<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Dhii Insights</title><description>Practical writing on agentic AI, RAG, fine-tuning and AI engineering.</description><link>https://dhii.ai/</link><language>en</language><item><title>What Is Agentic AI Automation? A Practical Guide for Business Teams</title><link>https://dhii.ai/insights/what-is-agentic-ai-automation/</link><guid isPermaLink="true">https://dhii.ai/insights/what-is-agentic-ai-automation/</guid><description>Agentic AI automation explained without the hype — how AI agents differ from chatbots and RPA, where they work well, where they fail, and how to start safely.</description><pubDate>Mon, 02 Nov 2026 00:00:00 GMT</pubDate><category>agentic AI</category><category>AI agents</category><category>automation</category><category>strategy</category></item><item><title>Designing Tools for AI Agents: Patterns That Make Agents Reliable</title><link>https://dhii.ai/insights/designing-reliable-ai-agent-tools/</link><guid isPermaLink="true">https://dhii.ai/insights/designing-reliable-ai-agent-tools/</guid><description>Most agent failures are tool-design failures. Practical patterns for naming, scoping, validating and securing tools so LLM agents choose and use them correctly.</description><pubDate>Mon, 26 Oct 2026 00:00:00 GMT</pubDate><category>AI agents</category><category>tool calling</category><category>engineering</category><category>MCP</category></item><item><title>The Production RAG Checklist: 25 Things to Get Right Before Launch</title><link>https://dhii.ai/insights/production-rag-checklist/</link><guid isPermaLink="true">https://dhii.ai/insights/production-rag-checklist/</guid><description>A practical checklist for building retrieval-augmented generation systems that work in production — ingestion, chunking, retrieval, grounding, permissions, evaluation and operations.</description><pubDate>Mon, 19 Oct 2026 00:00:00 GMT</pubDate><category>RAG</category><category>retrieval</category><category>LLM</category><category>engineering</category></item><item><title>LoRA vs QLoRA vs Full Fine-Tuning: Choosing the Right Method</title><link>https://dhii.ai/insights/lora-vs-qlora-vs-full-fine-tuning/</link><guid isPermaLink="true">https://dhii.ai/insights/lora-vs-qlora-vs-full-fine-tuning/</guid><description>How LoRA, QLoRA and full fine-tuning work, what they cost in memory and compute, how quality compares, and a decision guide for fine-tuning open-weight LLMs.</description><pubDate>Mon, 12 Oct 2026 00:00:00 GMT</pubDate><category>fine-tuning</category><category>LoRA</category><category>QLoRA</category><category>open models</category></item><item><title>How to Prepare a Fine-Tuning Dataset That Actually Improves Your Model</title><link>https://dhii.ai/insights/preparing-a-fine-tuning-dataset/</link><guid isPermaLink="true">https://dhii.ai/insights/preparing-a-fine-tuning-dataset/</guid><description>A step-by-step guide to building instruction datasets for LLM fine-tuning — sourcing examples, labelling guidelines, formatting, deduplication, synthetic data, splits and quality checks.</description><pubDate>Mon, 05 Oct 2026 00:00:00 GMT</pubDate><category>fine-tuning</category><category>datasets</category><category>data labelling</category><category>synthetic data</category></item><item><title>How to Evaluate an LLM Application: A Practical Guide</title><link>https://dhii.ai/insights/llm-evaluation-practical-guide/</link><guid isPermaLink="true">https://dhii.ai/insights/llm-evaluation-practical-guide/</guid><description>How to build evaluations for LLM features, chatbots, RAG systems and agents — defining quality, building test sets, choosing metrics, calibrating LLM judges and running evals in CI.</description><pubDate>Mon, 28 Sep 2026 00:00:00 GMT</pubDate><category>evaluation</category><category>LLM</category><category>testing</category><category>guardrails</category></item><item><title>Ollama vs vLLM: Choosing an Engine for Self-Hosted LLMs</title><link>https://dhii.ai/insights/ollama-vs-vllm-self-hosting/</link><guid isPermaLink="true">https://dhii.ai/insights/ollama-vs-vllm-self-hosting/</guid><description>A practical comparison of Ollama and vLLM for running open-weight LLMs on your own servers — ease of use, throughput, hardware, quantisation, APIs and production operations.</description><pubDate>Mon, 21 Sep 2026 00:00:00 GMT</pubDate><category>self-hosted LLM</category><category>Ollama</category><category>vLLM</category><category>infrastructure</category></item><item><title>Human-in-the-Loop Design for AI Automation: Approvals That Don&apos;t Slow You Down</title><link>https://dhii.ai/insights/human-in-the-loop-ai-automation/</link><guid isPermaLink="true">https://dhii.ai/insights/human-in-the-loop-ai-automation/</guid><description>How to design human oversight for AI agents and automations — risk tiers, approval thresholds, review UX, shadow mode, escalation and graduating to autonomy.</description><pubDate>Mon, 14 Sep 2026 00:00:00 GMT</pubDate><category>AI agents</category><category>human-in-the-loop</category><category>governance</category><category>automation</category></item><item><title>Model Context Protocol (MCP) Explained for Business and Engineering Leaders</title><link>https://dhii.ai/insights/model-context-protocol-explained/</link><guid isPermaLink="true">https://dhii.ai/insights/model-context-protocol-explained/</guid><description>What the Model Context Protocol is, why it matters, how MCP servers work, real use cases, security considerations and how to decide whether your organisation or product needs one.</description><pubDate>Mon, 07 Sep 2026 00:00:00 GMT</pubDate><category>MCP</category><category>AI integration</category><category>agents</category><category>security</category></item></channel></rss>