AI Agents
AI agents are LLM-powered systems that don't just answer — they plan steps, call tools and drive a task to completion: writing code, searching the web, booking, analyzing. 2026 became the year of agents, from coding agents to autonomous researchers. This page gathers all our coverage of agentic AI: launches, protocols (MCP, A2A), reliability and real-world use.
Why We Threw Out 70% of a Corporate Knowledge Base Without Writing a Single Line of Code: The Engineering Anatomy of Enterprise RAG
70–80% of enterprise RAG deployments fail because of garbage in the source documents: cleaning up a client's knowledge base from 12,000 to 3,800 current files…
Infinigence AI and "Three-Body" Release Sophon Agent 1.0 for AI Characters
Chinese infrastructure startup Infinigence AI and the Three-Body universe launched Sophon Agent 1.0, a character-agent platform without persona drift or slowdowns…
OpenAI Unveils Dots Agent and Promises a 'New Privacy Standard' in AI
At DevDay, Altman introduced the Dots agent and promised a "new privacy standard." Months earlier, Zuckerberg said the same about Muse. Which of them will keep…
Anthropic shows how to keep Claude coding for days: a list of 200+ tasks in JSON
Anthropic Details How to Build Evals for AI Agents: Three Grader Types and SWE-bench Going From 40% to 80%
Anthropic Reveals How It Isolates Claude: Users Simply Approved 93% of Confirmations
AI Reaches PLCs: Engineering Assistants Now Read Projects and Write Code
2GIS's MCP Server: How to Stop LLMs From Making Up Addresses and Coordinates
2GIS has released an MCP server with six tools that connect AI agents directly to its geo-services: place search, geocoding, routes, isochrones, and static maps.
Cognition builds its Devin agent into MongoDB's platform: migrations 4–5 times faster
Devin now plugs into MongoDB AMP: the agent rewrites code and data access, while AMP moves records into Atlas. In early tests, tasks dropped from 5–6 hours to just…
Why AI Agents Are Vulnerable to Prompt Injection — and How to Secure Them at the Architecture Level
Devin Now Works Inside Pylon: Bugs Reach a PR in 15–20 Minutes, Fixes Ship 30% Faster
Geoffrey Huntley fixes coding agents with a pre-commit hook and gets 10 out of 10
Simon Willison releases web-edit 0.1a0, a web file editor for agents that runs over Tailscale
600 billion tokens later: how to manage AI agents decompiling a game
Three months of work by AI agents built on Claude, Codex, Luna, and other models — a full reconstruction of a C++ shooter. 99% of functions recovered, 83% match the…
Odyssey opens preview of its 14-billion-parameter Odyssey-3 world model
Odyssey has released Odyssey-3, a 14-billion-parameter model. It generates interactive worlds in real time, leads physics benchmarks, and can control robot arms…