Agentic AI for Serious EngineersField Notes, Signal, Recipes, and Lab Reports from the agentic AI publication by Sunil Prakash.https://sunilprakash.com/en-usLAB-001: Multi-agent vs router on 100 customer-support querieshttps://sunilprakash.com/agentic-ai/labs/multi-agent-vs-router-100-queries/https://sunilprakash.com/agentic-ai/labs/multi-agent-vs-router-100-queries/100 real support queries from a public dataset, run twice — once through a single-agent workflow router, once through a 3-agent hierarchical multi-agent system. Measured against the same eval rubric.Wed, 20 May 2026 00:00:00 GMTLabsFN-002: Your eval rubric needs failure buckets, not just scoreshttps://sunilprakash.com/agentic-ai/field-notes/002-eval-rubric-failure-buckets/https://sunilprakash.com/agentic-ai/field-notes/002-eval-rubric-failure-buckets/Two agents can score identically on a benchmark and fail differently in production. Failure buckets are the rubric. The aggregate is what falls out of it.Sun, 17 May 2026 00:00:00 GMTField NotesFN-001: The multi-agent papers nobody is citinghttps://sunilprakash.com/agentic-ai/field-notes/001-multi-agent-papers-nobody-cites/https://sunilprakash.com/agentic-ai/field-notes/001-multi-agent-papers-nobody-cites/Three papers and one practitioner survey put multi-agent failure rates between 41 and 86.7 percent and error amplification up to 17.2x. The version that survived production looks more like a CI pipeline than a faculty meeting.Thu, 14 May 2026 00:00:00 GMTField NotesSG-001: The skills.md discourse is sharpening the wrong knifehttps://sunilprakash.com/agentic-ai/signal/001-skills-md-wrong-knife/https://sunilprakash.com/agentic-ai/signal/001-skills-md-wrong-knife/Most skills.md advice in circulation is optimizing the wrong surface. Anthropic's docs name the real constraint: a 1% context-window budget for descriptions that quietly trims the labels of skills you invoke least. The marketplace economy is a retrieval anti-pattern.Thu, 14 May 2026 00:00:00 GMTSignalR-001: Build and deploy your first Strands agent on AgentCore Runtimehttps://sunilprakash.com/agentic-ai/recipes/001-strands-on-agentcore-runtime/https://sunilprakash.com/agentic-ai/recipes/001-strands-on-agentcore-runtime/Build and deploy a working Strands agent on AWS Bedrock AgentCore Runtime in an afternoon. Uses the modern @aws/agentcore CLI (npm) on a current AWS account, not the deprecated Python starter toolkit. Verified on a live deploy.Wed, 13 May 2026 00:00:00 GMTRecipes