Work With Your Agent

Looky was built so your agent could use it

Everything in Looky is plain text — Malloy models, YAML visualizations and dashboards — published through a validated, human-approved flow. That is exactly the surface AI coding agents are good at. So instead of embedding a chatbot, Looky gives your own agent everything it needs to do the work, while you stay in charge.

• Agents are a dial, not a mode. Work everything by hand, or decide where, when and how much agents participate — from a quick edit in the in-app chat to your own agent running over local files. Everything an agent does, you can do yourself.
• Your agent, your account. Looky ships no AI of its own: the agent — or the provider key that powers the in-app chat — is yours. Keys stay in your browser and are never kept by Looky.
• You approve what ships. Content is validated before publishing, and publishing always requires your explicit yes.
• Viewers are untouched. Your audience keeps seeing dashboards in the browser, exactly as before — the agentic workflow is for the people who build.

Ways to author

Three rungs, by setup effort — pick per task, mix freely:

More rungs next — more chat providers, more workbench agents, and deeper editor integrations: same idea each time, tuned to how that tool works.

Already have your own setup?

Any agent that can read documentation and run a CLI can work with Looky today. Point it at the machine-readable docs — looky.studio/llms.txt — give it a folder linked with looky login, and it has everything: the content contracts, the build order, and looky validate as its safety net. The rungs above just make that setup effortless.