--- title: "Rudrendu Paul (@rudrendupaul) | Hashnode" description: "AI, Ads & Marketing Data Science Leader | Gen AI | LLM | AI Agents | Applied AI/ML | Ads | Monetization. Read the latest articles by Rudrendu Paul on Hashnode." url: "https://hashnode.com/@rudrendupaul" --- @rudrendupaul # Rudrendu Paul @rudrendupaul · San Francisco, USA · Joined April 2026 AI, Ads & Marketing Data Science Leader | Gen AI | LLM | AI Agents | Applied AI/ML | Ads | Monetization ### [What Is an Agent Harness? The Architecture Behind Claude Code, DeepSeek Harness, and Hermes Agent](https://freecodecamp.org/news/what-is-an-agent-harness?utm_source=hashnode&utm_medium=feed) On August 13, 2026, DeepSeek published a GitHub repository called deepseek-harness. Within two days, it had passed 95,386 stars and 8,826 forks (a vanity metric on its own, but a spike this fast signa 25 min read · [freecodecamp.org](https://freecodecamp.org/news/what-is-an-agent-harness?utm_source=hashnode&utm_medium=feed) [Sep 11](https://hashnode.com/posts/what-is-an-agent-harness/6aa41926c7a41a4b7462a57d) ### [Agentic AI Engineering in Practice: How AI Engineers and Forward-Deployed Engineers Build with Claude Code, Codex, and Gemini](https://freecodecamp.org/news/agentic-ai-engineering-in-practice-how-to-build-with-claude-code-codex-and-gemini?utm_source=hashnode&utm_medium=feed) A practical, three-tool guide to the AI-native software development life cycle (SDLC): Plan, Design, Build, Test, Deploy, Maintain, reimagined for agentic coding. In March 2025, a small nonprofit rese 40 min read · [freecodecamp.org](https://freecodecamp.org/news/agentic-ai-engineering-in-practice-how-to-build-with-claude-code-codex-and-gemini?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/agentic-ai-engineering-in-practice-how-to-build-with-claude-code-codex-and-gemini/6a9aee151eb1bdc38db233af) [Sep 4](https://hashnode.com/posts/agentic-ai-engineering-in-practice-how-to-build-with-claude-code-codex-and-gemini/6a9aee151eb1bdc38db233af) ### [Product Experimentation at Scale: How Airbnb, Netflix, Lyft, and Uber run Causal Inference on LLM-Based AI Features](https://freecodecamp.org/news/causal-inference-at-scale-with-case-studies?utm_source=hashnode&utm_medium=feed) Causal inference for LLM-based AI features is no longer theoretical. Airbnb, Netflix, Lyft, and Uber have published detailed engineering blog posts describing exactly how they measure the causal impac 37 min read · [freecodecamp.org](https://freecodecamp.org/news/causal-inference-at-scale-with-case-studies?utm_source=hashnode&utm_medium=feed) [Aug 11](https://hashnode.com/posts/causal-inference-at-scale-with-case-studies/6a7b522a304c202420dfd496) ### [Product Experimentation with Doubly Robust Estimation: When Both Your Models Are Wrong in LLM Applications](https://freecodecamp.org/news/doubly-robust-estimation-for-llm-product-experiments?utm_source=hashnode&utm_medium=feed) Your AI product shipped an agent-mode opt-in six months ago. You ran a propensity analysis, adjusted for engagement tier and query confidence, and reported a clean +8 percentage-point lift in task com 23 min read · [freecodecamp.org](https://freecodecamp.org/news/doubly-robust-estimation-for-llm-product-experiments?utm_source=hashnode&utm_medium=feed) [Aug 11](https://hashnode.com/posts/doubly-robust-estimation-for-llm-product-experiments/6a7a662d92a5f4f663b525f9) ### [Product Experimentation with Instrumental Variables: Unconfounding LLM Routing Decisions in Python](https://freecodecamp.org/news/instrumental-variables-for-llm-routing-in-python?utm_source=hashnode&utm_medium=feed) For data science leaders and product managers who are overseeing multi-model gateways, the standard regression approach to measuring model quality is fundamentally flawed. You're running a causal infe 21 min read · [freecodecamp.org](https://freecodecamp.org/news/instrumental-variables-for-llm-routing-in-python?utm_source=hashnode&utm_medium=feed) [Jul 29](https://hashnode.com/posts/instrumental-variables-for-llm-routing-in-python/6a69ffcc634c4a299b014f9f)