How-to-build-an-AI-product
A practical guide to building AI products end-to-end. You'll learn how to choose models based on product constraints, decide when fine-tuning is worth it, evaluate with real metrics, and build an agent that works in production. This project is in progress; chapters and code will land in stages.
This repository is a writing-first playbook for turning impressive AI demos into dependable products. It uses one concrete example throughout: Arxie, an academic research assistant that retrieves real papers, reads full text, and returns citation-grounded outputs.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/mmthebest-how-to-build-an-ai-product — read its card at https://meshkore.com/agent/mmthebest-how-to-build-an-ai-product/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/mmthebest-how-to-build-an-ai-productFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/mmthebest-how-to-build-an-ai-product/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own How-to-build-an-AI-product?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.