https://www.kelu.dev/blog/ Guides on RAG, support AI and company knowledge from Kelu. en https://www.kelu.dev/blog/test-ai-support-agent-before-go-live/ https://www.kelu.dev/blog/test-ai-support-agent-before-go-live/ Tue, 27 Oct 2026 00:00:00 GMT Replay resolved tickets through the AI, run Draft only for a week, and set the confidence threshold from real answers before an AI support agent goes live. https://www.kelu.dev/blog/replace-docs-site-search-with-ai/ https://www.kelu.dev/blog/replace-docs-site-search-with-ai/ Mon, 12 Oct 2026 00:00:00 GMT Swap keyword docs search for search with cited AI answers. Setup on Mintlify and Docusaurus, what works on GitBook, and how to measure the change with gaps. https://www.kelu.dev/blog/company-brain-how-to-build/ https://www.kelu.dev/blog/company-brain-how-to-build/ Thu, 01 Oct 2026 00:00:00 GMT Why wiki migrations fail, and how RAG builds a company brain across GitHub, Jira, Confluence, Notion and Drive, answering in Slack and Teams. https://www.kelu.dev/blog/permission-aware-ai-knowledge-base/ https://www.kelu.dev/blog/permission-aware-ai-knowledge-base/ Wed, 30 Sep 2026 00:00:00 GMT Stop AI assistants leaking confidential docs across teams with document-level visibility, role-based access and scoped retrieval. https://www.kelu.dev/blog/kapa-ai-alternatives/ https://www.kelu.dev/blog/kapa-ai-alternatives/ Wed, 16 Sep 2026 00:00:00 GMT The top Kapa.ai alternatives for technical docs, developer portals and support automation in 2026: Kelu, Inkeep, Chatbase, Mintlify, GitBook and Glean. https://www.kelu.dev/blog/how-to-deflect-support-tickets/ https://www.kelu.dev/blog/how-to-deflect-support-tickets/ Wed, 02 Sep 2026 00:00:00 GMT Auto-replies come too late: the ticket is already filed. Form deflection answers the question when the user presses submit. https://www.kelu.dev/blog/ai-for-company-policies/ https://www.kelu.dev/blog/ai-for-company-policies/ Wed, 05 Aug 2026 00:00:00 GMT Policies only work if people find them at the moment of decision. How retrieval-augmented AI turns a policy library into answers employees actually use. https://www.kelu.dev/blog/playbooks-that-answer-back/ https://www.kelu.dev/blog/playbooks-that-answer-back/ Wed, 22 Jul 2026 00:00:00 GMT A playbook nobody consults is documentation theater. Turning SOPs into an answer engine is how process actually changes behavior. https://www.kelu.dev/blog/runbooks-rag-incident-response/ https://www.kelu.dev/blog/runbooks-rag-incident-response/ Wed, 08 Jul 2026 00:00:00 GMT During an incident, the cost of finding the runbook is paid in downtime. Retrieval turns your runbook library into an on-call copilot. https://www.kelu.dev/blog/how-to-evaluate-rag/ https://www.kelu.dev/blog/how-to-evaluate-rag/ Tue, 30 Jun 2026 00:00:00 GMT Without a golden set and the right metrics, you can't tell a RAG improvement from a regression. The stack: retrieval metrics, answer metrics, abstention tests. https://www.kelu.dev/blog/governed-ai-for-internal-knowledge/ https://www.kelu.dev/blog/governed-ai-for-internal-knowledge/ Wed, 17 Jun 2026 00:00:00 GMT The fastest way to get an internal AI assistant blocked is to skip governance. Here is the checklist that gets policy and playbook Q&A approved. https://www.kelu.dev/blog/sales-playbooks-in-the-flow/ https://www.kelu.dev/blog/sales-playbooks-in-the-flow/ Wed, 03 Jun 2026 00:00:00 GMT Enablement content fails at the moment of the objection. Putting the playbook behind retrieval puts the approved answer in the rep's hands mid-call. https://www.kelu.dev/blog/employee-handbook-ai-assistant/ https://www.kelu.dev/blog/employee-handbook-ai-assistant/ Wed, 13 May 2026 00:00:00 GMT Handbooks fail because they are optimized for legal completeness, not for answering questions. An AI assistant lets both goals coexist. https://www.kelu.dev/blog/slack-ai-knowledge-bot/ https://www.kelu.dev/blog/slack-ai-knowledge-bot/ Tue, 05 May 2026 00:00:00 GMT Knowledge tools fail when they demand a context switch. Putting a grounded AI assistant inside Slack meets questions where they are already being asked. https://www.kelu.dev/blog/knowledge-gap-analysis/ https://www.kelu.dev/blog/knowledge-gap-analysis/ Tue, 21 Apr 2026 00:00:00 GMT A knowledge gap is a real question your content can't answer. Tracked systematically, gaps turn gut-feel docs planning into a ranked, evidence-based backlog. https://www.kelu.dev/blog/mcp-server-for-docs/ https://www.kelu.dev/blog/mcp-server-for-docs/ Tue, 07 Apr 2026 00:00:00 GMT The Model Context Protocol lets AI assistants query your live docs instead of guessing from training data. What an MCP docs server does and why it matters. https://www.kelu.dev/blog/geo-for-documentation/ https://www.kelu.dev/blog/geo-for-documentation/ Tue, 17 Mar 2026 00:00:00 GMT Generative engine optimization is SEO's successor problem: your docs now need to win citations inside AI answers, not just rankings on a results page. https://www.kelu.dev/blog/build-internal-knowledge-assistant/ https://www.kelu.dev/blog/build-internal-knowledge-assistant/ Tue, 03 Mar 2026 00:00:00 GMT The five-layer anatomy of an internal AI assistant — connectors, indexing, retrieval, governance, and interfaces — and a build-vs-buy framework for each. https://www.kelu.dev/blog/hybrid-search-explained/ https://www.kelu.dev/blog/hybrid-search-explained/ Tue, 17 Feb 2026 00:00:00 GMT Semantic search misses exact IDs; keyword search misses paraphrases. How hybrid search fuses both with reciprocal rank fusion, and why to start with it. https://www.kelu.dev/blog/why-ai-chatbots-hallucinate/ https://www.kelu.dev/blog/why-ai-chatbots-hallucinate/ Tue, 03 Feb 2026 00:00:00 GMT Hallucination is a property to engineer around, not a bug to patch. How grounding, citations, and enforced abstention make a chatbot a trustworthy answerer. https://www.kelu.dev/blog/rag-vs-fine-tuning/ https://www.kelu.dev/blog/rag-vs-fine-tuning/ Tue, 20 Jan 2026 00:00:00 GMT For Q&A over your own docs, retrieval-augmented generation beats fine-tuning on freshness, citations, and cost. A decision framework for choosing between them. https://www.kelu.dev/blog/what-is-ticket-deflection/ https://www.kelu.dev/blog/what-is-ticket-deflection/ Tue, 06 Jan 2026 00:00:00 GMT Ticket deflection is the share of support questions resolved without creating a ticket. Here is how to define it, measure it honestly, and raise it.