<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>hubagenticai — the Agentic AI Hub: learn, build, govern</title><description>hubagenticai is the agentic AI hub: hands-on MCP and agent tutorials, honest comparisons, copy-paste templates, and governance depth — evergreen, and every code block tested.</description><link>https://hubagenticai.com/</link><item><title>How to build a personal AI agent for daily productivity (note and task triage)</title><link>https://hubagenticai.com/tutorials/personal-productivity-agent/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/personal-productivity-agent/</guid><description>Build an agent that triages your notes into tasks, references, and archives — runnable today with zero API keys, upgradeable to any LLM, and scalable from personal to team use.</description><pubDate>Sun, 05 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to choose an LLM for your agent: Claude, GPT, Gemini, or open-weights</title><link>https://hubagenticai.com/compare/choose-an-llm-for-agents/</link><guid isPermaLink="true">https://hubagenticai.com/compare/choose-an-llm-for-agents/</guid><description>General benchmarks predict agent performance poorly. The six criteria that matter for agentic workloads, a tiering strategy that beats single-model loyalty, and the eval-driven way to decide.</description><pubDate>Sun, 05 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The agentic AI tech stack, layer by layer: what you actually need to build agents</title><link>https://hubagenticai.com/compare/agentic-ai-tech-stack/</link><guid isPermaLink="true">https://hubagenticai.com/compare/agentic-ai-tech-stack/</guid><description>Seven layers make up every serious agentic system — models, serving, harness, protocols, knowledge, evals, and controls. What each layer does, the main options in each, and where the choices actually matter.</description><pubDate>Sun, 05 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Skills vs. tools vs. hooks vs. subagents vs. prompts: when to use what</title><link>https://hubagenticai.com/compare/skills-tools-hooks-subagents/</link><guid isPermaLink="true">https://hubagenticai.com/compare/skills-tools-hooks-subagents/</guid><description>Agentic coding assistants offer half a dozen extension mechanisms, and picking wrong wastes context or bites silently. One decision table for instructions, skills, MCP tools, hooks, subagents, and slash commands.</description><pubDate>Sun, 05 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The agent adoption ladder: personal → team → enterprise, without the faceplant</title><link>https://hubagenticai.com/enterprise/agent-adoption-ladder/</link><guid isPermaLink="true">https://hubagenticai.com/enterprise/agent-adoption-ladder/</guid><description>What actually changes when an agent graduates from one laptop to a team to a company — identity, secrets, review, cost — and the checklist for each rung.</description><pubDate>Sun, 05 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to build your first MCP server, step by step (Python and TypeScript)</title><link>https://hubagenticai.com/tutorials/build-your-first-mcp-server/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/build-your-first-mcp-server/</guid><description>Build a working Model Context Protocol server with tools and resources, connect it to a real client, and understand what actually happens on the wire.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How an AI agent actually works: build the loop behind every framework</title><link>https://hubagenticai.com/tutorials/how-an-agent-actually-works/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/how-an-agent-actually-works/</guid><description>Every agent framework wraps the same ~40-line loop: model decides, tool runs, result feeds back. Build it in plain Python and the whole ecosystem stops being magic.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Multi-agent orchestration explained: build an orchestrator and sub-agents from scratch</title><link>https://hubagenticai.com/tutorials/multi-agent-orchestration-explained/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/multi-agent-orchestration-explained/</guid><description>Build the agent harness pattern in ~80 lines of plain Python — an orchestrator that plans, delegates to specialist sub-agents, and synthesizes — with a mock model so you can run it instantly.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>MCP vs. A2A vs. AG-UI: the agent protocol stack, explained with one diagram</title><link>https://hubagenticai.com/tutorials/agent-protocol-stack-mcp-a2a-ag-ui/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/agent-protocol-stack-mcp-a2a-ag-ui/</guid><description>The three agent protocols solve three different problems — agent-to-tools, agent-to-agent, and agent-to-user. Learn which layer each owns and when you need more than one.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Claude Code from zero: an agentic coding workflow, step by step</title><link>https://hubagenticai.com/tutorials/claude-code-from-zero/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/claude-code-from-zero/</guid><description>Install Claude Code, learn the core loop, and build up to a disciplined agentic workflow: CLAUDE.md, plan mode, custom skills, and MCP servers.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Agent memory patterns: vector stores, knowledge graphs, and context engineering</title><link>https://hubagenticai.com/tutorials/agent-memory-patterns/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/agent-memory-patterns/</guid><description>Why agents forget, the four memory patterns that fix it, and a working retrieval loop you can run in plain Python before you buy a vector database.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to evaluate an AI agent: build a golden-task eval harness from scratch</title><link>https://hubagenticai.com/tutorials/evaluate-your-agent/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/evaluate-your-agent/</guid><description>Agents without evals break silently on every prompt tweak. Build a small golden-task harness in plain Python — tasks, checks, scoring, and a regression gate you can run in CI.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>How to wrap a REST API in an MCP server (without handing the agent the whole API)</title><link>https://hubagenticai.com/tutorials/wrap-a-rest-api-in-mcp/</link><guid isPermaLink="true">https://hubagenticai.com/tutorials/wrap-a-rest-api-in-mcp/</guid><description>Turn any REST API into agent-safe MCP tools: a narrow allowlist instead of a proxy, PII redaction before the model sees data, and a fake API so you can test the whole thing offline.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Agent frameworks vs. rolling your own harness: build or buy the loop?</title><link>https://hubagenticai.com/compare/agent-framework-vs-own-harness/</link><guid isPermaLink="true">https://hubagenticai.com/compare/agent-framework-vs-own-harness/</guid><description>LangGraph, CrewAI, the OpenAI and Claude SDKs — or 200 lines of your own code? A decision framework based on what agent frameworks actually provide.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>MCP servers vs. direct CLI calls: when each wins</title><link>https://hubagenticai.com/compare/mcp-vs-direct-cli-calls/</link><guid isPermaLink="true">https://hubagenticai.com/compare/mcp-vs-direct-cli-calls/</guid><description>Agents can reach tools through an MCP server or by running CLI commands directly. A decision framework with the token economics of each approach.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>RAG vs. agent memory vs. fine-tuning: which knowledge problem do you actually have?</title><link>https://hubagenticai.com/compare/rag-vs-memory-vs-fine-tuning/</link><guid isPermaLink="true">https://hubagenticai.com/compare/rag-vs-memory-vs-fine-tuning/</guid><description>Three ways to make a model &quot;know&quot; things, routinely confused with each other. A diagnostic for picking the right one — and the order to try them in.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Workflow vs. agent: when BPMN-style orchestration beats dynamic reasoning</title><link>https://hubagenticai.com/compare/workflow-vs-agent/</link><guid isPermaLink="true">https://hubagenticai.com/compare/workflow-vs-agent/</guid><description>The most expensive architecture mistake in enterprise AI is putting an agent where a workflow belongs — or vice versa. A decision framework with a bright-line design principle.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>FinOps for AI agents: metering token spend before it meters you</title><link>https://hubagenticai.com/enterprise/finops-for-agents/</link><guid isPermaLink="true">https://hubagenticai.com/enterprise/finops-for-agents/</guid><description>An architecture for agent cost governance: OpenTelemetry GenAI conventions for instrumentation, a gateway for enforcement, and the reporting dimensions finance will actually ask for.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>AI agent governance for regulated industries: a practical framework</title><link>https://hubagenticai.com/enterprise/agent-governance-regulated-industries/</link><guid isPermaLink="true">https://hubagenticai.com/enterprise/agent-governance-regulated-industries/</guid><description>A working control framework for agentic AI in banks, insurers, and other regulated shops — translating model-risk discipline (SR 11-7, OCC, FFIEC, EU AI Act) into agent-specific controls.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Human-in-the-loop patterns that scale: approval design for agent actions</title><link>https://hubagenticai.com/enterprise/human-in-the-loop-patterns/</link><guid isPermaLink="true">https://hubagenticai.com/enterprise/human-in-the-loop-patterns/</guid><description>Naive HITL either rubber-stamps everything or drowns reviewers. Five approval patterns, a materiality matrix for choosing, and the metrics that tell you when to loosen the loop.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Prompt injection for agentic systems: a working threat model</title><link>https://hubagenticai.com/enterprise/prompt-injection-threat-model/</link><guid isPermaLink="true">https://hubagenticai.com/enterprise/prompt-injection-threat-model/</guid><description>When agents read email, web pages, and documents, every input is a potential instruction. The lethal trifecta, the controls that actually work, and the ones that only feel like they do.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>