<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent on Neat Guy Coding</title><link>https://neatguycoding.com/tags/agent/</link><description>Recent content in Agent on Neat Guy Coding</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 NeatGuyCoding</copyright><lastBuildDate>Mon, 18 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://neatguycoding.com/tags/agent/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent Oversight Stack: From Static Evaluation to Trajectory-Level Observability</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-patronus-ai-with-anand-kannappan-weaviate-podcast-122/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-patronus-ai-with-anand-kannappan-weaviate-podcast-122/</guid><description>Agent oversight stack: from static evaluation to trajectory-level observability—evaluation, observability, and supervision for multi-agent systems, with Percival, Lynx, and Glider, and evidence boundaries called out.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-patronus-ai-with-anand-kannappan-weaviate-podcast-122/cover.png"/></item><item><title>Agent-Agnostic Java Quality Guardrails: Put Standards in the Repo with AGENTS.md and Static Analysis</title><link>https://neatguycoding.com/posts/2026-05-18-javaone-2026-agent-agnostic-guardrails-universal-java-code-quality-with-agents-md-and/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-javaone-2026-agent-agnostic-guardrails-universal-java-code-quality-with-agents-md-and/</guid><description>Agent-agnostic Java quality guardrails: use AGENTS.md and static analysis to encode standards in the repository.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-javaone-2026-agent-agnostic-guardrails-universal-java-code-quality-with-agents-md-and/cover.png"/></item><item><title>Agents on Semi-Structured Retrieval: STaRK Benchmark and AvaTaR Optimization</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-optimizing-retrieval-agents-with-shirley-wu-weaviate-podcast-115/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-optimizing-retrieval-agents-with-shirley-wu-weaviate-podcast-115/</guid><description>Stanford&amp;rsquo;s STaRK benchmark and AvaTaR contrastive optimization for retrieval agents on semi-structured knowledge bases—metrics, multi-vector limits, when agents lose to dense retrievers, and what to ship in production.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-optimizing-retrieval-agents-with-shirley-wu-weaviate-podcast-115/cover.png"/></item><item><title>AI-Powered Search: When RAG, Agents, and Classic IR Get Rewired</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-doug-turnbull-and-trey-grainger-on-ai-powered-search-weaviate-podcast-13/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-doug-turnbull-and-trey-grainger-on-ai-powered-search-weaviate-podcast-13/</guid><description>AI-Powered Search: When RAG, agents, and classic IR get rewired—retrieval quality vs. agent loops, long context vs. searchable history, leaderboard embeddings vs. domain corpora, with Doug Turnbull and Trey Grainger on what ships.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-doug-turnbull-and-trey-grainger-on-ai-powered-search-weaviate-podcast-13/cover.png"/></item><item><title>Data Agents: When Code-Writing Models Meet the Real Data Stack</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-data-agents-with-shreya-shankar-weaviate-podcast-135/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-data-agents-with-shreya-shankar-weaviate-podcast-135/</guid><description>Data agents across Snowflake, MySQL, Mongo, and Salesforce—DAB benchmarks, DocETL, tribal knowledge, and agent-first databases, with verifiable claims separated from speaker opinion.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-data-agents-with-shreya-shankar-weaviate-podcast-135/cover.png"/></item><item><title>Enterprise AI on Exabyte-Scale Unstructured Content: Permissions, Layered Retrieval, and Agent Boundaries</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-box-ai-with-ben-kus-and-bob-van-luijt-weaviate-podcast-120/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-box-ai-with-ben-kus-and-bob-van-luijt-weaviate-podcast-120/</guid><description>Enterprise AI on exabyte-scale unstructured content: permissions, layered retrieval, and agent boundaries—engineering lessons from Box × Weaviate on ACL-aware RAG, embedding economics, and production agents.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-box-ai-with-ben-kus-and-bob-van-luijt-weaviate-podcast-120/cover.png"/></item><item><title>Enterprise RAG and Agents: From Frankenstein Pipelines to an Optimizable Whole System</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-contextual-ai-with-amanpreet-singh-weaviate-podcast-114/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-contextual-ai-with-amanpreet-singh-weaviate-podcast-114/</guid><description>Enterprise RAG and agents: from stitched-together pipelines to an end-to-end optimizable system—RAG 2.0, active retrieval, preference learning (KTO/APO), and LMUnit-style evaluation, with evidence boundaries called out.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-contextual-ai-with-amanpreet-singh-weaviate-podcast-114/cover.png"/></item><item><title>Enterprise RAG and Agents: When Vector Databases Meet Four Decades of Analytics Software</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-saurabh-mishra-and-bob-van-luijt-on-weaviate-and-sas-weaviate-podcast-12/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-saurabh-mishra-and-bob-van-luijt-on-weaviate-and-sas-weaviate-podcast-12/</guid><description>Enterprise RAG and agents when vector databases meet four decades of analytics software—engineering tensions in regulated industries, SAS RAM, Weaviate integration, and production boundaries.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-saurabh-mishra-and-bob-van-luijt-on-weaviate-and-sas-weaviate-podcast-12/cover.png"/></item><item><title>Enterprise RAG on Financial Research Corpora: Engineering Trade-offs in Vector Stores, Agents, and Eval</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-morningstar-intelligence-engine-with-aravind-kesiraju-weaviate-podcast-1/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-morningstar-intelligence-engine-with-aravind-kesiraju-weaviate-podcast-1/</guid><description>Enterprise RAG on financial research corpora: engineering trade-offs across vector stores, agents, and eval—ingestion throughput, retrieval granularity, entitlements, and agent latency.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-morningstar-intelligence-engine-with-aravind-kesiraju-weaviate-podcast-1/cover.png"/></item><item><title>From 'It Runs' to 'It's Controlled': Reliable Java AI Agents with Domain Modeling and Koog</title><link>https://neatguycoding.com/posts/2026-05-18-javaone-2026-reliable-ai-agents-using-domain-modeling-with-koog-in-java/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-javaone-2026-reliable-ai-agents-using-domain-modeling-with-koog-in-java/</guid><description>Use domain modeling to move Java AI agents from &amp;lsquo;it runs&amp;rsquo; to &amp;lsquo;it&amp;rsquo;s controlled&amp;rsquo;—orchestration, contracts, and type-safe pipelines with Koog.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-javaone-2026-reliable-ai-agents-using-domain-modeling-with-koog-in-java/cover.png"/></item><item><title>From RAG to Search Agents: Three Tensions in Retrieval, Synthetic Data, and Evaluation</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-search-agents-with-nandan-thakur-weaviate-podcast-137/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-search-agents-with-nandan-thakur-weaviate-podcast-137/</guid><description>From RAG to search agents: BEIR co-author Nandan Thakur on BrowseComp-Plus, synthetic data pipelines, GRPO economics, and why retrieval benchmarks, training cost, and harness design pull in different directions.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-search-agents-with-nandan-thakur-weaviate-podcast-137/cover.png"/></item><item><title>Query Agent on a Vector Database: Auditable Retrieval and Two Ways to Ask Your Data</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-weaviate-s-query-agent-with-charles-pierse-weaviate-podcast-128/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-weaviate-s-query-agent-with-charles-pierse-weaviate-podcast-128/</guid><description>Query Agent on a vector database: auditable retrieval, Ask vs Search modes, schema introspection, multi-collection routing, and what is verified in docs versus speaker claims.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-weaviate-s-query-agent-with-charles-pierse-weaviate-podcast-128/cover.png"/></item><item><title>Stateful Agents and Context Compilation: The Engineering Divide from MemGPT to Letta</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-letta-ai-with-sarah-wooders-weaviate-podcast-117/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-letta-ai-with-sarah-wooders-weaviate-podcast-117/</guid><description>Stateful agents and context compilation: how Letta (from MemGPT) treats the context window as a compiled runtime view—memory tiers, agentic RAG, tool-call unification, multi-agent blocks, and observability—with evidence boundaries called out.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-letta-ai-with-sarah-wooders-weaviate-podcast-117/cover.png"/></item><item><title>Synthetic Data: Boundaries of Data Fabrication in RAG, Agents, and Evaluation</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-synthetic-data-with-david-berenstein-and-ben-burtenshaw-weaviate-podcast/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-synthetic-data-with-david-berenstein-and-ben-burtenshaw-weaviate-podcast/</guid><description>Synthetic data for RAG, agents, and offline evaluation—when to augment, how to trust the distribution, and pipelines from distilabel and Persona Hub to Hub SQL and quality filters.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-synthetic-data-with-david-berenstein-and-ben-burtenshaw-weaviate-podcast/cover.png"/></item><item><title>When Format Constraints Hurt LLMs: A Split Between Agent Pipelines and Benchmark Evaluation</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-let-me-speak-freely-with-zhi-rui-tam-weaviate-podcast-108/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-let-me-speak-freely-with-zhi-rui-tam-weaviate-podcast-108/</guid><description>When format constraints hurt LLMs: the same structured-output techniques often lower scores on reasoning tasks and raise them on discrete classification—from agent pipelines to benchmark evaluation.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-let-me-speak-freely-with-zhi-rui-tam-weaviate-podcast-108/cover.png"/></item></channel></rss>