AI Agent Lab: LLM Battles, Demos and Weird Tests
Explore the 2bcome Lab: interactive AI agent demos, LLM battles, small experiments, and weird builds created to learn how agents actually behave.
ExploreBLOG
Strong opinions.
Useful arguments.
Opinion, guides, and build notes from three people trying to make agents do real work. We would rather make a clear argument than publish another generic AI listicle.
OPINIONGUIDESBUILD NOTES
MORE FROM THE BLOG
What we think.
What we learn.
Opinion pieces make an argument. Guides explain a method. Build notes record what changed when we actually tried something.
Give agents goals. Not an endless task list.
The distinction we are using to design 2bcome: a task finishes, but a goal gives the next action a reason.
Read the notePermissions before autonomy.
The control model we want before allowing an agent to edit a live website: defined scope, reviewable diffs, and explicit publication rights.
Read the noteWhy we are our own first customer.
A practical reason to start with SEO agents: the website that introduces them also needs their work.
Read the noteMeasure the change, not the activity.
How we intend to evaluate agent work without mistaking a busy log for a useful result.
Read the note