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.
| Dimension | What it asks |
|---|---|
| Works | Does the deployed agent actually respond and do the thing? |
| Agentic depth | Tools, state, scheduling, durability — or a completion call in a trench coat? |
| Industry relevance | Would someone in this industry recognise the problem as real? |
| Path to production | Is there a credible route from this demo to something shippable? |
| Human approval gate | Does 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.