<?xml version="1.0" encoding="UTF-8" ?> <?xml-stylesheet type="text/xsl" href="rss.xsl"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/"> <channel> <title>Jason Liu</title><description>Applied AI, RAG, and personal notes.</description><link>https://jxnl.co/</link><atom:link href="https://jxnl.co/feed_rss_created.xml" rel="self" type="application/rss+xml" /> <managingEditor>Jason Liu</managingEditor><docs>https://github.com/jxnl/blog/</docs><language>en</language> <pubDate>Wed, 15 Apr 2026 17:43:34 -0000</pubDate> <lastBuildDate>Wed, 15 Apr 2026 17:43:34 -0000</lastBuildDate> <ttl>1440</ttl> <generator>MkDocs RSS plugin - v1.18.1</generator> <image> <url>None</url> <title>Jason Liu</title> <link>https://jxnl.co/</link> </image> <item> <title>What Music Do You Listen To?</title> <author>Jason Liu</author> <category>Personal</category> <description>My top albums and artists from Spotify — and what the mix actually says about taste.</description> <link>https://jxnl.co/writing/2026/04/02/what-music-do-you-listen-to/</link> <pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2026/04/02/what-music-do-you-listen-to/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2026/04/02/what-music-do-you-listen-to.png" type="image/png" length="41437" /> </item> <item> <title>Sunsetting 567 Labs and Open Sourcing the Course Content</title> <author>Jason Liu</author> <category>567 Labs</category> <category>Courses</category> <category>Open Source</category> <category>RAG</category> <category>Writing and Communication</category> <description>Sunsetting 567 Labs, closing the courses today, and open sourcing the written content from transcripts as ebooks.</description> <link>https://jxnl.co/writing/2026/02/02/sunsetting-567-labs/</link> <pubDate>Mon, 02 Feb 2026 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2026/02/02/sunsetting-567-labs/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2026/02/02/sunsetting-567-labs.png" type="image/png" length="62096" /> </item> <item> <title>Things</title> <author>Jason Liu</author> <category>Personal</category> <category>personal</category> <category>recommendations</category> <category>things</category> <description>A list of things I&#39;ve been using and plan to use.</description> <link>https://jxnl.co/writing/2026/01/24/things/</link> <pubDate>Sat, 24 Jan 2026 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2026/01/24/things/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2026/01/24/things.png" type="image/png" length="18845" /> </item> <item> <title>Do Your Engineers Know How to Leverage AI?</title> <author>Jason Liu</author> <category>Applied AI</category> <description>A letter to the readers of the AI Coding Accelerator.</description> <link>https://jxnl.co/writing/2025/09/11/do-your-engineers-know-how-to-leverage-ai/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/do-your-engineers-know-how-to-leverage-ai/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/do-your-engineers-know-how-to-leverage-ai.png" type="image/png" length="40422" /> </item> <item> <title>Coding Agents Speaker Series: Lessons from Industry Leaders</title> <category>Coding Agents</category> <category>Context Engineering</category> <category>Multi-Agent Systems</category> <category>RAG</category> <category>RAG</category> <category>Speaker Series</category> <category>Speaker Series</category> <description>Deep insights from the teams behind Devin, Amp, Cline, and Augment on building effective coding agents. Learn why simple approaches are winning over complex architectures in autonomous coding systems.</description> <link>https://jxnl.co/writing/2025/09/11/coding-series-index/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/coding-series-index/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/coding-series-index.png" type="image/png" length="54322" /> </item> <item> <title>RAG Master Series: Complete Guide to Retrieval-Augmented Generation</title> <category>AI</category> <category>Machine Learning</category> <category>RAG</category> <category>RAG</category> <category>Retrieval-Augmented Generation</category> <category>Series</category> <description>Comprehensive guide to building, improving, and scaling RAG systems. From fundamentals to advanced enterprise implementations with real-world examples and proven strategies.</description> <link>https://jxnl.co/writing/2025/09/11/rag-series-index/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/rag-series-index/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/rag-series-index.png" type="image/png" length="49572" /> </item> <item> <title>Domain Experts: The Lever for Vertical AI</title> <category>RAG</category> <category>Speaker Series</category> <category>domain experts</category> <category>evaluation</category> <category>prompting</category> <category>security</category> <category>trust</category> <category>vertical AI</category> <description>How to successfully apply LLMs in specialized industries by building domain‑expert review loops, augmenting prompts with expert knowledge, and earning customer trust.</description> <link>https://jxnl.co/writing/2025/09/11/domain-experts-the-lever-for-vertical-ai/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/domain-experts-the-lever-for-vertical-ai/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/domain-experts-the-lever-for-vertical-ai.png" type="image/png" length="47832" /> </item> <item> <title>Text Chunking Strategies for RAG Applications</title> <category>ChromaDB</category> <category>RAG</category> <category>Speaker Series</category> <category>evaluation</category> <category>heuristic chunking</category> <category>retrieval performance</category> <category>semantic chunking</category> <category>text chunking</category> <description>Technical session with Anton from ChromaDB on text chunking fundamentals, evaluation methods, and practical tips for improving retrieval performance</description> <link>https://jxnl.co/writing/2025/09/11/text-chunking-strategies-for-rag-applications/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/text-chunking-strategies-for-rag-applications/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/text-chunking-strategies-for-rag-applications.png" type="image/png" length="58731" /> </item> <item> <title>Why Grep Beat Embeddings in Our SWE-Bench Agent (Lessons from Augment)</title> <category>Coding Agent Series</category> <category>RAG</category> <category>RAG</category> <category>Speaker Series</category> <category>agentic systems</category> <category>agents</category> <category>autonomous coding</category> <category>retrieval</category> <description>Insights from Colin Flaherty on building autonomous coding agents and how agentic approaches reshape retrieval-augmented generation systems.</description> <link>https://jxnl.co/writing/2025/09/11/why-grep-beat-embeddings-in-our-swe-bench-agent-lessons-from-augment/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/why-grep-beat-embeddings-in-our-swe-bench-agent-lessons-from-augment/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/why-grep-beat-embeddings-in-our-swe-bench-agent-lessons-from-augment.png" type="image/png" length="59872" /> </item> <item> <title>Why Cognition does not use multi-agent systems</title> <category>Coding Agent Series</category> <category>RAG</category> <category>Speaker Series</category> <category>agent development</category> <category>coding</category> <category>context engineering</category> <category>multi-agent systems</category> <description>A deep dive into why multi-agent systems might not be the optimal approach for coding contexts, exploring context engineering, challenges of context passing between agents, and how single agents with proper context management can outperform multi-agent setups.</description> <link>https://jxnl.co/writing/2025/09/11/why-cognition-does-not-use-multi-agent-systems/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/why-cognition-does-not-use-multi-agent-systems/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/why-cognition-does-not-use-multi-agent-systems.png" type="image/png" length="54024" /> </item> <item> <title>Stop Trusting MTEB Rankings (Kelly Hong, Chroma)</title> <category>Chroma</category> <category>RAG</category> <category>Speaker Series</category> <category>benchmarking</category> <category>embeddings</category> <category>evaluation</category> <category>generative evals</category> <description>A deep dive into generative benchmarking - creating custom evaluation sets from your own data to better assess embedding model performance.</description> <link>https://jxnl.co/writing/2025/09/11/stop-trusting-mteb-rankings-kelly-hong-chroma/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/stop-trusting-mteb-rankings-kelly-hong-chroma/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/stop-trusting-mteb-rankings-kelly-hong-chroma.png" type="image/png" length="59917" /> </item> <item> <title>How Extend Achieves 95%+ Document Automation (Lessons from Eli Badgio)</title> <category>Extend</category> <category>RAG</category> <category>Speaker Series</category> <category>document automation</category> <category>evaluation</category> <category>extraction</category> <category>human-in-the-loop</category> <category>workflow</category> <description>Insights from Eli Badgio, CTO of Extend, on mapping document workflows, building task-specific evaluations, and implementing partial automation with human-in-the-loop approaches for 95%+ extraction accuracy.</description> <link>https://jxnl.co/writing/2025/09/11/how-extend-achieves-95-document-automation-lessons-from-eli-badgio/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/how-extend-achieves-95-document-automation-lessons-from-eli-badgio/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/how-extend-achieves-95-document-automation-lessons-from-eli-badgio.png" type="image/png" length="54091" /> </item> <item> <title>The 12% RAG Performance Boost You&#39;re Missing (Ayush, LanceDB)</title> <category>LanceDB</category> <category>RAG</category> <category>RAG performance</category> <category>Speaker Series</category> <category>embedding models</category> <category>fine-tuning</category> <category>re-rankers</category> <description>Practical approaches to enhancing retrieval quality through fine-tuning, re-ranking, and understanding trade-offs in RAG systems</description> <link>https://jxnl.co/writing/2025/09/11/the-12-rag-performance-boost-youre-missing-ayush-lancedb/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/the-12-rag-performance-boost-youre-missing-ayush-lancedb/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/the-12-rag-performance-boost-youre-missing-ayush-lancedb.png" type="image/png" length="56770" /> </item> <item> <title>Why Glean Builds Custom Embedding Models for Every Customer</title> <category>Glean</category> <category>RAG</category> <category>RAG optimization</category> <category>Speaker Series</category> <category>custom models</category> <category>embedding models</category> <category>enterprise search</category> <category>fine-tuning</category> <description>How Glean achieves 20% search performance improvements through customer-specific embedding models, unified data architecture, and smart feedback loops that most enterprise AI companies are missing.</description> <link>https://jxnl.co/writing/2025/09/11/why-glean-builds-custom-embedding-models-for-every-customer/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/why-glean-builds-custom-embedding-models-for-every-customer/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/why-glean-builds-custom-embedding-models-for-every-customer.png" type="image/png" length="61428" /> </item> <item> <title>Lexical Search in RAG Applications</title> <category>RAG</category> <category>Speaker Series</category> <category>TF-IDF</category> <category>filtering</category> <category>hybrid search</category> <category>information retrieval</category> <category>lexical search</category> <category>traditional search</category> <description>Guest lecture with John Berryman on traditional search techniques, their application in RAG systems, and how lexical search complements semantic search</description> <link>https://jxnl.co/writing/2025/09/11/lexical-search-in-rag-applications/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/lexical-search-in-rag-applications/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/lexical-search-in-rag-applications.png" type="image/png" length="46604" /> </item> <item> <title>Why Your AI Is Failing in Production (Ben &amp; Sidhant)</title> <category>AI systems</category> <category>RAG</category> <category>Speaker Series</category> <category>debugging</category> <category>evaluation</category> <category>monitoring</category> <category>production</category> <description>AI monitoring, production testing, and data analysis frameworks for identifying issues in AI systems and implementing structured monitoring.</description> <link>https://jxnl.co/writing/2025/09/11/why-your-ai-is-failing-in-production-ben--sidhant/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/why-your-ai-is-failing-in-production-ben--sidhant/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/why-your-ai-is-failing-in-production-ben--sidhant.png" type="image/png" length="57880" /> </item> <item> <title>Data Organization and Query Routing for RAG Systems</title> <category>ChromaDB</category> <category>RAG</category> <category>Speaker Series</category> <category>data organization</category> <category>filtering</category> <category>query routing</category> <category>retrieval optimization</category> <category>vector search</category> <description>Guest lecture with Anton Troynikov from ChromaDB on organizing data for retrieval systems, query routing strategies, and optimizing vector search performance</description> <link>https://jxnl.co/writing/2025/09/11/data-organization-and-query-routing-for-rag-systems/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/data-organization-and-query-routing-for-rag-systems/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/data-organization-and-query-routing-for-rag-systems.png" type="image/png" length="64110" /> </item> <item> <title>The RAG Mistakes That Are Killing Your AI (Skylar Payne)</title> <category>RAG</category> <category>RAG</category> <category>Speaker Series</category> <category>antipatterns</category> <category>best practices</category> <category>data quality</category> <category>evaluation</category> <description>Common RAG anti-patterns across different industries and practical advice for improving AI systems through better data handling, retrieval, and evaluation practices.</description> <link>https://jxnl.co/writing/2025/09/11/the-rag-mistakes-that-are-killing-your-ai-skylar-payne/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/the-rag-mistakes-that-are-killing-your-ai-skylar-payne/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/the-rag-mistakes-that-are-killing-your-ai-skylar-payne.png" type="image/png" length="62628" /> </item> <item> <title>Why I Stopped Using RAG for Coding Agents (And You Should Too)</title> <category>Coding Agent Series</category> <category>RAG</category> <category>RAG</category> <category>Speaker Series</category> <category>agentic exploration</category> <category>code understanding</category> <category>coding agents</category> <category>embeddings</category> <description>Why leading coding agent companies are abandoning embedding-based RAG in favor of direct, agentic approaches to code exploration that mirror how senior engineers actually work.</description> <link>https://jxnl.co/writing/2025/09/11/why-i-stopped-using-rag-for-coding-agents-and-you-should-too/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/why-i-stopped-using-rag-for-coding-agents-and-you-should-too/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/why-i-stopped-using-rag-for-coding-agents-and-you-should-too.png" type="image/png" length="66409" /> </item> <item> <title>How OpenBB Ditched APIs and Put RAG in the Browser (Michael Struwig)</title> <category>OpenBB</category> <category>RAG</category> <category>RAG</category> <category>Speaker Series</category> <category>browser</category> <category>data security</category> <category>function calling</category> <description>A novel approach to RAG systems that leverages the browser as a data layer, connecting agents to sensitive data without traditional APIs.</description> <link>https://jxnl.co/writing/2025/09/11/how-openbb-ditched-apis-and-put-rag-in-the-browser-michael-struwig/</link> <pubDate>Thu, 11 Sep 2025 00:00:00 +0000</pubDate> <source url="https://jxnl.co/feed_rss_created.xml">Jason Liu</source><guid isPermaLink="true">https://jxnl.co/writing/2025/09/11/how-openbb-ditched-apis-and-put-rag-in-the-browser-michael-struwig/</guid> <enclosure url="https://jxnl.co/assets/images/social/writing/2025/09/11/how-openbb-ditched-apis-and-put-rag-in-the-browser-michael-struwig.png" type="image/png" length="54872" /> </item> </channel> </rss>