https://abhirupamitra.com/ Abhirupa Mitra is a senior frontend engineer at Slack designing agentic AI interfaces — the UI and UX research layer where AI agents think alongside people. A personal knowledge ecosystem on frontend for AI, design thinking, and slow living. en-us Fri, 25 Sep 2026 00:00:00 GMT https://abhirupamitra.com/the-practice/i-overloaded-slacks-job-queue/ https://abhirupamitra.com/the-practice/i-overloaded-slacks-job-queue/ Fri, 25 Sep 2026 00:00:00 GMT What a million-user mistake taught me about backfills, thundering herds, fan-out, and why randomized delays exist. system-design scale backfills job-queues caching incident https://abhirupamitra.com/field-notes/how-do-agents-talk-to-each-other/ https://abhirupamitra.com/field-notes/how-do-agents-talk-to-each-other/ Mon, 21 Sep 2026 00:00:00 GMT Explaining the A2A protocol that powers complex orchestration systems — Agent Cards, task lifecycles, streaming subscriptions, and why an unverified card is an open door. agentic-ai a2a-protocol multi-agent orchestration mcp https://abhirupamitra.com/the-practice/ai-assisted-coding-setup-guide/ https://abhirupamitra.com/the-practice/ai-assisted-coding-setup-guide/ Wed, 19 Aug 2026 00:00:00 GMT Months of what worked and what didn't — context engineering, spec-driven development, sub-agents, skills, and harness engineering, plus what the research actually says about token cost. ai-tooling context-engineering claude-code agents-md spec-driven-development developer-workflow https://abhirupamitra.com/field-notes/can-llms-jump-a-beginner-s-guide-to-jepa-and-multi-modality-world-models/ https://abhirupamitra.com/field-notes/can-llms-jump-a-beginner-s-guide-to-jepa-and-multi-modality-world-models/ Sun, 09 Aug 2026 00:00:00 GMT Why LLMs can't make the creative leap from data to discovery, and how JEPA — Yann LeCun's world-model architecture — might finally close the gap between language models and real reasoning. jepa world-models llm yann-lecun ai-reasoning https://abhirupamitra.com/the-practice/designing-gemini-chat-frontend-for-100m-llm-users/ https://abhirupamitra.com/the-practice/designing-gemini-chat-frontend-for-100m-llm-users/ Wed, 29 Jul 2026 00:00:00 GMT A frontend engineer's perspective on designing a complex agentic interface: streaming, state, rendering, and failure. agentic-ui llm frontend streaming state-management system-design https://abhirupamitra.com/design-thinking/breaking-down-harness-engineering-how-to-vibecode-like-a-senior-engineer/ https://abhirupamitra.com/design-thinking/breaking-down-harness-engineering-how-to-vibecode-like-a-senior-engineer/ Thu, 23 Jul 2026 00:00:00 GMT Here's everything around the model that makes the model good — and how to build your own agent harness: the phased workflow, grading criteria, and guardrails that separate senior engineering from unguided vibecoding. harness-engineering agentic-ai claude-code ai-agents developer-workflow https://abhirupamitra.com/design-thinking/i-don-t-trust-the-internet-anymore-here-s-what-will-make-it-better/ https://abhirupamitra.com/design-thinking/i-don-t-trust-the-internet-anymore-here-s-what-will-make-it-better/ Thu, 16 Jul 2026 00:00:00 GMT Storytelling in the age of AI: authenticity vs. automation, rebuilding trust online through human stories, and why imperfection is what makes us different. ai storytelling authenticity trust technology https://abhirupamitra.com/design-thinking/how-goodhart-s-law-ate-your-ai-strategy/ https://abhirupamitra.com/design-thinking/how-goodhart-s-law-ate-your-ai-strategy/ Fri, 10 Jul 2026 00:00:00 GMT An interesting story that needs to be heard — and why we should be more concerned now than ever. ai-strategy goodharts-law metrics engineering-culture agentic-ai https://abhirupamitra.com/field-notes/why-every-serious-agent-orchestrator-is-secretly-a-dag/ https://abhirupamitra.com/field-notes/why-every-serious-agent-orchestrator-is-secretly-a-dag/ Tue, 28 Apr 2026 00:00:00 GMT Inside the graph theory powering AI agent orchestration — how DAGs, topological sorting, and Kahn's algorithm enable parallel multi-agent execution, reliable agent-to-agent communication, and dynamic MCP server loading at scale. agentic-ai orchestration graph-theory multi-agent mcp https://abhirupamitra.com/the-practice/the-complete-ai-mcp-server-setup-for-10x-faster-production-code/ https://abhirupamitra.com/the-practice/the-complete-ai-mcp-server-setup-for-10x-faster-production-code/ Thu, 16 Apr 2026 00:00:00 GMT Raw notes on the AI arsenal — LLM picks, prompt engineering, and MCP servers — behind writing scalable, production-ready code 10x faster. mcp ai-tooling claude-code developer-workflow agentic-ai https://abhirupamitra.com/the-practice/hosting-my-full-stack-next-js-app-on-vercel-render/ https://abhirupamitra.com/the-practice/hosting-my-full-stack-next-js-app-on-vercel-render/ Mon, 23 Mar 2026 00:00:00 GMT A first-hand walkthrough of deploying a Next.js full-stack app — CORS nightmares, env variable setup, and a domain setup that'll make you question your career. No AI could save me. This guide might save you. nextjs deployment vercel render cors https://abhirupamitra.com/the-practice/demystifying-mcp-servers-the-part-no-one-explains-well/ https://abhirupamitra.com/the-practice/demystifying-mcp-servers-the-part-no-one-explains-well/ Thu, 11 Dec 2025 00:00:00 GMT A clear, practical look at MCP servers and their real value in today's tech world — what they are, why LLMs need them, and how one actually works under the hood. mcp llm ai-tooling javascript agentic-ai https://abhirupamitra.com/field-notes/how-i-make-ai-handle-the-boring-parts-of-frontend-so-i-could-focus-on-real-engineering/ https://abhirupamitra.com/field-notes/how-i-make-ai-handle-the-boring-parts-of-frontend-so-i-could-focus-on-real-engineering/ Mon, 01 Dec 2025 00:00:00 GMT Offload the repetitive chaos to AI-powered tools and MCP servers, and save your focus for the tasks that actually make you a better engineer. frontend ai-tooling developer-workflow mcp react https://abhirupamitra.com/field-notes/anthropic-proved-ai-thinks-the-frontend-architecture-we-need-to-watch-it-happen/ https://abhirupamitra.com/field-notes/anthropic-proved-ai-thinks-the-frontend-architecture-we-need-to-watch-it-happen/ Thu, 13 Nov 2025 00:00:00 GMT Exploring how modern frontend design can make an AI's hidden reasoning visible — turning abstract model introspection into human-understandable insight. llm-introspection frontend-architecture agentic-ai ui-design anthropic https://abhirupamitra.com/design-thinking/the-end-of-the-single-truth-rethinking-ai-user-interfaces-to-combat-mode-collapse/ https://abhirupamitra.com/design-thinking/the-end-of-the-single-truth-rethinking-ai-user-interfaces-to-combat-mode-collapse/ Mon, 10 Nov 2025 00:00:00 GMT A very honest POV on designing user interfaces in a way that lets users take control of the narrative and eliminate LLM bias. llm ux mode-collapse ui-design ai-bias