AI Frontend EngineerAbhirupa Mitra · Senior Frontend Engineer · Agentic AI Interfaces
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.
Read the guideFrontend work at Slack for agentic AI — the surfaces where agents reason, pause, and hand control back.
Working notes on designing frontends for AI, published while the ink is still wet.
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.
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.
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.
Exploring how modern frontend design can make an AI's hidden reasoning visible — turning abstract model introspection into human-understandable insight.
UI/UX research and process — starting from the person, treating the model as a material.
Working prototypes for agentic AI — interfaces that reveal an agent’s state, confidence, and thinking, beyond loaders and progress bars.
More experiments are in the workshop. New agentic-interface prototypes land here as they come to life.
