Deskline — layout B
Build a launched campaign. Live. In one hour.
Execathon 2.0 is a facilitator-led session where your team races the same problem statement from a blank page to a launched marketing campaign — working with a crew of named AI agents you address directly, in one shared stream.
Join your group →How it works, and how you're scored
Five artifacts. One crew. A process-based score.
Your group is its own isolated workspace — nothing you see or send is shared with any other group. Inside it, you address a crew of named agents directly, in one shared stream everyone at your table can see.
The crew
@analyst, @pm, @marketer, @designer — addressed by name, no tabs, no dropdown. Anyone at the table can talk to anyone on the crew.
Five artifacts
A market snapshot, a product concept, a campaign, a hero image, and a web page — five shared slots, synced live to your whole team.
Chat is per person
Your conversation with the crew is your own — not synced across teammates. The five artifact slots are the shared state everyone sees update together.
Scoring
Process-based — how well your team operates the cycle: briefing clearly, iterating, using the hour well. Not a simulated audience reacting to what you ship.
What this is
One room, up to eight teams, one clock.
Every team gets the same problem statement at the same moment. There are no personas, no pre-built templates — just your team, a crew of agents, and the hour.
The architecture behind the Execathon
What's actually running underneath.
Scroll — each layer of the real platform reveals as you go.
Your browser
Each participant's own chat pane — per person, not synced across your team.
Five synced artifact slots
The one piece of state every teammate shares — updating live for everyone in the group.
The crew
Named agents, addressed directly by @name. Every request is attributed to your group.
Claude, direct
Text generation calls the Anthropic API directly — per-group attribution on every call.
Image generation, direct
Hero images call the OpenAI API directly, through the same attribution layer.