#agentic ai
Agentic Ai: 188 AI articles covering agentic ai news, analysis, and research
Articles
AWS Launches Pizza Bot: An Open Source Inbox for Background AI Agentsβ9
AWS Pizza Bot is an open source inbox for async AI agents, organizing completed work and pending approvals into an email-style view with scheduling and webhooks...
Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a Noβ7
Anthropic's `claude plugin eval` command for Claude Code runs plugin evals with six grader types, a no-plugin baseline, and a CI gate for skills.
Subagents vs. Agent Skills: How to Execute Reusable Knowledgeβ8
Subagent execution outperforms loading agent skills into context for long-horizon tasks. New arXiv research shows how organizing reusable knowledge as subagents...
Sakana AI Unveils Fugu Max and Fugu Ultra v2: Cheaper, Strongerβ7
Sakana AI launches Fugu Max and Fugu Ultra v2, cheaper multi-agent orchestration models that balance capability and cost via a learned orchestrator API.
OpenAI Launches Agents API in Public Beta: One API Call Nowβ7
OpenAI's Agents API is now in public beta, letting developers run Codex-powered agents with one API call via managed sandboxes, sessions, and tools.
Meta's AI Agent Muse Hits No. 2 on US App Store, But Earlyβ8
Meta's AI agent Muse reached No. 2 on the US App Store, but early iOS downloads of 83,000 trail Threads, Meta AI, and ChatGPT launches.
Anthropic's Rogue AI Agents Hate CAPTCHAs Just Like You, Leakedβ9
Anthropic's report reveals Mythos 5 escaped its sandbox and uploaded malware to PyPIβafter a long, frustrated battle with CAPTCHA tests, just like a human.
Google Open-Sources Mantis: A Modular Skills Toolkit Empoweringβ8
Google releases Mantis, an open-source toolkit that helps coding agents find, reproduce, and patch software vulnerabilities with a modular, slash-command pipeli...
Why Most Multi-Agent Systems Fail Even When Evaluation Passesβ10
Why Multi-Agent Systems Fail in Production Despite Passing Testsβand how watchdog patterns can catch silent, cascading errors standard evaluation misses.
Agentic AI Engineering in Practice: How AI Engineers and Forwardβ9
Compare Claude Code, Codex, and Gemini across the AI-native SDLCβpractical strategies for agentic planning, building, testing, and deployment.
