Morning QA

every card waiting on your input · single source = brain public.tasks + gates · generated 2026-07-28 10:50 UTC · preview build
The morning QA block (~1 hour, your sharpest focus). One surface, every card waiting on you. Per card, three moves:
  1. 80/20 first — should this exist at all? Kill before you polish.
  2. Dump context — voice/type a brain dump onto the card (capture context).
  3. Verdict — approve / redo / kill.
Every command below is one-click copyable — paste into your terminal / Claude. A static page can't write the brain; verdict.py does.
16
QA queue
39
Decisions
15
Your lane
0
Aging >48h

1 · QA queue

16every parked card — dump context, then rule: approve / redo / kill
Set the one big goal number for the sprint
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Akash states the number and it goes on the scoreboard as the top target.
No proof note/url attached yet.
akashWaitingneeds: Owner sets the north-star number.waiting 2hverdict: park
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context 5cf8b9e4 "…your context / what you were thinking…"
(b) Verdict — pick one
verdict 5cf8b9e4 approve
verdict 5cf8b9e4 redo "what to change"
verdict 5cf8b9e4 kill "why it should not exist"
Decide whether to switch the earlier ad round back on
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Akash decides relight or leave off, and the decision is logged with an undo path.
No proof note/url attached yet.
akashWaitingneeds: Owner relight decision.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context 772c858b "…your context / what you were thinking…"
(b) Verdict — pick one
verdict 772c858b approve
verdict 772c858b redo "what to change"
verdict 772c858b kill "why it should not exist"
Get our own ads running again - they stopped spending on Jul 21
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Ads are delivering again after Akash flips the campaign back on, confirmed by a screenshot.
No proof note/url attached yet.
akashWaitingneeds: Akash re-enables the paused campaign (spend/activation decision).waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context "own ads running" "…your context / what you were thinking…"
(b) Verdict — pick one
verdict "own ads running" approve
verdict "own ads running" redo "what to change"
verdict "own ads running" kill "why it should not exist"
Fix the Facebook lead tracking and re-send 3 client leads that got lost
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: The tracking setup is live and the 3 lost Dallas leads are re-sent, with receipts, before the window closes.
No proof note/url attached yet.
akashWaitingneeds: Akash confirms re-sending client leads (client-facing send).waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context bcdfea93 "…your context / what you were thinking…"
(b) Verdict — pick one
verdict bcdfea93 approve
verdict bcdfea93 redo "what to change"
verdict bcdfea93 kill "why it should not exist"
Submit the Facebook app review before deadline so the client bot keeps running
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: The app review is submitted before the trial deadline, confirmed by a screenshot.
No proof note/url attached yet.
akashWaitingneeds: Needs Akash's own FB browser session + passcodes (host/credential).waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context d7568fd5 "…your context / what you were thinking…"
(b) Verdict — pick one
verdict d7568fd5 approve
verdict d7568fd5 redo "what to change"
verdict d7568fd5 kill "why it should not exist"
Get the two missing pieces for Dan's setup (software key + service area)
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Dan's leads flow into his follow-up software and his service area is set on the bot.
No proof note/url attached yet.
akashWaitingneeds: Only Akash can provide the DripJobs key + confirmed ZIP list.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context "two missing" "…your context / what you were thinking…"
(b) Verdict — pick one
verdict "two missing" approve
verdict "two missing" redo "what to change"
verdict "two missing" kill "why it should not exist"
Launch the 27-ad campaign that's built and waiting
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: All 27 ads are live at the agreed budget, confirmed by an independent check, with a screenshot sent to Akash first.
No proof note/url attached yet.
akashWaitingneeds: Akash's budget + stop-loss + activation decision.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context 1e3b67a9 "…your context / what you were thinking…"
(b) Verdict — pick one
verdict 1e3b67a9 approve
verdict 1e3b67a9 redo "what to change"
verdict 1e3b67a9 kill "why it should not exist"
Turn on call recording in the CRM (needed to coach setters)
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: A test call records and can be played back.
No proof note/url attached yet.
akashWaitingneeds: GHL UI setting change - workflow-builder/UI work is Akash-only.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context ef46964c "…your context / what you were thinking…"
(b) Verdict — pick one
verdict ef46964c approve
verdict ef46964c redo "what to change"
verdict ef46964c kill "why it should not exist"
Approve turning on the follow-up sequences one at a time
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Each sequence gets Akash's okay before its auto-send is switched on.
No proof note/url attached yet.
akashWaitingneeds: Send/auto-send approval, staged.waiting 2hverdict: park
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context "approve turning" "…your context / what you were thinking…"
(b) Verdict — pick one
verdict "approve turning" approve
verdict "approve turning" redo "what to change"
verdict "approve turning" kill "why it should not exist"
Approve removing the 'I'm a real person' line from the client bots
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Akash lifts the hold and the line is removed across the bots, with a tested undo in place.
No proof note/url attached yet.
akashWaitingneeds: Live client-bot script change needs Akash sign-off.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context "approve removing" "…your context / what you were thinking…"
(b) Verdict — pick one
verdict "approve removing" approve
verdict "approve removing" redo "what to change"
verdict "approve removing" kill "why it should not exist"
Approve small fixes to the live application form so we can track where leads come from
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: The tracking fields fill in on more than 9 of every 10 new applications.
No proof note/url attached yet.
akashWaitingneeds: Editing the one live application form needs Akash's okay.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context "approve small" "…your context / what you were thinking…"
(b) Verdict — pick one
verdict "approve small" approve
verdict "approve small" redo "what to change"
verdict "approve small" kill "why it should not exist"
Approve moving the sign-up question higher on the landing page
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: At least one form question shows without scrolling on both phone and desktop, after Akash approves the preview.
No proof note/url attached yet.
akashWaitingneeds: Visual LP change needs Akash's preview approval.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context "approve moving" "…your context / what you were thinking…"
(b) Verdict — pick one
verdict "approve moving" approve
verdict "approve moving" redo "what to change"
verdict "approve moving" kill "why it should not exist"
Approve the new follow-up text sequence
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Akash approves it and okays switching auto-send on.
No proof note/url attached yet.
akashWaitingneeds: Send/auto-send approval.waiting 2hverdict: park
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context e7b1ce59 "…your context / what you were thinking…"
(b) Verdict — pick one
verdict e7b1ce59 approve
verdict e7b1ce59 redo "what to change"
verdict e7b1ce59 kill "why it should not exist"
Confirm the job value for each trade (this sets the target cost per lead)
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Each trade has a confirmed job value on record, with no made-up default.
No proof note/url attached yet.
akashWaitingneeds: Akash must confirm each trade's ticket; unknowns stay 'unknown'.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context 605b41fe "…your context / what you were thinking…"
(b) Verdict — pick one
verdict 605b41fe approve
verdict 605b41fe redo "what to change"
verdict 605b41fe kill "why it should not exist"
Launch the two more ad packs that are built and waiting
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Both packs are live after Akash's go, with tracking tags on every ad link.
No proof note/url attached yet.
akashWaitingneeds: Akash's launch approval + activation.waiting 2hverdict: keep
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context f6ffbd68 "…your context / what you were thinking…"
(b) Verdict — pick one
verdict f6ffbd68 approve
verdict f6ffbd68 redo "what to change"
verdict f6ffbd68 kill "why it should not exist"
Clear Facebook login checkpoint so IG Lead Form draft can be created (10-15 min)
80/20 first: Should this exist at all? Kill it before you polish it.
Done when: Blocker from v12 gap-close Path B. Every live Meta Graph call via connection cf9a1ed1-89fc-4d61-ae1a-70c5d8478400 (Akash Punnoose login) returns OAuth 190/459: 'log in to [www.facebook.com](<http://www.facebook.com>) and follow the instructions'. Action: log in at [facebook.com](<http://facebook.com>), clear the checkpoint; if calls still fail, reconnect at [pipeboard.co/connections](<http://pipeboard.co/connections>). Then any executor creates the v12-parity IG Lead Form as DRAFT using the exact payload in _scratch/deliverables/2026-07-06/typeform-ig-parity-edits-2026-07-06.html (section C) against page 1197436790119715 (St. Pierre ad account act_1096498922089551; EyeFly excluded). Default path: create draft, verify, then retire old Instant Form 1619080676409391 which lacks revenue+urgency questions.
No proof note/url attached yet.
agentWaitingneeds: akashwaiting 1h
No activity-trail entries yet.
(a) Dump context — voice/type your brain dump
capture context d60f78ba "…your context / what you were thinking…"
(b) Verdict — pick one
verdict d60f78ba approve
verdict d60f78ba redo "what to change"
verdict d60f78ba kill "why it should not exist"

2 · Decisions & approvals

39audit + gate items (excludes the waiting cards above) — ★ = 80/20 default
1 Lead stuck in NEEDS-REVIEW with no hand-off: Spencer Johnson (+14699955538) — lead is 1h old and still unhandled. The needs-review branch notifies nowhere; open the contact card and push the transfer.needs you
Why it's a must
  • Source gate: sp-lead-needs-review · severity critical
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
2 Lead stuck in NEEDS-REVIEW with no hand-off: Sam Etoum (+12147098019) — lead is 1.3h old and still unhandled. The needs-review branch notifies nowhere; open the contact card and push the transfer.needs you
Why it's a must
  • Source gate: sp-lead-needs-review · severity critical
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
3 Hot-lead hand-off is FAILING: Mike Yeo — 2 attempt(s) (14.1h old), error: awaiting_enrichment_no_contact_info. No working transfer to the client.needs you
Why it's a must
  • Source gate: sp-lead-transfer-failed · severity critical
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
4 Lead stuck in NEEDS-REVIEW with no hand-off: Twyler Webster — lead is 1d 11h old and still unhandled. The needs-review branch notifies nowhere; open the contact card and push the transfer.needs you
Why it's a must
  • Source gate: sp-lead-needs-review · severity critical
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
5 Lead stuck in NEEDS-REVIEW with no hand-off: John McLaughlin — lead is 3d 13h old and still unhandled. The needs-review branch notifies nowhere; open the contact card and push the transfer.needs you
Why it's a must
  • Source gate: sp-lead-needs-review · severity critical
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
6 Hot-lead hand-off is FAILING: Twyler Webster — 142 failed attempts (34.7h old), error: lead_delivery_city_unresolved. No working transfer to the client.needs you
Why it's a must
  • Source gate: sp-lead-transfer-failed · severity critical
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
7 Nightly transcript reconcile: backfilled 12 rows the message_echoes event path missed (outbound 12 / inbound 0), 0 fetch-or-store errors, across 9 active leadsreference only
Why it's a must
  • Source gate: sp_client_messages · severity warn
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
8 Daily huddle + weekly scorecard render looks dead — last ran Jul 26 10:32 UTC (26.5h ago), expected within 26h. Trigger: launchd com.stpierre.scorecard-huddlereference only
Why it's a must
  • Source gate: scorecard-huddle · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
9 Command Center board sweep + cockpit briefing looks dead — last ran Jul 22 20:06 UTC (112.9h ago), expected within 10h. Trigger: claude-scheduled-task command-center-sweepreference only
Why it's a must
  • Source gate: command-center-sweep · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
10 SP Ads live contact-sheet dashboard looks dead — last ran Jul 23 05:44 UTC (103.3h ago), expected within 26h. Trigger: launchd com.stpierre.finance-room-renderreference only
Why it's a must
  • Source gate: sp-ads-live-dashboard · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
11 The Morning Read (daily synthesized read to #notes) looks dead — last ran NEVER, expected within 80h. Trigger: claude-scheduled-task sp-morning-readreference only
Why it's a must
  • Source gate: sp-morning-read · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
12 Viktor — daily Slack report to #daily-reports looks dead — last ran NEVER, expected within 26h. Trigger: claude-scheduled-task viktor-daily-reportreference only
Why it's a must
  • Source gate: viktor-daily-report · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
13 Finance / cockpit / sales / CX HTML render chain looks dead — last ran Jul 26 10:50 UTC (26.2h ago), expected within 26h. Trigger: launchd com.stpierre.finance-room-renderreference only
Why it's a must
  • Source gate: finance-room-render · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
14 The Morning Read (daily synthesized read to #notes) looks dead — last ran NEVER, expected within 80h. Trigger: claude-scheduled-task sp-morning-readreference only
Why it's a must
  • Source gate: sp-morning-read · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
15 Command Center board sweep + cockpit briefing looks dead — last ran Jul 22 20:06 UTC (88.9h ago), expected within 10h. Trigger: claude-scheduled-task command-center-sweepreference only
Why it's a must
  • Source gate: command-center-sweep · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
16 Viktor — daily Slack report to #daily-reports looks dead — last ran NEVER, expected within 26h. Trigger: claude-scheduled-task viktor-daily-reportreference only
Why it's a must
  • Source gate: viktor-daily-report · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
17 SP Ads live contact-sheet dashboard looks dead — last ran Jul 23 05:44 UTC (79.3h ago), expected within 26h. Trigger: launchd com.stpierre.finance-room-renderreference only
Why it's a must
  • Source gate: sp-ads-live-dashboard · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
18 Command Center board sweep + cockpit briefing looks dead — last ran Jul 22 20:06 UTC (64.9h ago), expected within 10h. Trigger: claude-scheduled-task command-center-sweepreference only
Why it's a must
  • Source gate: command-center-sweep · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
19 The Morning Read (daily synthesized read to #notes) looks dead — last ran NEVER, expected within 80h. Trigger: claude-scheduled-task sp-morning-readreference only
Why it's a must
  • Source gate: sp-morning-read · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
20 SP Ads live contact-sheet dashboard looks dead — last ran Jul 23 05:44 UTC (55.3h ago), expected within 26h. Trigger: launchd com.stpierre.finance-room-renderreference only
Why it's a must
  • Source gate: sp-ads-live-dashboard · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
21 Viktor — daily Slack report to #daily-reports looks dead — last ran NEVER, expected within 26h. Trigger: claude-scheduled-task viktor-daily-reportreference only
Why it's a must
  • Source gate: viktor-daily-report · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
22 Viktor — daily Slack report to #daily-reports looks dead — last ran NEVER, expected within 26h. Trigger: claude-scheduled-task viktor-daily-reportreference only
Why it's a must
  • Source gate: viktor-daily-report · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
23 The Morning Read (daily synthesized read to #notes) looks dead — last ran NEVER, expected within 80h. Trigger: claude-scheduled-task sp-morning-readreference only
Why it's a must
  • Source gate: sp-morning-read · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
24 SP Ads live contact-sheet dashboard looks dead — last ran Jul 23 05:44 UTC (31.3h ago), expected within 26h. Trigger: launchd com.stpierre.finance-room-renderreference only
Why it's a must
  • Source gate: sp-ads-live-dashboard · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
25 Command Center board sweep + cockpit briefing looks dead — last ran Jul 22 20:06 UTC (40.9h ago), expected within 10h. Trigger: claude-scheduled-task command-center-sweepreference only
Why it's a must
  • Source gate: command-center-sweep · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
26 Viktor — daily Slack report to #daily-reports looks dead — last ran NEVER, expected within 26h. Trigger: claude-scheduled-task viktor-daily-reportreference only
Why it's a must
  • Source gate: viktor-daily-report · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
27 The Morning Read (daily synthesized read to #notes) looks dead — last ran NEVER, expected within 80h. Trigger: claude-scheduled-task sp-morning-readreference only
Why it's a must
  • Source gate: sp-morning-read · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
28 Command Center board sweep + cockpit briefing looks dead — last ran Jul 22 20:06 UTC (16.9h ago), expected within 10h. Trigger: claude-scheduled-task command-center-sweepreference only
Why it's a must
  • Source gate: command-center-sweep · severity stale
A Kill / dismiss — this gate does not need to exist right now★ my pick
  • Why: 80/20 first move: clear noise before acting
B Act on it — resolve the underlying gate
  • Why: only if it moves a real metric today
C Defer — leave unresolved, revisit next sweep
29 Postgres DSN + password printed into transcripts by brain.py --help -> A — mask the DSN in output now; rotation stays behind the existing key-rotation gate. Stops new leaks immediately; immediate rotation would break every rail overnight without a consumer inventoryreference only
Why it's a must
  • Decision-log event · info
30 Nurture workflow 6cc98165 armed with unapproved copy -> A — unpublish tomorrow AM (Block 4 item 2). Restores the approval gate; unpublish is UI-only so it stays queued to Akash, never auto-firedreference only
Why it's a must
  • Decision-log event · info
31 Slack alerting fix for 4 dead rails -> A — Akash creates Slack bot token + vaults as slack/stpierre/n8n_bot_token. Restores all 4 rails as designed; data-only fix, no redeploy; queued to Block 4 (Akash-only click)reference only
Why it's a must
  • Decision-log event · info
32 CL Dallas campaign found ACTIVE $50/day unattributed -> A — assume Akash/Sarah relit it; let it run, log retroactively, canary watches. Matches prior unattributed-flip pattern (Jul-22 audit: all flips were Akash in Ads Manager); campaign is the CL Dallas winner in the right seasonreference only
Why it's a must
  • Decision-log event · info
33 When does Meta count a lead — on hello, or when qualified? -> Qualified only. Only 1 of 4 live Lead events was ever a qualified lead; one was explicitly out-of-area. Ads are already off, so a learning lag costs nothing now.reference only
Why it's a must
  • Decision-log event · info
34 Send the loop-engine context pack to Collins? -> Hold. The standing 'nothing to Collins without explicit go' gate has not been lifted and his scope/pay are unsettled.reference only
Why it's a must
  • Decision-log event · info
35 Does Dan get a direct lead feed? -> Yes — book the call to wire it up. Akash is currently the human wire between the bot and Dan; that is the last single point of failure in the client rail.reference only
Why it's a must
  • Decision-log event · info
36 How does the needs-review pile get noticed? -> Both — keep the 2-hourly sweep AND add the real-time text step. The sweep is the working safety net; the text step is the real fix and only Akash can click it. This pile silently ate two qualified leads.reference only
Why it's a must
  • Decision-log event · info
37 Publish the rewritten video scripts to the page Akash shoots from? -> Preview, then publish. He shoots off his phone from a hosted page still serving version 1; all of Sunday's rewrite is local-only. Preview-before-deploy is the standing rule for creative.reference only
Why it's a must
  • Decision-log event · info
38 Which Meta token do we rebuild the rails on? -> A machine token that survives password changes. Second outage from the same class of personal token. The documented fix was written and never executed.reference only
Why it's a must
  • Decision-log event · info
39 How do the ads come back on (SP's own B2B account)? -> Text Sarah, confirm she's done, strip the retired 'inspections in 7 days' line, then relight. She paused deliberately after the compromised-account flag cleared; a conversation unblocks it. The retired line caused 47 of 52 recent rejections, so cleaning first avoids re-buying them.reference only
Why it's a must
  • Decision-log event · info

3 · Human-execute lane today

15your cards to run — Collins lane is read-only
Akash — your cards
Set the one big goal number for the sprint
Done when: Akash states the number and it goes on the scoreboard as the top target.
akashWaitingneeds: Owner sets the north-star number.2h old
80/20 + verdict
verdict 5cf8b9e4 kill "not worth doing"
Decide whether to switch the earlier ad round back on
Done when: Akash decides relight or leave off, and the decision is logged with an undo path.
akashWaitingneeds: Owner relight decision.2h old
80/20 + verdict
verdict 772c858b kill "not worth doing"
Get our own ads running again - they stopped spending on Jul 21
Done when: Ads are delivering again after Akash flips the campaign back on, confirmed by a screenshot.
akashWaitingneeds: Akash re-enables the paused campaign (spend/activation decision).2h old
80/20 + verdict
verdict "own ads running" kill "not worth doing"
Fix the Facebook lead tracking and re-send 3 client leads that got lost
Done when: The tracking setup is live and the 3 lost Dallas leads are re-sent, with receipts, before the window closes.
akashWaitingneeds: Akash confirms re-sending client leads (client-facing send).2h old
80/20 + verdict
verdict bcdfea93 kill "not worth doing"
Submit the Facebook app review before deadline so the client bot keeps running
Done when: The app review is submitted before the trial deadline, confirmed by a screenshot.
akashWaitingneeds: Needs Akash's own FB browser session + passcodes (host/credential).2h old
80/20 + verdict
verdict d7568fd5 kill "not worth doing"
Get the two missing pieces for Dan's setup (software key + service area)
Done when: Dan's leads flow into his follow-up software and his service area is set on the bot.
akashWaitingneeds: Only Akash can provide the DripJobs key + confirmed ZIP list.2h old
80/20 + verdict
verdict "two missing" kill "not worth doing"
Launch the 27-ad campaign that's built and waiting
Done when: All 27 ads are live at the agreed budget, confirmed by an independent check, with a screenshot sent to Akash first.
akashWaitingneeds: Akash's budget + stop-loss + activation decision.2h old
80/20 + verdict
verdict 1e3b67a9 kill "not worth doing"
Turn on call recording in the CRM (needed to coach setters)
Done when: A test call records and can be played back.
akashWaitingneeds: GHL UI setting change - workflow-builder/UI work is Akash-only.2h old
80/20 + verdict
verdict ef46964c kill "not worth doing"
Approve turning on the follow-up sequences one at a time
Done when: Each sequence gets Akash's okay before its auto-send is switched on.
akashWaitingneeds: Send/auto-send approval, staged.2h old
80/20 + verdict
verdict "approve turning" kill "not worth doing"
Approve removing the 'I'm a real person' line from the client bots
Done when: Akash lifts the hold and the line is removed across the bots, with a tested undo in place.
akashWaitingneeds: Live client-bot script change needs Akash sign-off.2h old
80/20 + verdict
verdict "approve removing" kill "not worth doing"
Approve small fixes to the live application form so we can track where leads come from
Done when: The tracking fields fill in on more than 9 of every 10 new applications.
akashWaitingneeds: Editing the one live application form needs Akash's okay.2h old
80/20 + verdict
verdict "approve small" kill "not worth doing"
Approve moving the sign-up question higher on the landing page
Done when: At least one form question shows without scrolling on both phone and desktop, after Akash approves the preview.
akashWaitingneeds: Visual LP change needs Akash's preview approval.2h old
80/20 + verdict
verdict "approve moving" kill "not worth doing"
Approve the new follow-up text sequence
Done when: Akash approves it and okays switching auto-send on.
akashWaitingneeds: Send/auto-send approval.2h old
80/20 + verdict
verdict e7b1ce59 kill "not worth doing"
Confirm the job value for each trade (this sets the target cost per lead)
Done when: Each trade has a confirmed job value on record, with no made-up default.
akashWaitingneeds: Akash must confirm each trade's ticket; unknowns stay 'unknown'.2h old
80/20 + verdict
verdict 605b41fe kill "not worth doing"
Launch the two more ad packs that are built and waiting
Done when: Both packs are live after Akash's go, with tracking tags on every ad link.
akashWaitingneeds: Akash's launch approval + activation.2h old
80/20 + verdict
verdict f6ffbd68 kill "not worth doing"
Collins lane — read-only (4)

Whole-system builds scoped to Collins. Nothing sent to Collins without an explicit go — shown here for visibility only.

Map out today's client-setup steps (what's built vs missing)
Done when: A map lists every setup step marked done or missing.
collinsNext2h old
Turn Dan's setup into a reusable checklist for the next client
Done when: A checklist covers page, local ad, account ownership, lead routing, customer list, and measurement.
collinsNext2h old
Design the system that tracks and coaches setters
Done when: A written plan defines what to track per setter and how the daily brief works.
collinsNext2h old
Build the daily coaching brief for each setter
Done when: A sample daily brief is produced per setter from real call data.
collinsNext2h old

4 · Aging

0waiting >48h — flagged, never auto-actioned

— nothing aging past 48h — clean —

Server-rendered from public.tasks (flow_status=waiting), brain.ops_alerts, public.taskos_events. Re-render: render_morning_qa.py in 01-Projects/St_Pierre_Digital/morning-qa/. Card idiom reused from the daily-shutdown card engine (system_files/recommendation_card.py). Preview only — no live route touched.