From Manual Meeting Notes to an Agent-Run Meeting Summary
Before
After every call, I opened the recording, replayed the parts I missed, typed notes by hand, copied action items into a separate doc, and wrote a summary to send to the team. By the time the notes were ready, the next meeting had already started.
After
Now an agent drafts the summary from the recording, pulls out decisions and next steps, and files it where the team can find it. I review the draft, fix anything it missed, and send it. The notes are ready while the conversation is still fresh, and nothing agreed on the call gets lost.
Shipping the design system and agent skills together with the template is a smart move, it gives the Framer Agent rules to follow instead of guessing. Curious how well it keeps new sections on-brand.
What sells it for me is the refusal telling the agent exactly where the token should go. A bare "no hex" error usually just sends it looping. Does guard.mjs run only as an agent hook, or in pre-commit too so it catches humans as well?
A status label alone doesn't explain what happens next.
In this Strata practice project, the request screen combines the resident's conversation with the building manager, its current status, and a progress timeline.
A useful UX check is to ask which updates customers still have to call for. If the answer is already in the system, make it visible to them.
Which update would you put on screen first?
Practice UX/UI project for a fictional company. Sample data.