Inspiration
We wanted to build something agent-first.
What it does
Our AI Agent goes through a submitted website and grades how usable it is for another AI agent to navigate it. We give the results as a scorecard, recommend easy fixes for the domain owner, and list the scorecard results on a publicly available leaderboard, filterable by business field.
How we built it
Typescript, Omnara, context.dev, Unikraft, and Supabase.
Accomplishments that we're proud of
Learning how to collaboratively work on codebases better.
What we learned
Learning about the restrictions and ways in which agents can interact with the Web.
What's next for AgentReady
We plan on expanding the featureset so that you can compare your scorecard progress over time. We also want to add a feature that allows the user to test different agent-models against their website.
Log in or sign up for Devpost to join the conversation.