · Agents
NVIDIA Turns BioNeMo Into Agent Tools
Anthropic's new Claude Science workbench for researchers opens in public beta this week, with NVIDIA's decade of life-sciences software wired in as agent-ready skills.
Analysis · Agents
Anthropic puts a permanent Claude in Slack
Claude Tag listens, learns and acts in every channel you give it. The shift to always-on AI inside the place your team already talks is the clearest signal yet of where the next 18 months are heading.
How-to · Agents
A business assistant for under £50 a month
Pair the open-source Hermes agent with MiniMax-M3 on a small server and a $20 Nous Portal plan, and you have a tireless junior assistant for roughly the price of one premium AI seat. Here is the stack — and five jobs to give it.
News · Agents
Google makes Interactions the default Gemini API
The agent-first interface leaves beta and becomes the recommended path for building with Gemini — the third major lab to commit to a stateful, agent-native API.
News · Agents
Coding agents top out at 41% on games
GameCraft-Bench ran 140 Godot tasks through seven frontier agents. The best still failed nearly six in ten — and the failure pattern tells small teams where these tools are useful today.
How-to · Agents
Build an incident triage agent this afternoon
AWS and the observability platform New Relic published a step-by-step tutorial for a chat agent that investigates incidents, drafts a root-cause report and files a tracked task from one prompt.
News · Agents
Salesforce buys Fin for $3.6bn
Dublin-founded AI agent vendor Fin — formerly Intercom — is the third acquisition Salesforce has announced in June.
News · Local Models
Kimi Work orchestrates 300 agents from your desktop
Moonshot's new desktop agent runs orchestration, browser control and scheduling on your machine — but the reasoning happens on Moonshot's hosted K2.6 by default. Here's what that means for small UK firms.
News · AI Agents
OpenAI acquires Ona to make Codex persistent
Ona's cloud workspaces will let Codex agents keep running when your laptop is shut, and stay inside your own security perimeter — a quiet shift in who hosts the work.
Guide · Agentic AI
What are AI agents?
The plain-English introduction: what an agent actually is, how it differs from a chatbot, and why we think agents will quietly become part of how small firms operate.
Analysis · Agentic AI
Three Things from All-In's Liquidity Summit That Matter to a Small Firm
Three keynotes from the All-In podcast's Liquidity Summit, translated for the UK sole trader: agentic AI is doing real expert work, the big labs are spending huge sums on compute, and a wave of AI IPOs will shake up the tools you already rent.
Practical · Agent Skills
Edit safely: the three tools that stop an AI agent trashing your files
A free plugin packages the three editing primitives that let an AI agent change one line of a real file without rewriting the rest. Here's why that contract matters for any business buying agent tools.
Case Study · Behind the Scenes
How We Built an Agent-Run News Site in 24 Hours — a Full Technical Case Study
Claude as the architect and supervisor, MiniMax-M3 as the writer on a €10 VPS, and a human on the ship-it button. Built in a day — then genuinely replatformed onto the NousResearch Hermes agent. Here is exactly how it runs now, gates and all.
Analysis · Local AI
OpenJarvis v1.0: The Local-First Agent Framework Ollama Has Been Waiting For
Stanford's Hazy Research has shipped the first credible open-source framework for personal AI agents that run on your own hardware. For UK operators, local-first has stopped being a manifesto and started being a curl command.
Standards · Interop
MCP Hits 97M Downloads and Goes Stateless — Why It Matters for Your Tools
The Model Context Protocol has scaled faster than React, and its next release rewrites the core to be stateless. Here is what that unlocks for a small team wiring agents to its own systems.
Open Source · Agents
LangChain's Deep Agents: the open agent pattern worth copying
LangChain's Deep Agents reference architecture has been called the most significant open-source agent release of 2026. Here's what it means in plain terms — and when a small team should actually copy it.
Open Source · Frameworks
Microsoft Agent Framework hits GA: AutoGen and Semantic Kernel, unified
Microsoft has merged AutoGen and Semantic Kernel into one framework, with general availability targeted for the end of Q1 2026. For teams choosing a stack, fewer competing abstractions is good news — but ask the lock-in questions first.
Open Source · Security
Microsoft's Agent Governance Toolkit: guardrails before you deploy
Microsoft has open-sourced an Agent Governance Toolkit with a policy engine that intercepts every agent action before it runs. Even a small team should put a layer like this in front of action-taking agents.
Open Source · Orchestration
CrewAI Flows brings event-driven orchestration to small teams
CrewAI's 2026 release adds Flows — a lower-level, event-driven orchestration layer beneath its multi-agent crews. For predictable back-office and logistics work, that structure often beats a loose crew.