.png&w=256&q=75)
Kaman singh anand@jhonsmith007
2
Events attended
1
Submissions made
India
1 year of experience
About me
I'm Kmn — an AI builder based in Nashik, working across autonomous agents and applied AI products. Currently: building a cost-aware general-purpose AI agent for the AMD Developer Hackathon (Track 1) — a Dockerized agent that classifies incoming questions across 8 categories and routes each to the cheapest backend that can still answer it correctly (a free local model for simple tasks, a paid API only when accuracy demands it). Built, containerized, pushed to a public registry, and tested end-to-end against real infrastructure, including finding and fixing two live bugs. Other AI work: an Indian equities analysis agent that delivers AI-generated market reports over Telegram (n8n + Groq); Vicky, a conversational AI travel-planning agent debugged through eight confirmed production issues; and Next Vicky, a premium Android-first AI phone assistant concept. Certifications: Anthropic's AI Fluency series (Students, Educators, Framework & Foundations, Nonprofits, Small Businesses, AI Capabilities & Limitations), Claude 101, Claude Code 101, Introduction to Claude Cowork, and Model Context Protocol fundamentals (in progress). Recognition: CampusCrew 100K Milestone Honor (June 2026).
🤓 Latest Submissions
track one project
I am Kaman Singh Anand, my email is [email protected], contact me at 9604090790, please help me with a good group as i want to fuel my passion as a 16 year old, i would really apprieciate your help, i made this project all by myself and ai, i have no team so this was a solo, this is my first time participating in a hackathon and i could only make the track one project as given, i made it in 1 day, due to some critical difficulties i could not get more time, anyways here is my actual discription A cost-aware AI agent built for Track 1 that routes every question to the cheapest backend that can still answer it correctly, instead of sending everything through Fireworks. How it works: a free, instant classifier sorts each question into one of the 8 required categories. Factual knowledge, sentiment, summarization, and named entity recognition go to a quantized Qwen2.5-3B model bundled in the container, running fully offline at zero token cost. Math, logic puzzles, code debugging, and code generation route to Fireworks, since testing showed the local model reliably struggles with multi-step reasoning even with careful prompting. Built-in safeguards, found through real testing: low-confidence classifications get a free local second opinion before routing; local answers that look like non-answers auto-escalate to Fireworks; multi-part questions route straight to Fireworks after the local model was caught dropping the second half of compound questions; summaries with explicit length limits are deterministically trimmed to comply. Fireworks calls run concurrently, not one-by-one, keeping runtime well inside the 10-minute limit even on larger task sets. The container falls back gracefully at every failure point rather than crashing, and a final validation pass guarantees schema-valid JSON output. Built in Python with llama-cpp-python for local inference, Docker (linux/amd64), ~2.3GB compressed.
13 Jul 2026
