OpenHome already has a useful core: developers can create and iterate on an Agent and Ability, while the conversation experience gives the product its purpose.
Highlights worth preserving
K01 · positive finding
Developers can complete a useful Agent and Ability loop
The bounded API-key workflow completed Agent/Ability creation, push, text invocation, edit, commit, retrigger and source sync. This gives developers a working foundation for iteration. Preserve the successful loop while clarifying session-specific enablement and revision state.
Evidence: report backed
What to preserve and evidence limits
Trial journey, live evidence. Preserve as regression acceptance for future fixes.
Verified in the bounded API-key/text journey. Disable/re-enable success in fresh sessions does not establish existing-session behavior; X01 records the separate active-session limit. Native audio and hardware were not accepted.
K04 · positive finding
The onboarding tour explains conversation controls
The supplied screenshots show a guided tour explaining how to start and stop a conversation, with progress indicators and Back, Next and Skip controls. Gabriel explicitly values having this guidance.
View screenshot evidence (2)
Tour state A. The tour introduces conversation controls and provides Back, Next and Skip. User-supplied screenshot; capture date is not independently verified.Tour state B. The tour includes progress indicators and navigation controls. User-supplied screenshot; capture date is not independently verified.
Evidence: user screenshot and positive report
What to preserve and evidence limits
Preserve the contextual explanation, progress and skip/back/next flow while fixing readability. Verify completion, dismissal, reopening and keyboard access; measure whether new users reach their first conversation without assistance.
Presence and the displayed instruction are screenshot-backed; usefulness is the user's assessment. Successful completion, adoption impact and full accessibility were not tested.
K05 · positive finding
Sleep guidance explains how to resume
The conversation visibly tells the user to call the Agent's name to wake it from sleep mode. The user specifically appreciated the guidance on how to reawaken it.
Evidence: user screenshot and positive report
What to preserve and evidence limits
Preserve actionable wake-up guidance as a clearly identified status message. State the actual accepted wake phrase or action for the current Agent and verify successful recovery without requiring the user to guess.
The guidance is visible and was valued by the user. This does not prove that the attempted phrase was the correct wake phrase or that wake-up recognition worked reliably.
K06 · positive finding
SDK helpers passed bounded hosted checks
40 of 43 methods exercised: 18 working in bounded checks, 22 partially tested and 3 blocked by remaining prerequisites. The corrected foreground suite completed 39 command/recovery cases; instrumented timing samples are available. Synthetic audio is not microphone/speaker acceptance.
Evidence: hosted observation
What to preserve and evidence limits
Preserve these bounded contracts in repeatable regression checks; expand coverage using the per-method prerequisites.
Partial results and three prerequisite blockers are explicit; no universal SDK certification or native audio acceptance.
K07 · positive finding
A relative-time Alarm rang in one reported trial
Gabriel reports a one-minute-from-now request rang about one minute later at 11:08 p.m. A separate screenshot shows a later flooring exchange receiving an ordinary reply after an Alarm interaction; it does not show or establish that the reported one-minute alarm rang.
Evidence: user screenshot and report
What to preserve and evidence limits
Preserve relative-time scheduling and easy topic recovery while correcting unwanted activation.
Single user-reported timing trial; not a measured timing guarantee or certification of the separate Timer Ability. Recovery screenshots rule out a consistent lock-in claim.
Build on the foundation
The priorities below focus on making conversation, execution, onboarding and user control more dependable. Each detail page includes evidence limits and a suggested direction.
Direct tests, source inspection and user reports are labeled separately. Native mobile, physical devices and real audio performance have not been independently verified by this review.
Suggested next discussion
Reproduce the conversation sequence. Correlate transcript, generation and playback events before choosing fixes.
Agree on execution controls. Define immediate disablement and already-running work separately.
Repair one onboarding path. Protect existing developer work and preserve the working baseline.