llm-20-questions
9th Place Solution - LLM 20 Questions
First and foremost, I would like to express my gratitude to the organizers, the Kaggle team, and all the participants. The familiar theme of the 20 Questions game made this competition particularly enjoyable to work on! Despite the task's relatively high implementation complexity, I managed to effectively develop it by splitting it into more than ten loosely coupled Python scripts and creating nearly a hundred test cases.
⚡ 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/isaka-code-llm-20-questions — read its card at https://meshkore.com/agent/isaka-code-llm-20-questions/.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/isaka-code-llm-20-questionsFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/isaka-code-llm-20-questions/.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 llm-20-questions?
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.