{"posts":[{"_id":"6a6ae7ec1d68c145dca72ae5","slug":"autopilots-microsoft-gave-every-ai-agent-its-own-identity","title":"Autopilots: Microsoft Gave Every AI Agent Its Own Identity","excerpt":"The product story is an assistant that books your meetings. The architectural story is one sentence, and it is the more important of the two: \"Every agent operates under its own governed Entra identity, not a shared, anonymous service account, so the work it does is attributab...","tag":"infrastructure","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:58:04.124Z","postId":"ntwrYwX2szOm","createdAt":"2026-07-30T05:58:04.124Z","updatedAt":"2026-07-30T05:58:04.124Z","__v":0},{"_id":"6a6ae7ea1d68c145dca72ae1","slug":"github-shipped-four-agent-features-in-july-and-all-of-them-were-brakes","title":"GitHub Shipped Four Agent Features in July - And All of Them Were Brakes","excerpt":"Four agent-related features landed in GitHub's changelog in July. Three of them make agents easier to watch, question, or stop. Only one gives an agent more authority — and it hands that authority over your security alerts. Read individually, they are routine release notes. Re...","tag":"news","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:58:02.818Z","postId":"H_Wwe2gkMqC4","createdAt":"2026-07-30T05:58:02.819Z","updatedAt":"2026-07-30T05:58:02.819Z","__v":0},{"_id":"6a6ae7e91d68c145dca72add","slug":"your-ai-agent-is-a-yaml-file-now-and-it-can-rewrite-itself","title":"Your AI Agent Is a YAML File Now - And It Can Rewrite Itself","excerpt":"Buried in Pydantic's v2 announcement is a claim that reframes the entire declarative-agent conversation. Describing agent specs, the team notes that because capabilities are serializable, an agent can be loaded from a spec file — and that \"the surface is small enough that an L...","tag":"tool","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:58:01.531Z","postId":"4cRNN-f6LHXg","createdAt":"2026-07-30T05:58:01.532Z","updatedAt":"2026-07-30T05:58:01.532Z","__v":0},{"_id":"6a6ae7e81d68c145dca72ad9","slug":"prompt-loop-graph-the-three-layers-of-ai-agent-control","title":"Prompt, Loop, Graph: The Three Layers of AI Agent Control","excerpt":"A prompt that fails gives you a bad answer. A loop that fails does something worse: it keeps going. It cannot distinguish finished from stuck, so it does not stop, and it does not error — it just spends tokens until someone notices the bill. That asymmetry is the reason \"promp...","tag":"guide","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:58:00.232Z","postId":"mvooQ-l4TFnr","createdAt":"2026-07-30T05:58:00.233Z","updatedAt":"2026-07-30T05:58:00.233Z","__v":0},{"_id":"6a6ae7e61d68c145dca72ad5","slug":"deepagents-07-cut-its-own-prompt-by-65-percent-why-less-scaffolding-made-agents-better","title":"DeepAgents 0.7 Cut Its Own Prompt by 65 Percent - Why Less Scaffolding Made Agents Better","excerpt":"In deepagents 0.7.0, released July 24, the authored base prompt starts empty. That is a framework whose entire value proposition was scaffolding — prompts, middleware, structured guidance wrapped around a model — publicly concluding that most of its own scaffolding was overhea...","tag":"tool","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:57:58.926Z","postId":"TqLqiPJATBjT","createdAt":"2026-07-30T05:57:58.926Z","updatedAt":"2026-07-30T05:57:58.926Z","__v":0},{"_id":"6a6ae7e51d68c145dca72ad1","slug":"behavioral-state-decay-why-long-horizon-ai-agents-forget-what-matters","title":"Behavioral State Decay: Why Long-Horizon AI Agents Forget What Matters","excerpt":"A memory system that keeps quiet most of the time beat one that always spoke up. It also beat merely making the memory available, beat an advisor that offered guidance, and beat generic retrieval. That result, from a paper submitted on July 9, is the most useful thing publishe...","tag":"research","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:57:57.534Z","postId":"bYyQ91BsVFoK","createdAt":"2026-07-30T05:57:57.536Z","updatedAt":"2026-07-30T05:57:57.536Z","__v":0},{"_id":"6a6ae7e41d68c145dca72acd","slug":"the-weekend-an-ai-broke-into-hugging-face-and-an-ai-caught-it","title":"The Weekend an AI Broke Into Hugging Face - And an AI Caught It","excerpt":"Over a single weekend, something autonomous walked into Hugging Face's production infrastructure, ran thousands of actions across internal clusters, and harvested service credentials. It was found by an LLM reading security telemetry. By the time the forensics were complete, t...","tag":"security","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:57:56.228Z","postId":"JyzfNLQuAmkJ","createdAt":"2026-07-30T05:57:56.229Z","updatedAt":"2026-07-30T05:57:56.229Z","__v":0},{"_id":"6a6ae7e21d68c145dca72ac9","slug":"mcp-just-went-stateless-what-the-2026-07-28-spec-breaks-and-how-to-migrate","title":"MCP Just Went Stateless: What the 2026-07-28 Spec Breaks and How to Migrate","excerpt":"You cannot put a load balancer in front of a conversation. That single operational fact, discovered independently by every team that tried to run a Model Context Protocol server for more than one user, is what produced the spec published on July 28 — the largest revision to MC...","tag":"mcp","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-07-30T05:57:54.923Z","postId":"83uO7Ws-Zw7f","createdAt":"2026-07-30T05:57:54.925Z","updatedAt":"2026-07-30T05:57:54.925Z","__v":0},{"_id":"6a3e181d6e4798d4074b7917","slug":"stop-listing-tools-start-writing-code-cloudflare-code-mode-rethinks-mcp","title":"Stop Listing Tools, Start Writing Code: Cloudflare Code Mode Rethinks MCP","excerpt":"Here is a counterintuitive fact about AI agents: the more tools you give one, the dumber it tends to get. Every tool you register goes into the model's context as a description it has to read, hold, and choose between on each step. Wire up a few dozen and the system prompt blo...","tag":"tool","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-06-26T06:11:41.203Z","postId":"BdNPD-XTWTQh","createdAt":"2026-06-26T06:11:41.203Z","updatedAt":"2026-06-26T06:11:41.203Z","__v":0},{"_id":"6a3e181c6e4798d4074b7913","slug":"august-2-the-day-your-ai-agent-becomes-high-risk-in-europe","title":"August 2: The Day Your AI Agent Becomes High-Risk in Europe","excerpt":"There is a date on the European calendar that quietly changes what your AI agent is, legally speaking. On August 2, 2026, the high-risk obligations of the EU AI Act become binding . Not proposed, not phased in later — enforceable, with a compliance regime attached. And here is...","tag":"news","author":"AI Agent Engineering","authorUserId":"","status":"published","publishedAt":"2026-06-26T06:11:40.708Z","postId":"Z6ye88dmXcjf","createdAt":"2026-06-26T06:11:40.710Z","updatedAt":"2026-06-26T06:11:40.710Z","__v":0}],"total":39,"page":1,"pages":4}