Skip to main content

Submit

Register your build for the showcase. You can update the demo URL right up until you're called — submitting twice updates your entry, it never duplicates it.

Or just ask your agent

Once Arm Your Agent is wired up to the agenthack MCP server, the fastest path is to ask your own coding agent to submit for you — it calls the same submit_project tool a host would use to check the board:

Submit our project. It's called <name>, deployed at <your worker URL>, and here's what it
does: <one sentence>.

If the tool isn't live yet when you get here, use the form above once M6 ships it, or ask a host — nothing about the showcase depends on the MCP server being available.

How judging works

Final score = agent rubric (reviewed and approved by a human host) + room vote.

DimensionWhat it asks
WorksDoes the deployed agent actually respond and do the thing?
Agentic depthTools, state, scheduling, durability — or a completion call in a trench coat?
Industry relevanceWould someone in this industry recognise the problem as real?
Path to productionIs there a credible route from this demo to something shippable?
Human approval gateDoes your agent have a human approval gate?

A Workflow scores your submission automatically — screenshot, a quick probe if you registered handle_request, a rubric pass — and then pauses for a human host to approve or override it live, on the big screen, before it counts. That's not a formality; it's the same accountability theme as the human approval gate above, aimed at the judging itself.

What happens at the showcase

Each of the 7–8 teams gets a couple of minutes to demo, live on the big-screen Mission Control board. Then the finale fans one cross-industry scenario out across every team that opted into handle_request — if you built it, bring it.

Good luck.