https://rajasekarvenkatesan.com/ 2026-09-27 weekly 1.0 https://rajasekarvenkatesan.com/work 2026-09-27 monthly 0.9 https://rajasekarvenkatesan.com/video/genai-service-layer.jpg GenAI Service Layer A captioned explainer of GenAI Service Layer. https://rajasekarvenkatesan.com/video/genai-service-layer.mp4 60 https://rajasekarvenkatesan.com/video/agent-service-layer.jpg Agent Service Layer A captioned explainer of Agent Service Layer. https://rajasekarvenkatesan.com/video/agent-service-layer.mp4 63 https://rajasekarvenkatesan.com/video/multi-agent-customer-chatbot.jpg Multi-agent customer chatbot A captioned explainer of Multi-agent customer chatbot. https://rajasekarvenkatesan.com/video/multi-agent-customer-chatbot.mp4 58 https://rajasekarvenkatesan.com/video/ai-powered-travel-planning-experience.jpg AI-powered travel-planning experience A captioned explainer of AI-powered travel-planning experience. https://rajasekarvenkatesan.com/video/ai-powered-travel-planning-experience.mp4 49 https://rajasekarvenkatesan.com/video/policy-enforced-agent-authorization.jpg Policy-Enforced Agent Authorization A captioned explainer of Policy-Enforced Agent Authorization. https://rajasekarvenkatesan.com/video/policy-enforced-agent-authorization.mp4 54 https://rajasekarvenkatesan.com/video/workload-based-model-evaluation.jpg Workload-Based Model Evaluation A captioned explainer of Workload-Based Model Evaluation. https://rajasekarvenkatesan.com/video/workload-based-model-evaluation.mp4 56 https://rajasekarvenkatesan.com/video/unified-enterprise-ai-workspace.jpg Unified Enterprise AI Workspace A captioned explainer of Unified Enterprise AI Workspace. https://rajasekarvenkatesan.com/video/unified-enterprise-ai-workspace.mp4 69 https://rajasekarvenkatesan.com/video/evidence-gated-document-extraction.jpg Evidence-Gated Document Extraction A captioned explainer of Evidence-Gated Document Extraction. https://rajasekarvenkatesan.com/video/evidence-gated-document-extraction.mp4 64 https://rajasekarvenkatesan.com/video/reusable-spreadsheet-workflows.jpg Reusable Spreadsheet Workflows A captioned explainer of Reusable Spreadsheet Workflows. https://rajasekarvenkatesan.com/video/reusable-spreadsheet-workflows.mp4 58 https://rajasekarvenkatesan.com/video/governed-ai-classification.jpg Governed AI Classification A captioned explainer of Governed AI Classification. https://rajasekarvenkatesan.com/video/governed-ai-classification.mp4 68 https://rajasekarvenkatesan.com/video/ai-assisted-legacy-modernization.jpg AI-Assisted Legacy Modernization A captioned explainer of AI-Assisted Legacy Modernization. https://rajasekarvenkatesan.com/video/ai-assisted-legacy-modernization.mp4 58 https://rajasekarvenkatesan.com/video/structured-travel-query-extraction.jpg Structured Travel Query Extraction A captioned explainer of Structured Travel Query Extraction. https://rajasekarvenkatesan.com/video/structured-travel-query-extraction.mp4 57 https://rajasekarvenkatesan.com/video/synthetic-media-provenance.jpg Synthetic Media Provenance A captioned explainer of Synthetic Media Provenance. https://rajasekarvenkatesan.com/video/synthetic-media-provenance.mp4 63 https://rajasekarvenkatesan.com/video/dociq.jpg DocIQ: Document Intelligence A captioned explainer of DocIQ: Document Intelligence. https://rajasekarvenkatesan.com/video/dociq.mp4 54 https://rajasekarvenkatesan.com/video/tacit.jpg Tacit: Curated Organizational Knowledge A captioned explainer of Tacit: Curated Organizational Knowledge. https://rajasekarvenkatesan.com/video/tacit.mp4 54 https://rajasekarvenkatesan.com/video/smartresearch.jpg SmartResearch: Steerable Research A captioned explainer of SmartResearch: Steerable Research. https://rajasekarvenkatesan.com/video/smartresearch.mp4 58 https://rajasekarvenkatesan.com/video/reusable-agent-skills-and-portable-knowledge.jpg Reusable Agent Skills and Portable Knowledge A captioned explainer of Reusable Agent Skills and Portable Knowledge. https://rajasekarvenkatesan.com/video/reusable-agent-skills-and-portable-knowledge.mp4 57 https://rajasekarvenkatesan.com/video/voice-ai-for-staff-operations.jpg Voice AI for Staff Operations A captioned explainer of Voice AI for Staff Operations. https://rajasekarvenkatesan.com/video/voice-ai-for-staff-operations.mp4 71 https://rajasekarvenkatesan.com/writing 2026-09-27 weekly 0.8 https://rajasekarvenkatesan.com/articles/mcp-2-0-what-changed 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/mcp-2-0-what-changed.jpg MCP 2.0? What Changed, What Remained, and How it Impacts Practitioners Enterprise field notes on the MCP 2026-07-28 revision: stateless HTTP, retry correctness, identity, state handles and the controls practitioners still own. https://rajasekarvenkatesan.com/video/mcp-2-0-what-changed.mp4 60 https://rajasekarvenkatesan.com/articles/your-agent-has-too-many-tools 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/your-agent-has-too-many-tools.jpg Your Agent Has Too Many Tools, and No Way to Take Any Back Tool discovery and tool permission are different problems. Field notes on deferred loading, runtime capability gating, trusted-state controls and model fallbacks. https://rajasekarvenkatesan.com/video/your-agent-has-too-many-tools.mp4 60 https://rajasekarvenkatesan.com/articles/open-weights-are-good-enough 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/open-weights-are-good-enough.jpg Open Weights Are Good Enough. The Hard Part Is Everything After. Open models now match commercial ones on most enterprise work at a fraction of the cost. The differentiating skill is no longer picking a model. It is drawing the open-versus-commercial line well, and running the open side with discipline. https://rajasekarvenkatesan.com/video/open-weights-are-good-enough.mp4 67 https://rajasekarvenkatesan.com/articles/gpt-5-6-what-actually-changed-on-your-bill 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/gpt-5-6-what-actually-changed-on-your-bill.jpg GPT-5.6: What Actually Changed on Your Bill Read the diff, not the demo. Field notes on the GPT-5.5 to 5.6 migration: the flagship price held, but a few things that used to be free now cost money and several defaults moved underfoot. https://rajasekarvenkatesan.com/video/gpt-5-6-what-actually-changed-on-your-bill.mp4 59 https://rajasekarvenkatesan.com/articles/agentic-engineer-part-3 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/agentic-engineer-part-3.jpg The Agentic Engineer [Part 3/3]: Into the Brownfield What changes when you point an AI coding agent at a large codebase you didn't write: mapping subagents, reverse-engineered configs, discovered-convention skills, and characterization tests. https://rajasekarvenkatesan.com/video/agentic-engineer-part-3.mp4 58 https://rajasekarvenkatesan.com/articles/agentic-engineer-part-2 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/agentic-engineer-part-2.jpg The Agentic Engineer [Part 2/3]: Shipping a Feature Without Losing the Thread The full pipeline for running an AI coding agent on a real feature: spec, data contracts, controlled fan-out, arbitrated review, and bounded autonomy. https://rajasekarvenkatesan.com/video/agentic-engineer-part-2.mp4 58 https://rajasekarvenkatesan.com/articles/agentic-engineer-part-1 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/agentic-engineer-part-1.jpg The Agentic Engineer [Part 1/3]: Claude Code Is Not a Chatbot. It's an Engineer You Build Structure Around. Why the structure is the job and the prompting is secondary: how I run an AI coding agent like a production engineering practice. https://rajasekarvenkatesan.com/video/agentic-engineer-part-1.mp4 55 https://rajasekarvenkatesan.com/articles/decompose-first-judge-last 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/decompose-first-judge-last.jpg Decompose First, Judge Last Field notes on evaluating LLM systems in production: why deterministic checks beat an LLM judge, and the one ordering decision that decides whether your evaluation layer works. https://rajasekarvenkatesan.com/video/decompose-first-judge-last.mp4 61 https://rajasekarvenkatesan.com/articles/ai-agent-reads-are-executable 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/ai-agent-reads-are-executable.jpg Everything Your AI Agent Reads Is Executable Inside an AI agent, the line between data and instructions disappears. That single blur is the root of nearly every security risk in agentic AI. https://rajasekarvenkatesan.com/video/ai-agent-reads-are-executable.mp4 57 https://rajasekarvenkatesan.com/articles/llm-api-call-agent-loop 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/llm-api-call-agent-loop.jpg The LLM API Call Quietly Became an Agent Loop One API request now runs a server-side loop of model passes and tool calls. What that buys you, what it quietly costs, and how to decide. https://rajasekarvenkatesan.com/video/llm-api-call-agent-loop.mp4 60 https://rajasekarvenkatesan.com/articles/anthropic-openai-same-answer 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/anthropic-openai-same-answer.jpg Anthropic and OpenAI Just Shipped the Same Answer to AI Agents, Seven Days Apart Inside one week in April 2026, the two largest frontier labs independently shipped the same agent architecture: a clean split between harness and sandbox. The convergence matters more than either release. https://rajasekarvenkatesan.com/video/anthropic-openai-same-answer.mp4 62 https://rajasekarvenkatesan.com/articles/prompts-are-technical-debt 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/prompts-are-technical-debt.jpg Your Prompts Are Technical Debt: A Migration Framework for Production LLM Systems A prompt in production is a contract with a specific model version. When the model changes, the contract is voided. Here is a four-layer framework to migrate without the firefighting. https://rajasekarvenkatesan.com/video/prompts-are-technical-debt.mp4 55 https://rajasekarvenkatesan.com/articles/superpowers-stops-winging-it 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/superpowers-stops-winging-it.jpg Your AI Coding Agent Is Winging It. Superpowers Makes It Stop. The most popular Claude Code plugin doesn't make your agent faster. It makes your agent think before it types: brainstorm, plan, test, review, then ship. https://rajasekarvenkatesan.com/video/superpowers-stops-winging-it.mp4 58 https://rajasekarvenkatesan.com/articles/making-most-of-claude-code 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/making-most-of-claude-code.jpg Making the Most of Claude Code: Best Practices & Hidden Features A practical guide to the underused features and workflows that get the most out of Claude Code: context management, CLAUDE.md, hooks, skills, subagents, MCP, and more. https://rajasekarvenkatesan.com/video/making-most-of-claude-code.mp4 67 https://rajasekarvenkatesan.com/articles/rise-of-harness-engineering 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/video/rise-of-harness-engineering.jpg The Rise of Harness Engineering: Why the Code Around the Model Matters More Than the Model Itself One team moved a coding agent from the bottom 30 to the top 5 on Terminal-Bench 2.0. Same model, same weights, zero retraining. They only changed the harness. https://rajasekarvenkatesan.com/video/rise-of-harness-engineering.mp4 53 https://rajasekarvenkatesan.com/about 2026-09-27 monthly 0.8 https://rajasekarvenkatesan.com/connect 2026-09-27 monthly 0.6 https://rajasekarvenkatesan.com/principles 2026-09-27 monthly 0.7 https://rajasekarvenkatesan.com/bio 2026-09-27 yearly 0.5