<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Praneeth Paikray</title><description>Field notes on building, measuring, and operating AI systems.</description><link>https://praneeth16.github.io/</link><item><title>Threat Intelligence on Databricks: From Feed to Investigation</title><link>https://praneeth16.github.io/writing/threat-intelligence-databricks/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/threat-intelligence-databricks/</guid><description>A two-hour workshop that turns fragmented threat feeds into an analyst-ready, agent-assisted investigation workflow.</description><pubDate>Mon, 06 Jul 2026 00:00:00 GMT</pubDate><category>workshop</category><category>cybersecurity</category><category>databricks</category><category>agents</category><category>threat-intelligence</category></item><item><title>What Gemma 4 Reveals About Where Open Model Design is Heading: Part 1</title><link>https://praneeth16.github.io/writing/gemma-4-open-model-design/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/gemma-4-open-model-design/</guid><description>A visual, systems-level breakdown of Gemma 4 architecture choices and what they suggest about open model design.</description><pubDate>Sat, 04 Jul 2026 00:00:00 GMT</pubDate><category>essay</category><category>gemma</category><category>llm-architecture</category><category>open-models</category><category>multimodal</category></item><item><title>What Is a Meta-Harness, Really?</title><link>https://praneeth16.github.io/writing/what-is-a-meta-harness/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/what-is-a-meta-harness/</guid><description>Why enterprises need a control layer above individual coding and agent runtimes.</description><pubDate>Wed, 24 Jun 2026 00:00:00 GMT</pubDate><category>note</category><category>agents</category><category>harnesses</category><category>omnigent</category><category>enterprise</category></item><item><title>Verify Before You Cite</title><link>https://praneeth16.github.io/writing/verify-before-cite/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/verify-before-cite/</guid><description>A small trajectory rule that caught a large class of polished agent failures.</description><pubDate>Thu, 18 Jun 2026 00:00:00 GMT</pubDate><category>note</category><category>evaluation</category><category>agents</category><category>traces</category><category>citations</category></item><item><title>Journey of an Agent: From Demo to Production</title><link>https://praneeth16.github.io/writing/journey-agent-demo-to-production/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/journey-agent-demo-to-production/</guid><description>A practical map of what changes when an agent leaves the notebook and starts serving real users.</description><pubDate>Tue, 02 Jun 2026 00:00:00 GMT</pubDate><category>essay</category><category>agents</category><category>evaluation</category><category>mlflow</category><category>production</category></item><item><title>Compress the Embedding, Keep the Retrieval</title><link>https://praneeth16.github.io/writing/embedding-compression/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/embedding-compression/</guid><description>A research note on reducing vector storage after embeddings are generated.</description><pubDate>Thu, 21 May 2026 00:00:00 GMT</pubDate><category>note</category><category>embeddings</category><category>retrieval</category><category>compression</category><category>vector-search</category></item><item><title>LangGraph vs CrewAI vs DSPy</title><link>https://praneeth16.github.io/writing/langgraph-crewai-dspy/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/langgraph-crewai-dspy/</guid><description>A framework comparison built around one refund assistant, repeated runs, and the costs hidden by a single successful demo.</description><pubDate>Sat, 25 Apr 2026 00:00:00 GMT</pubDate><category>essay</category><category>agents</category><category>benchmarks</category><category>dspy</category><category>langgraph</category><category>crewai</category></item><item><title>Build a Full-Stack Databricks App in Five Prompts</title><link>https://praneeth16.github.io/writing/build-full-stack-databricks-app/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/build-full-stack-databricks-app/</guid><description>What prompt-driven application development gets right, where it breaks, and the engineering checks that still matter.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate><category>essay</category><category>databricks</category><category>apps</category><category>agents</category><category>prototyping</category></item><item><title>Real-Time Agents with FastAPI and WebSockets</title><link>https://praneeth16.github.io/writing/realtime-agents-websockets/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/realtime-agents-websockets/</guid><description>Workshop notes for moving from request-response agents to observable, event-driven systems.</description><pubDate>Sat, 14 Mar 2026 00:00:00 GMT</pubDate><category>workshop</category><category>agents</category><category>fastapi</category><category>websockets</category><category>python</category></item><item><title>Building LLM Agents From Scratch: Crafting a Dynamic NLP Data Generator</title><link>https://praneeth16.github.io/writing/building-llm-agents-from-scratch/</link><guid isPermaLink="true">https://praneeth16.github.io/writing/building-llm-agents-from-scratch/</guid><description>A practical walkthrough of an LLM-based synthetic data generator with learning, creation, and validation stages.</description><pubDate>Tue, 21 Jan 2025 00:00:00 GMT</pubDate><category>essay</category><category>llm-agents</category><category>synthetic-data</category><category>nlp</category><category>python</category></item></channel></rss>