From a result
to the next request
Check the day and ask a follow-up. Short replies stay associated with the candidates and change draft the user is looking at.
Case 05 · AI Personal Assistant
Use voice and a screen on Mac, or Telegram and mobile web elsewhere, to check schedules, tasks, goals and content production progress. Each channel keeps its own request and approval context.
Check the day and ask a follow-up. Short replies stay associated with the candidates and change draft the user is looking at.
Review and edit transcribed speech or extracted photo text before sending it. Listen to replies and stop playback when needed.
Inspect a draft before changing a schedule or task. Save the outcome so the same request can be checked after reconnecting.
I chose to prevent duplicate changes and expose the actual state, even when that meant giving up the convenience of an automatic retry.
Fixed cases where a short follow-up lost the actionable draft. Preserve the previous candidates and invalidate an earlier approval when the draft changes.
A change may have been saved even when its response is lost. Do not repeat it automatically; show the uncertain state and check the existing record after reconnection.
A failed lookup must not look like an empty calendar. Separate unnecessary lookups from the conversation and reduce repetitive diagnostic notices.
I defined useful tasks and failure criteria, divided AI-assisted development work, and reviewed the integrated result. AI supported implementation; product scope and final acceptance remained my responsibility.
Check that requested candidates are not lost, stale approvals cannot run again, and uncertain results never appear as success.
Connected Python-based work functions, conversation handling and saved records to the Mac app, Telegram and mobile web. Integrated voice and photo text extraction (OCR) into the reviewable input flow.
Everyday functions were checked through real tool connections. Approval and recovery exceptions were checked with non-personal examples and isolated tests.2
Early functional tests and wake-word comparisons predate later changes. False wakes and missed real calls were evaluated together; those results are not reused as current product-wide performance.
Understanding a request and changing external information are different responsibilities. I make that boundary visible in the product.