The Voice App

say a request in the car, carry on at the desk, finish it in the kitchen — and the work gets done, not just discussed.

As of September 10, 08:02 PM
What the status words mean proven · done, not independently checked · partly done · not started · blocked · parked
47%partly done

30 steps: 6 proven · 19 partly done · 5 untouched · 0 blocked · 0 parked

agent runs · not recordedtokens used · not recordedreview notes · not recordeddollars charged · not recorded

The plan as first written

Nick speaks, and the thing gets done. In his own words this morning: *"i asked for a working voice app - i dont need the technical works i need to know how thats going to work and whats left"* and *"lets get a useable version of this live somewhere"*. Finished is Nick saying a request out loud on his phone or his Mac, hearing the first word almost immediately, hearing his own people's names said back correctly, and finding the work actually done — not a demo that speaks.

Steps

IdPlain wordsPercentStateProofWhat is left
STEP 1Find out why it does nothing when you ask it for something100% provenNode projects/personal/family-app/_test-voice-requests.mjs --replay reproduces 0 of 5 delivered on today's build, and one cause is named with its file and lineThe step
STEP 2Make a spoken request actually get the thing done90% done, not independently checkedThe same harness that was red in STEP 1 reports 5 of 5 delivered, re-run first-hand by the checkerThe step
STEP 3When you ask for the careful answer, you get one100% provenFive of five deep requests produce audio, and a deliberately broken deep route still speaks a plain sentenceThe step
STEP 4Correcting yourself never gets you the old answer100% provenZero of ten stale takeovers with the older answer deliberately delayed, AND the corrected answer is audibly spoken on ten of ten — silence on any trial is a failure, not a passThe step
STEP 5It stops asking you a question at the end of every answer70% partly doneZero of ten ordinary exchanges end with an unnecessary closing question, and a request that genuinely lacks context still asks for itThe step
STEP 6Five real work requests, five things actually done0% not started5 of 5 on the recorded set and at least 4 of 5 on a fresh set chosen inside the plan's test-request fence, graded by a session that built none of the fixes, and a search for the VOICE-TEST marker afterwards returns nothingThe step
STEP 7A way to time the app you actually open100% provenNode projects/personal/family-app/_test-voice-rig.mjs --selftest --sabotage prints a silent control and a triggered positive on the family window and the installed Mac windowThe step
STEP 8It starts talking while it is still thinking25% partly doneFirst audio begins before the written answer completes on 10 of 10 trials, and STEP 4's ten corrections still show zero stale takeoversThe step
STEP 9You hear the first word inside two seconds20% partly doneNode projects/personal/family-app/_test-voice-rig.mjs --timing --samples 10 reports every one of twenty samples under 2.0 s across both surfaces, against a dated baseline of 7.433 s median; if STEP 7 recorded the installed Mac window as not measurable after three attempts, that surface reads NOT MEASURABLE with its instrument named and the family window still has to pass ten of tenThe step
STEP 10It hears Captus, Chantelle, Jasmin, Anatoly and your clients85% done, not independently checkedThe four names come back exact, and a name deliberately removed from the list transcribes no worse than todayThe step
STEP 11The ten recorded test phrases all come back right20% partly doneThe ten recorded phrases in projects/ops/life-os/audits/A9/LIVE/audio score 10 of 10 exact, scored the same way as the 5 of 10 baseline; 9 of 10 fails, whatever the missed phrase containsThe step
STEP 12Put the work live, on the version you actually open30% partly doneNode projects/ops/deploy.mjs deck-family publishes from a tree at origin/main with projects/personal/family-app/dist removed first, and the served service-worker cache tag read back SIGNED IN equals the tag just built and is newer than the tag before the publish; both deploy guards — the behind-origin refusal and the build-output clearing — are recorded as having runThe step
STEP 13A usable version live: three requests, first word in two seconds, all three done, names right0% not startedAll four conditions pass together on one run of the build STEP 12 published: three of three delivered and read back, first word under 2.0 s each, every name exact — and a search for the VOICE-TEST marker afterwards returns nothingThe step
STEP 14It installs on your phone's home screen and signing in from that icon works20% partly doneThe installed app opens standalone at phone width and reads back the right identity; a signed-out state shows an honest reason on screenThe step
STEP 15Tapping a notification drops you straight into the conversation, ready to talk0% not startedThe tap lands on the right conversation with the microphone armed and the receipt visible; every test notification went only to the one fenced test device and was titled TEST; the test push subscription is deleted; and node projects/personal/skippy-app/design-directions/_pearl-fidelity-check.mjs prints mismatched properties: 0 · unmeasured anchors: 0 at 584x763 light and 390x844 light, with side-by-sides and both verdictsThe step
STEP 16Start in the car, finish at the desk, without repeating yourself10% partly doneOne conversation continues across two signed-in surfaces and back with nothing repeated, and one turn produces one record, not twoThe step
STEP 17Draw the Hub's new voice screens and get them signed off before anything is built95% done, not independently checkedThe drawing is published from one generator at a login-free address, the anchor map is signed with the distinct-element count beside the anchor count, the new check's --selftest prints mismatched properties: 0 · unmeasured anchors: 0 and its sabotage names every compared property, and the hash is machine-written by shasum -a 256The step
STEP 18Voice inside the Hub, where you actually work0% not startedMismatched properties: 0 · unmeasured anchors: 0 at every signed viewport on a populated screen, reproduced by a checker running the same command into its own folder, and the screens published with the served version recordedWaiting on Nick: , as this step's entry condition only: his approving words on STEP 17's drawing, naming the page and revision. This is the single Hub wait and it sits on the first Hub screen being built, exactly where he put it
STEP 19A fair side-by-side against the voice assistants you already use20% partly doneThirty matched trials — the same ten phrases into all three — with every excluded trial counted rather than silently droppedThe step
STEP 20The little program on your Mac gets measured, and a verdict written100% provenVoice is exercised with the program stopped, running, and with the cloud route deliberately failed; the startup file is copied to the lane's evidence folder and the copy is proven to restore; the service is left in the state it was found in; and the verdict is written with what was observed under each conditionThe step
STEP 21The Mac window finished — after the phone version is live, never before20% partly doneThe installed Mac window passes all four of STEP 13's conditions, and the voice-state bridge test is still proven able to failThe step
STEP 22Talking to Skippy through the Echos you already own30% partly doneOne real spoken exchange on a real Echo is recorded, and a recording of a different voice played into the same speaker is correctly refused; if Amazon's recogniser cannot evaluate a played recording at all, that reads NOT MEASURABLE with the instrument named and the refusal check is listed for a person, never counted as a passThe step
STEP 23A current, independent verdict on how the app looks40% partly doneMismatched properties: 0 · unmeasured anchors: 0 at 584x763 light and 390x844 light on the build STEP 15 published, both counts reproduced by a checker, plus one signed verdictThe step
STEP 24The app's final blind review, with a score that is actually current40% partly doneExactly 32 fresh rows merged against the published build with a current score, every NOT MEASURABLE result kept, and neither older score reusedThe step
STEP 25The single image that did not match, opened rather than waved through100% provenPython3 projects/personal/skippy-app/design-directions/_proof-all-designs.py re-runs the sixteen comparisons and the difference is either named or does not reproduceThe step
STEP 26The honest closing note: what worked, what did not, what is left55% partly doneThe postmortem and NEXT list exist in this plan, the older measurement plan's handback row is answered, the wired-room-box correction is readable in both plans, and every failure caught or shipped is appended to the failure registryThe step
STEP 27Five minutes talking to it yourself, and one honest sentence back50% partly doneHis own words exist, dated, beside this plan; agents have already run the same five-minute test as him firstWaiting on Nick: five minutes talking to it in his own room, then one sentence — was he heard, and did the reply sound right. This step blocks nothing. STEP 28 is the only step that names it, and only to exclude it from its entry condition
STEP 28One proper security pass at the very end0% not startedEvery finding queued in projects/ops/sp-sec/PLAN.md carries a verdict — including the shortcut that grants Nick access before it looks him up — and each of this lane's own three surfaces carries a written verdict: the voice pipeline, the installed-app door, and the image path if it lands hereWaiting on Nick: , one tap to start, per the click gate on all security work. The paid scan is a SEPARATE money decision asked as its own plain question; a no, or no answer, leaves the by-hand review as the pass and this step still closes
STEP 29The app in your Dock stops lagging behind your phone30% partly doneNode projects/ops/skippy-jobs/_test-desktop-build-freshness.mjs and node projects/ops/skippy-jobs/_test-desktop-collapsed-state.mjs both pass, with the built app’s own version read out of the app rather than a build log and recorded in this lane’s evidence folderThe step
STEP 30Everything marked done that nobody outside the lane ever re-tested50% partly donePython3 projects/ops/agents/check_plan.py projects/ops/skippy-master-plan/PLAN-SKIPPY-FINISH-2.txt passes AND one line per re-checked step in this lane’s evidence folder saying re-proved or marked down, with the instrument used and its output — the checker command never closes this row on its ownThe step

Done

6 of 30 steps proven

Left

24 of 30 steps not yet proven

Blocked on

  • Nothing currently blocked.

Formal remaining plan

#StepNeeds Nick
1Make a spoken request actually get the thing doneNo
2It stops asking you a question at the end of every answerNo
3Five real work requests, five things actually doneNo
4It starts talking while it is still thinkingNo
5You hear the first word inside two secondsNo
6It hears Captus, Chantelle, Jasmin, Anatoly and your clientsNo
7The ten recorded test phrases all come back rightNo
8Put the work live, on the version you actually openNo
9A usable version live: three requests, first word in two seconds, all three done, names rightNo
10It installs on your phone's home screen and signing in from that icon worksNo
11Tapping a notification drops you straight into the conversation, ready to talkNo
12Start in the car, finish at the desk, without repeating yourselfNo
13Draw the Hub's new voice screens and get them signed off before anything is builtNo
14Voice inside the Hub, where you actually workYes
15A fair side-by-side against the voice assistants you already useNo
16The Mac window finished — after the phone version is live, never beforeNo
17Talking to Skippy through the Echos you already ownNo
18A current, independent verdict on how the app looksNo
19The app's final blind review, with a score that is actually currentNo
20The honest closing note: what worked, what did not, what is leftNo
21Five minutes talking to it yourself, and one honest sentence backYes
22One proper security pass at the very endYes
23The app in your Dock stops lagging behind your phoneNo
24Everything marked done that nobody outside the lane ever re-testedNo

Decisions this lane is waiting on

  1. None.