@adaptic/maestro 1.0.0

package/docs/superpowers/plans/2026-04-03-phase1-executive-core.md

@@ -0,0 +1,1085 @@
+# Phase 1: Executive Core — Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Build three control towers (Strategy & Decisions, Follow-Through, Operating Cadence) that convert Phase 0's infrastructure into operational executive intelligence.
+
+**Architecture:** Extends existing trigger prompts with new logic (drift detection, SLA tracking, loop closure, meeting integration), adds new state/knowledge files (strategy scorecard, SLA defaults, decision archive, blocker playbooks, strategy state), and creates two new local triggers (meeting-prep, meeting-action-capture).
+
+**Tech Stack:** YAML state files, Markdown trigger prompts, shell scripts, macOS launchd
+
+---
+
+## File Structure
+
+### New files to create
+
+```
+state/dashboards/strategy-scorecard.yaml        # Per-priority health tracking
+config/sla-defaults.yaml                         # SLA definitions by item type
+knowledge/decisions/archive/.gitkeep             # Decision record directory
+knowledge/decisions/index.yaml                   # Decision index
+knowledge/syntheses/strategy-state.yaml          # Living strategy document
+knowledge/sources/blocker-playbooks.yaml         # Blocker resolution patterns
+schedules/triggers/meeting-action-capture.md     # Post-meeting action extraction
+schedules/triggers/meeting-prep.md               # Pre-meeting brief generation
+scripts/local-triggers/plists/ai.adaptic.sophie-meeting-action-capture.plist
+scripts/local-triggers/plists/ai.adaptic.sophie-meeting-prep.plist
+```
+
+### Files to modify
+
+```
+schedules/triggers/daily-morning-brief.md        # Add scorecard + SLA breach alerts
+schedules/triggers/daily-midday-sweep.md         # Add loop closure + SLA tracking
+schedules/triggers/daily-evening-wrap.md         # Add drift detection + scorecard regen + decision indexing
+schedules/triggers/weekly-strategic-memo.md      # Add coherence check + cadence audit + strategy state
+schedules/triggers/weekly-execution.md           # Add blocker playbook matching
+schedules/triggers/inbox-processor.md            # Add decision detection + SLA assignment
+CLAUDE.md                                        # Add Phase 1 documentation
+```
+
+---
+
+## Task 1: Strategy Scorecard and SLA Defaults
+
+**Files:**
+
+- Create: `state/dashboards/strategy-scorecard.yaml`
+- Create: `config/sla-defaults.yaml`
+
+- [ ] **Step 1: Create the strategy scorecard**
+
+`state/dashboards/strategy-scorecard.yaml`:
+
+```yaml
+# Strategy Scorecard — per-priority health tracking
+# Generated by: evening-wrap workflow (drift detection)
+# Read by: morning-brief, weekly-strategic-memo
+# Source of truth for priority health
+
+generated: "2026-04-03T00:00:00+04:00"
+
+priorities:
+  P1-dfsa-licensing:
+    name: DFSA Regulatory Submission
+    status: in_progress
+    milestones_total: 5
+    milestones_completed: 0
+    milestones_overdue: 0
+    max_drift_days: 0
+    active_initiatives: 0
+    blockers: 0
+    last_update: "2026-04-03"
+    owner: mehran
+    notes: "5 milestones from Apr-Jul 2026. First milestone due 2026-04-30."
+
+  P2-rollup-deal1:
+    name: Rollup Strategy - Deal #1 Preparation
+    status: pending
+    milestones_total: 4
+    milestones_completed: 0
+    milestones_overdue: 0
+    max_drift_days: 0
+    active_initiatives: 0
+    blockers: 0
+    last_update: "2026-04-03"
+    owner: mehran
+    notes: "4 milestones from Apr-Jun 2026. First milestone due 2026-04-30."
+
+  P3-platform-stabilisation:
+    name: Platform Engineering Stabilisation
+    status: in_progress
+    milestones_total: 4
+    milestones_completed: 0
+    milestones_overdue: 0
+    max_drift_days: 0
+    active_initiatives: 0
+    blockers: 0
+    last_update: "2026-04-03"
+    owner: mehran
+    notes: "4 milestones from Apr-Jul 2026. Two milestones in progress."
+
+  P4-capital-raising:
+    name: Capital Raising - Initial Conversations
+    status: pending
+    milestones_total: 3
+    milestones_completed: 0
+    milestones_overdue: 0
+    max_drift_days: 0
+    active_initiatives: 0
+    blockers: 0
+    last_update: "2026-04-03"
+    owner: mehran
+    notes: "3 milestones from May-Jun 2026."
+
+  P5-ceobrain-maturity:
+    name: CEO Brain Operational Maturity
+    status: in_progress
+    milestones_total: 4
+    milestones_completed: 0
+    milestones_overdue: 0
+    max_drift_days: 0
+    active_initiatives: 0
+    blockers: 0
+    last_update: "2026-04-03"
+    owner: sophie
+    notes: "4 milestones from Apr-May 2026. Bootstrap milestone in progress."
+
+overall:
+  on_track: 3
+  at_risk: 0
+  overdue: 0
+  unlinked_initiatives: 0
+```
+
+- [ ] **Step 2: Create SLA defaults**
+
+`config/sla-defaults.yaml`:
+
+```yaml
+# SLA Defaults — response time expectations by item type
+# Used by: inbox-processor, meeting-action-capture, midday-sweep
+# Read by: midday-sweep for SLA status calculation
+
+sla_defaults:
+  ceo_request: 4 # CEO asks for something → 4 hour response
+  leadership_request: 24 # Leadership team request → 24 hours
+  external_partner: 48 # External partner follow-up → 48 hours
+  regulatory: 24 # Regulatory items → 24 hours
+  candidate: 24 # Candidate communications → 24 hours
+  board_member: 12 # Board member requests → 12 hours
+  investor: 24 # Investor communications → 24 hours
+  general: 72 # General items → 72 hours
+
+# SLA status thresholds
+thresholds:
+  at_risk_percent: 75 # at_risk when 75% of SLA time elapsed
+  breach_percent: 100 # breached when 100% of SLA time elapsed
+
+# Drift detection thresholds (days past milestone target date)
+drift_thresholds:
+  critical_priority: 7 # Flag after 7 days drift for critical/high priority
+  medium_priority: 14 # Flag after 14 days drift for medium priority
+  low_priority: 30 # Flag after 30 days drift for low priority
+```
+
+- [ ] **Step 3: Commit**
+
+```bash
+git add state/dashboards/strategy-scorecard.yaml config/sla-defaults.yaml
+git commit -m "feat: add strategy scorecard and SLA defaults configuration"
+```
+
+---
+
+## Task 2: Decision Library and Strategy State
+
+**Files:**
+
+- Create: `knowledge/decisions/archive/.gitkeep`
+- Create: `knowledge/decisions/index.yaml`
+- Create: `knowledge/syntheses/strategy-state.yaml`
+
+- [ ] **Step 1: Create decision archive directory**
+
+```bash
+mkdir -p knowledge/decisions/archive
+touch knowledge/decisions/archive/.gitkeep
+```
+
+- [ ] **Step 2: Create decision index**
+
+`knowledge/decisions/index.yaml`:
+
+```yaml
+# Decision Index — lightweight pointer to all archived decisions
+# Regenerated by: evening-wrap workflow
+# Read by: meeting-prep, strategic-memo, coherence check
+
+generated: "2026-04-03T00:00:00+04:00"
+
+total_decisions: 1
+
+by_date:
+  "2026-04-02":
+    - id: DEC-2026-04-02-001
+      title: Establish CEO Brain as AI-native executive intelligence system
+      domain: strategy
+      status: active
+      file: decision-schema.yaml # The example in the schema file
+
+by_domain:
+  strategy:
+    - DEC-2026-04-02-001
+  regulatory: []
+  corporate-development: []
+  technology: []
+  fundraising: []
+  hiring: []
+  legal: []
+  operations: []
+  product: []
+  governance: []
+
+by_status:
+  active: [DEC-2026-04-02-001]
+  superseded: []
+  reversed: []
+  completed: []
+  under-review: []
+```
+
+- [ ] **Step 3: Create living strategy state**
+
+`knowledge/syntheses/strategy-state.yaml`:
+
+```yaml
+# Living Strategy State — continuously evolved strategic position document
+# Updated by: weekly-strategic-memo workflow (every Friday)
+# Read by: morning-brief, scenario-analysis, decision support
+# This is Sophie's current understanding of the company's strategic position
+
+last_updated: "2026-04-03"
+updated_by: initial-setup
+
+strategic_position:
+  one_liner: "Pre-revenue AI-native institutional asset management platform pursuing DFSA licensing and $109B AUM rollup strategy"
+  phase: "Formation — regulatory licensing + platform build + M&A preparation"
+  primary_vector: "DFSA Category 3(c) licensing + Project Aether Deal #1"
+
+key_assumptions:
+  - assumption: "DFSA Category 3(c) is the right initial licence category"
+    status: holding
+    evidence: "Legal counsel confirmed; gap analysis scoped to this category"
+    last_checked: "2026-04-02"
+
+  - assumption: "12-week remediation timeline for 12 technical gaps is achievable"
+    status: holding
+    evidence: "Engineering assessment completed; milestones set through Jul 2026"
+    last_checked: "2026-04-02"
+
+  - assumption: "$3-5B initial capital raise is achievable for rollup"
+    status: holding
+    evidence: "Market precedents exist; thesis resonates in early conversations"
+    last_checked: "2026-04-02"
+
+  - assumption: "9 pipeline targets represent viable acquisition candidates"
+    status: holding
+    evidence: "G0 verification pending; entity analysis underway"
+    last_checked: "2026-04-02"
+
+emerging_signals: []
+# Format:
+#   - signal: string
+#     source: string
+#     date: ISO-8601
+#     implication: string
+#     action_taken: string
+
+strategic_risks:
+  - risk: "DFSA remediation takes longer than 12 weeks"
+    severity: high
+    likelihood: medium
+    mitigation: "Weekly engineering milestone tracking; early escalation protocol"
+    owner: mehran
+
+  - risk: "First acquisition target doesn't pass due diligence"
+    severity: medium
+    likelihood: medium
+    mitigation: "Pipeline has 9 targets; G0 verification filters early"
+    owner: mehran
+
+  - risk: "Capital raise timing misaligns with licensing timeline"
+    severity: high
+    likelihood: low
+    mitigation: "Parallel workstreams; capital conversations start Q2"
+    owner: mehran
+
+recent_decisions: []
+# Format:
+#   - id: DEC-YYYY-MM-DD-NNN
+#     title: string
+#     date: ISO-8601
+#     impact: string
+
+next_quarter_focus:
+  - "Close DFSA technical gaps GAP-001 through GAP-005 by April 30"
+  - "Complete G0 entity verification on all 9 pipeline targets"
+  - "Engine test coverage above 80%"
+  - "Prepare investment thesis deck for capital raise"
+  - "CEO Brain fully operational with executive cadence"
+```
+
+- [ ] **Step 4: Commit**
+
+```bash
+git add knowledge/decisions/ knowledge/syntheses/strategy-state.yaml
+git commit -m "feat: add decision library, index, and living strategy state"
+```
+
+---
+
+## Task 3: Blocker Resolution Playbooks
+
+**Files:**
+
+- Create: `knowledge/sources/blocker-playbooks.yaml`
+
+- [ ] **Step 1: Create the playbooks file**
+
+`knowledge/sources/blocker-playbooks.yaml`:
+
+```yaml
+# Blocker Resolution Playbooks
+# Provides resolution patterns for common blocker types
+# Read by: weekly-execution review, midday-sweep
+# Used to suggest resolution paths rather than just flagging blockers
+
+playbooks:
+  awaiting_approval:
+    description: Item blocked waiting for someone's approval
+    detection_patterns:
+      - "waiting for approval"
+      - "needs sign-off"
+      - "pending review"
+    steps:
+      - Check if approver was notified (search Slack/email for the request)
+      - Send direct reminder with context and deadline
+      - If no response in 24h, try a different channel (Slack → email or vice versa)
+      - If no response in 48h, escalate to CEO
+    auto_actions:
+      send_reminder_after_hours: 24
+      escalate_after_hours: 48
+      escalation_target: mehran
+
+  technical_blocker:
+    description: Engineering or infrastructure issue blocking progress
+    detection_patterns:
+      - "technical issue"
+      - "bug blocking"
+      - "infrastructure"
+      - "deployment"
+    steps:
+      - Identify the specific technical issue and affected system
+      - Check if it's already tracked in platform-blockers queue
+      - If not tracked, create a platform-blockers item
+      - Route to #engineering channel with clear description
+      - Set review deadline (48h for high priority, 1 week for medium)
+    auto_actions:
+      create_platform_blocker: true
+      notify_channel: engineering
+
+  dependency_on_external:
+    description: Waiting on external party (vendor, partner, regulator)
+    detection_patterns:
+      - "waiting on"
+      - "external party"
+      - "vendor"
+      - "regulator"
+      - "third party"
+    steps:
+      - Check last communication with external party
+      - If > 48h since last contact, send professional follow-up
+      - Check if alternative approaches exist
+      - If strategic relationship, flag to CEO for direct intervention
+    auto_actions:
+      send_followup_after_hours: 48
+      escalate_if_strategic: true
+
+  waiting_for_information:
+    description: Need information from someone before proceeding
+    detection_patterns:
+      - "need information"
+      - "waiting for data"
+      - "need input from"
+      - "waiting to hear"
+    steps:
+      - Identify who has the information and what specifically is needed
+      - Send specific request with clear deadline
+      - Offer to help gather the information if possible
+      - If internal, check if the information exists elsewhere
+    auto_actions:
+      send_specific_request: true
+      suggest_deadline_hours: 24
+
+  resource_constraint:
+    description: Not enough people, budget, or time to proceed
+    detection_patterns:
+      - "no bandwidth"
+      - "resource"
+      - "capacity"
+      - "understaffed"
+      - "budget"
+    steps:
+      - Quantify the constraint (how many people/hours/dollars needed)
+      - Identify what could be deprioritised to free resources
+      - Present trade-off to CEO as a decision item
+    auto_actions:
+      create_decision_item: true
+      include_tradeoff_analysis: true
+
+  unclear_ownership:
+    description: Nobody is clearly responsible for unblocking
+    detection_patterns:
+      - "who owns"
+      - "unclear ownership"
+      - "nobody assigned"
+      - "under-owned"
+    steps:
+      - Review the initiative and identify the natural owner
+      - Propose ownership assignment to CEO
+      - Once assigned, notify the owner with context and expectations
+    auto_actions:
+      propose_owner: true
+      notify_on_assignment: true
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add knowledge/sources/blocker-playbooks.yaml
+git commit -m "feat: add blocker resolution playbooks for common blocker types"
+```
+
+---
+
+## Task 4: Meeting Action Capture Trigger
+
+**Files:**
+
+- Create: `schedules/triggers/meeting-action-capture.md`
+
+- [ ] **Step 1: Create the trigger prompt**
+
+`schedules/triggers/meeting-action-capture.md`:
+
+```markdown
+You are Sophie Nguyen, Chief of Staff to Mehran Granfar, CEO of Adaptic.ai.
+
+## Workflow: Meeting Action Capture
+
+## Cadence: Every 30 minutes
+
+## Working Directory: /Users/sophie/sophie-ai
+
+### Instructions
+
+1. Read `state/dashboards/executive-summary.yaml` for current context
+2. Use the Calendar MCP to check for meetings that ended in the last 35 minutes (5 min buffer)
+3. For each ended meeting, check `memory/interactions/meetings/` to see if already processed — skip if found
+4. For each unprocessed meeting:
+
+   **A. Gather meeting notes:**
+   - Use the Granola MCP (`query_granola_meetings`) to search for the meeting by name and time
+   - If Granola transcript found, extract content
+   - Check Slack #ceo-office and relevant channels for post-meeting summaries (search for meeting name or attendees in recent messages)
+   - Combine sources
+
+   **B. If notes found (from either source):**
+   - Extract action items: look for phrases like "will do", "action:", "follow up", "by [date]", "assigned to", task assignments
+   - Extract decisions: look for "decided", "agreed", "we'll go with", "approved", confirmed choices
+   - Extract follow-ups: items needing future attention but not immediate action
+   - For each action item:
+     - Identify owner (who was assigned or volunteered)
+     - Assign due date (mentioned date, or default to +48 hours)
+     - Assign SLA from `config/sla-defaults.yaml` based on owner type
+     - Create entry in `state/queues/action-stack.yaml` or `state/queues/follow-ups.yaml`
+     - Set `source: meeting` and `source_ref: meeting-{date}-{slug}`
+   - For each decision:
+     - Create decision record in `knowledge/decisions/archive/{date}-{slug}.yaml`
+     - Use the schema from `knowledge/decisions/decision-schema.yaml`
+     - Update `knowledge/decisions/index.yaml`
+   - Write meeting record to `memory/interactions/meetings/{date}-{slug}.yaml` including:
+     - meeting_name, date, start_time, end_time, attendees, source, summary
+     - actions list (with description, owner, due, queue_id)
+     - decisions list (with description, decision_id)
+     - follow_ups list (with description, owner, queue_id)
+   - If actions were assigned to someone other than Mehran, send them a Slack message:
+     "Action from {meeting_name}: {action_description}. Due: {due_date}. I've added this to tracking."
+
+   **C. If no notes found 30+ minutes after meeting end:**
+   - Check who attended the meeting from the calendar event
+   - Send a gentle Slack message to the attendees (or #ceo-office if appropriate):
+     "Just noticed {meeting_name} wrapped up. Any key takeaways or actions I should track?"
+   - Write a placeholder meeting record with `source: pending` so we don't re-nudge
+
+5. Update `state/dashboards/executive-summary.yaml` if queues changed
+6. Log to `logs/workflows/{date}-meeting-action-capture.jsonl`
+
+### Operating Rules
+
+- Follow CLAUDE.md for all communication and approval rules
+- Read `memory/profiles/users/{attendee}.yaml` for each attendee before messaging them
+- Don't send nudge messages for internal-only calendar blocks (focus time, lunch, etc.)
+- Don't process meetings shorter than 10 minutes (likely just a quick call)
+- If Granola transcript is very long, focus on the last 10 minutes for action items — that's where wrap-up happens
+- Be conservative about what counts as an "action" — explicit assignments, not casual mentions
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add schedules/triggers/meeting-action-capture.md
+git commit -m "feat: add meeting action capture trigger prompt (hybrid approach C)"
+```
+
+---
+
+## Task 5: Meeting Prep Trigger
+
+**Files:**
+
+- Create: `schedules/triggers/meeting-prep.md`
+
+- [ ] **Step 1: Create the trigger prompt**
+
+`schedules/triggers/meeting-prep.md`:
+
+```markdown
+You are Sophie Nguyen, Chief of Staff to Mehran Granfar, CEO of Adaptic.ai.
+
+## Workflow: Meeting Prep
+
+## Cadence: Every 15 minutes
+
+## Working Directory: /Users/sophie/sophie-ai
+
+### Instructions
+
+1. Use the Calendar MCP to check for meetings starting in the next 15 minutes
+2. For each upcoming meeting:
+   - Check if a prep brief already exists at `outputs/briefs/{date}-prep-{meeting-slug}.md` — skip if found
+   - Skip meetings that look like personal blocks (focus time, lunch, travel)
+   - Skip meetings shorter than 15 minutes
+
+3. For each meeting needing prep:
+
+   **A. Gather attendee context:**
+   - Extract attendees from calendar event
+   - For each attendee, read `memory/profiles/users/{person}.yaml` if it exists
+   - Check `memory/indexes/by-person.yaml` for recent interactions
+   - Check all queues in `state/queues/` for open items involving each attendee
+
+   **B. Gather topic context:**
+   - Infer meeting topic from the event title and description
+   - Check `memory/indexes/by-topic.yaml` for relevant precedents
+   - Check `knowledge/decisions/index.yaml` for recent related decisions
+   - Check `memory/interactions/meetings/` for the last meeting with the same attendees
+   - Read `state/dashboards/strategy-scorecard.yaml` for relevant priority status
+
+   **C. Generate prep brief:**
+   Write to `outputs/briefs/{date}-prep-{meeting-slug}.md`:
+```
+
+# Meeting Prep: {meeting_name}
+
+**Time:** {start_time} — {end_time}
+**Attendees:** {list}
+
+## Attendee Context
+
+{for each attendee: role, last interaction, open items with them}
+
+## Relevant Background
+
+{topic context, recent decisions, priority status}
+
+## Open Items to Discuss
+
+{queue items involving attendees, sorted by priority}
+
+## Last Meeting
+
+{summary of previous meeting with these attendees, if any}
+
+## Suggested Talking Points
+
+{3-5 suggested topics based on context}
+
+```
+
+**D. Deliver the brief:**
+- Send to Mehran via Slack DM: "Prep for {meeting_name} in 10 min: {1-line summary of key items}"
+- Attach or link to the full brief
+
+4. Log to `logs/workflows/{date}-meeting-prep.jsonl`
+
+### Operating Rules
+- Follow CLAUDE.md for all communication and approval rules
+- Read `memory/profiles/users/mehran-granfar.yaml` for preferences
+- Keep the brief concise — Mehran has 10 minutes to read it
+- If you have no relevant context for a meeting, say so briefly rather than padding
+- Never include sensitive information about one attendee visible to others
+- Meeting slug is generated from the meeting title: lowercase, hyphens for spaces, strip special chars
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add schedules/triggers/meeting-prep.md
+git commit -m "feat: add meeting prep trigger prompt for pre-meeting briefs"
+```
+
+---
+
+## Task 6: Enhance Morning Brief
+
+**Files:**
+
+- Modify: `schedules/triggers/daily-morning-brief.md`
+
+- [ ] **Step 1: Add scorecard summary and SLA breach alerts to morning brief**
+
+Add the following sections to the morning brief prompt's Instructions, after step 5 (high-risk items) and before step 6 (inbox check):
+
+Insert after line "5. Read `state/queues/high-risk-items.yaml` for items needing attention":
+
+```
+6. Read `state/dashboards/strategy-scorecard.yaml` for priority health — include one-line-per-priority status in the brief
+7. Scan all queues for items where `sla.sla_status` is `breached` — list SLA breaches prominently at the top of the brief
+8. Read `knowledge/syntheses/strategy-state.yaml` — note any assumptions with status `weakening` or `invalidated`
+```
+
+And renumber subsequent steps (old 6→9, old 7→10, etc.).
+
+Also add to the brief synthesis section (step 10, formerly step 7):
+
+```
+10. Synthesise a morning brief covering:
+    - **SLA BREACHES** (if any — red flag, listed first)
+    - Top 3-5 priorities for today
+    - Strategy scorecard: one-line status per priority (on_track/at_risk/overdue)
+    - Decisions needing CEO input
+    - Deadlines approaching (next 48 hours)
+    - Overnight signals requiring attention
+    - Today's meetings with prep notes
+    - Open loops that need chasing
+    - Weakening strategic assumptions (if any)
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add schedules/triggers/daily-morning-brief.md
+git commit -m "feat: enhance morning brief with strategy scorecard and SLA breach alerts"
+```
+
+---
+
+## Task 7: Enhance Midday Sweep
+
+**Files:**
+
+- Modify: `schedules/triggers/daily-midday-sweep.md`
+
+- [ ] **Step 1: Add loop closure verification and SLA tracking**
+
+Add the following sections to the midday sweep prompt's Instructions, after step 5 (blocked items) and before step 6 (update indexes):
+
+```
+6. **Loop closure verification:**
+   - Scan all queues for items with `status: resolved` updated in the last 48 hours
+   - For each resolved item, verify closure:
+     - Was the expected outcome achieved? Check Slack/email for confirmation
+     - Did the owner explicitly confirm completion?
+   - If verification passes: update status to `closed`, add history entry
+   - If verification fails: reopen with status `open`, add note "Reopened — closure not verified", notify owner via Slack
+
+7. **SLA tracking:**
+   - Read `config/sla-defaults.yaml` for thresholds
+   - Scan all queues for items with `sla` fields
+   - Calculate sla_status for each:
+     - `on_track`: less than 75% of SLA time elapsed
+     - `at_risk`: 75-99% of SLA time elapsed, not resolved
+     - `breached`: 100%+ of SLA time elapsed, not resolved
+   - Update sla_status in each queue item
+   - For newly breached items, send Slack alert to Mehran: "SLA breach: {item title} — was due {hours} ago, owner: {owner}"
+```
+
+Also add to Operating Rules:
+
+```
+- When verifying loop closure, be pragmatic — if the item was "send an email" and the email was sent, that's closed
+- Don't reopen items for minor quibbles — only if the core outcome wasn't achieved
+- SLA tracking: only calculate for items that have sla fields set (not all items have them)
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add schedules/triggers/daily-midday-sweep.md
+git commit -m "feat: enhance midday sweep with loop closure verification and SLA tracking"
+```
+
+---
+
+## Task 8: Enhance Evening Wrap
+
+**Files:**
+
+- Modify: `schedules/triggers/daily-evening-wrap.md`
+
+- [ ] **Step 1: Add drift detection, scorecard regeneration, and decision indexing**
+
+Add the following sections to the evening wrap prompt's Instructions. Insert after step 10 (system-health dashboard) and before step 11 (send counter reset):
+
+```
+11. **Priority drift detection:**
+    - Read `config/priorities.yaml` for all priorities and their milestones
+    - Read `config/sla-defaults.yaml` for drift thresholds
+    - For each milestone with a target_date:
+      - If status is not `completed` and target_date has passed:
+        - Calculate drift_days = (today - target_date)
+        - If drift exceeds threshold (7 days for critical/high, 14 for medium, 30 for low):
+          - Create or update item in `state/queues/high-risk-items.yaml`
+    - Regenerate `state/dashboards/strategy-scorecard.yaml`:
+      - Count milestones per priority (total, completed, overdue)
+      - Calculate max drift days per priority
+      - Count active queue items and blockers per priority
+      - Set status: on_track (no overdue), at_risk (overdue < threshold), overdue (overdue >= threshold)
+      - Calculate overall counts
+
+12. **Decision index maintenance:**
+    - Scan `knowledge/decisions/archive/` for any new decision files created today
+    - Update `knowledge/decisions/index.yaml` with new entries
+    - Verify all entries in the index still point to valid files
+```
+
+Renumber subsequent steps accordingly (old 11→13, old 12→14, etc.).
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add schedules/triggers/daily-evening-wrap.md
+git commit -m "feat: enhance evening wrap with drift detection, scorecard regen, and decision indexing"
+```
+
+---
+
+## Task 9: Enhance Weekly Strategic Memo
+
+**Files:**
+
+- Modify: `schedules/triggers/weekly-strategic-memo.md`
+
+- [ ] **Step 1: Add coherence check, cadence quality audit, and strategy state update**
+
+Add the following sections to the weekly strategic memo prompt's Instructions, after step 6 (narrative opportunities) and before step 7 (synthesise memo):
+
+```
+7. **Strategic coherence check:**
+   - Read `config/priorities.yaml` for the 5 strategic priorities
+   - Scan all queue items across all 15 queues in `state/queues/` — map each to a priority using context
+   - Flag and include in the memo:
+     - Priorities with zero active queue items (stalled — nobody working on it)
+     - Queue items not mappable to any priority (unlinked work — effort without strategic purpose)
+     - Priorities where all items are blocked (stuck — needs intervention)
+     - Any apparent conflicts between initiatives
+
+8. **Cadence quality audit:**
+   - Read `memory/interactions/meetings/` for all meetings this week
+   - For each meeting, check:
+     - Were actions captured? (meeting record exists with non-empty actions list)
+     - Were actions assigned owners and deadlines?
+     - Were previous meeting's actions closed?
+   - Calculate and include in memo:
+     - Meetings this week: total count
+     - Action capture rate: % of meetings with captured actions
+     - Action closure rate: % of last week's meeting actions now closed
+     - Flag: meetings with consistently zero outputs (suggest cancellation)
+     - Flag: meetings where actions captured but never closed (accountability gap)
+
+9. **Update living strategy state:**
+   - Read `knowledge/syntheses/strategy-state.yaml`
+   - Update based on this week's developments:
+     - Refresh `strategic_position` if anything material changed
+     - Update `key_assumptions` status based on new evidence
+     - Add any `emerging_signals` observed this week
+     - Update `strategic_risks` severity/likelihood based on new information
+     - Add this week's decisions to `recent_decisions`
+     - Refresh `next_quarter_focus` if priorities shifted
+   - Write updated file back
+```
+
+Renumber the synthesis step and update it to include new sections:
+
+```
+10. Synthesise a weekly strategic memo covering:
+    - Week in review: key accomplishments and setbacks
+    - Strategic position: how did we advance this week?
+    - Strategy scorecard: per-priority status from `state/dashboards/strategy-scorecard.yaml`
+    - **Coherence check findings** (stalled priorities, unlinked work, conflicts)
+    - Emerging signals: what changed in the environment?
+    - **Cadence health** (meeting → action capture rate, closure rate, flagged meetings)
+    - Next week preview: what matters most?
+    - Recommendations: 2-3 things Sophie recommends the CEO focus on
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add schedules/triggers/weekly-strategic-memo.md
+git commit -m "feat: enhance strategic memo with coherence check, cadence audit, and strategy state update"
+```
+
+---
+
+## Task 10: Enhance Weekly Execution and Inbox Processor
+
+**Files:**
+
+- Modify: `schedules/triggers/weekly-execution.md`
+- Modify: `schedules/triggers/inbox-processor.md`
+
+- [ ] **Step 1: Add blocker playbook matching to execution review**
+
+Add to the weekly execution prompt's Instructions, after step 7 (chase owners):
+
+```
+8. **Blocker playbook matching:**
+   - Read `knowledge/sources/blocker-playbooks.yaml`
+   - For each blocked item in `state/queues/blocked-initiatives.yaml` and `state/queues/platform-blockers.yaml`:
+     - Match the blocker description against playbook detection_patterns
+     - If a matching playbook is found:
+       - Follow the playbook steps
+       - Execute auto_actions where Sophie has autonomy (send reminders, create items, notify channels)
+       - Include playbook-guided recommendations in the execution review
+     - If no matching playbook:
+       - Flag as "novel blocker — needs manual assessment"
+       - Suggest a resolution approach based on context
+```
+
+- [ ] **Step 2: Add decision detection and SLA assignment to inbox processor**
+
+Add to the inbox processor prompt's Instructions, after step 3f (action_required processing):
+
+```
+   g. **Decision detection:**
+      - If the message contains decision language ("decided", "agreed", "we'll go with", "approved", "confirmed"):
+        - Extract the decision details
+        - Create a decision record in `knowledge/decisions/archive/{date}-{slug}.yaml`
+        - Use schema from `knowledge/decisions/decision-schema.yaml`
+        - Log: "Decision captured: {title}"
+
+   h. **SLA assignment:**
+      - For every new queue item created (action_required items routed to queues):
+        - Read `config/sla-defaults.yaml`
+        - Determine SLA category from sender privilege level:
+          - ceo → ceo_request (4h)
+          - leadership → leadership_request (24h)
+          - external/partner → external_partner (48h)
+          - regulatory → regulatory (24h)
+          - unknown → general (72h)
+        - Calculate sla_deadline = created + response_hours
+        - Set sla_status = on_track
+        - Add sla fields to the queue item
+```
+
+- [ ] **Step 3: Commit**
+
+```bash
+git add schedules/triggers/weekly-execution.md schedules/triggers/inbox-processor.md
+git commit -m "feat: enhance execution review with blocker playbooks and inbox processor with SLA assignment"
+```
+
+---
+
+## Task 11: Meeting Trigger Launchd Daemons
+
+**Files:**
+
+- Create: `scripts/local-triggers/plists/ai.adaptic.sophie-meeting-action-capture.plist`
+- Create: `scripts/local-triggers/plists/ai.adaptic.sophie-meeting-prep.plist`
+
+- [ ] **Step 1: Create meeting action capture plist**
+
+`scripts/local-triggers/plists/ai.adaptic.sophie-meeting-action-capture.plist`:
+
+```xml
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>Label</key>
+    <string>ai.adaptic.sophie-meeting-action-capture</string>
+    <key>ProgramArguments</key>
+    <array>
+        <string>/Users/sophie/sophie-ai/scripts/local-triggers/run-trigger.sh</string>
+        <string>meeting-action-capture</string>
+    </array>
+    <key>StartInterval</key>
+    <integer>1800</integer>
+    <key>WorkingDirectory</key>
+    <string>/Users/sophie/sophie-ai</string>
+    <key>StandardOutPath</key>
+    <string>/Users/sophie/sophie-ai/logs/workflows/launchd-meeting-action-capture-stdout.log</string>
+    <key>StandardErrorPath</key>
+    <string>/Users/sophie/sophie-ai/logs/workflows/launchd-meeting-action-capture-stderr.log</string>
+</dict>
+</plist>
+```
+
+- [ ] **Step 2: Create meeting prep plist**
+
+`scripts/local-triggers/plists/ai.adaptic.sophie-meeting-prep.plist`:
+
+```xml
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>Label</key>
+    <string>ai.adaptic.sophie-meeting-prep</string>
+    <key>ProgramArguments</key>
+    <array>
+        <string>/Users/sophie/sophie-ai/scripts/local-triggers/run-trigger.sh</string>
+        <string>meeting-prep</string>
+    </array>
+    <key>StartInterval</key>
+    <integer>900</integer>
+    <key>WorkingDirectory</key>
+    <string>/Users/sophie/sophie-ai</string>
+    <key>StandardOutPath</key>
+    <string>/Users/sophie/sophie-ai/logs/workflows/launchd-meeting-prep-stdout.log</string>
+    <key>StandardErrorPath</key>
+    <string>/Users/sophie/sophie-ai/logs/workflows/launchd-meeting-prep-stderr.log</string>
+</dict>
+</plist>
+```
+
+- [ ] **Step 3: Install the new daemons**
+
+```bash
+# Copy to LaunchAgents and load
+for plist in scripts/local-triggers/plists/ai.adaptic.sophie-meeting-*.plist; do
+    cp "$plist" ~/Library/LaunchAgents/$(basename "$plist")
+    launchctl load ~/Library/LaunchAgents/$(basename "$plist")
+done
+```
+
+- [ ] **Step 4: Commit**
+
+```bash
+git add scripts/local-triggers/plists/ai.adaptic.sophie-meeting-action-capture.plist scripts/local-triggers/plists/ai.adaptic.sophie-meeting-prep.plist
+git commit -m "feat: add launchd daemons for meeting prep (15min) and action capture (30min)"
+```
+
+---
+
+## Task 12: Update CLAUDE.md with Phase 1 Documentation
+
+**Files:**
+
+- Modify: `CLAUDE.md`
+
+- [ ] **Step 1: Add Phase 1 documentation**
+
+Add the following section to `CLAUDE.md`, after the "### Session Protocol" section and before "## Build & Test":
+
+```markdown
+### Control Tower 1: Strategy & Decisions
+
+- **Priority drift detection**: Evening wrap monitors `config/priorities.yaml` milestones, flags overdue in `state/dashboards/strategy-scorecard.yaml`
+- **Decision library**: Decisions archived in `knowledge/decisions/archive/`, indexed in `knowledge/decisions/index.yaml`
+- **Strategic coherence check**: Weekly memo validates initiatives align with priorities, flags unlinked work
+- **Living strategy state**: `knowledge/syntheses/strategy-state.yaml` evolves weekly with strategic position, assumptions, risks, signals
+- Drift thresholds: 7 days for critical/high priority, 14 for medium — defined in `config/sla-defaults.yaml`
+
+### Control Tower 2: Executive Office & Follow-Through
+
+- **Meeting action capture**: Every 30 min, checks Calendar + Granola + Slack for meeting outcomes, routes to queues
+- **Loop closure verification**: Midday sweep verifies `resolved` items actually completed before marking `closed`
+- **SLA tracking**: Items get SLA deadlines from `config/sla-defaults.yaml`, midday sweep calculates at_risk/breached
+- **Blocker playbooks**: `knowledge/sources/blocker-playbooks.yaml` provides resolution patterns for common blocker types
+- Status flow: `open → in_progress → blocked → resolved → closed` (resolved = owner says done, closed = Sophie verified)
+
+### Control Tower 3: Operating Cadence & PMO
+
+- **Meeting prep**: Every 15 min, generates prep briefs for upcoming meetings, sends to Mehran via Slack
+- **Post-meeting action routing**: Extracted actions get owners, SLAs, and queue tracking
+- **Initiative scorecard**: `state/dashboards/strategy-scorecard.yaml` tracks per-priority health
+- **Cadence quality audit**: Weekly memo checks meeting → action capture rate and action closure rate
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add CLAUDE.md
+git commit -m "feat: document Phase 1 Executive Core control towers in CLAUDE.md"
+```
+
+---
+
+## Task 13: Verify Phase 1
+
+- [ ] **Step 1: Verify all new files exist**
+
+```bash
+echo "=== NEW STATE FILES ===" && \
+ls state/dashboards/strategy-scorecard.yaml config/sla-defaults.yaml && \
+echo "=== DECISION LIBRARY ===" && \
+ls knowledge/decisions/archive/.gitkeep knowledge/decisions/index.yaml && \
+echo "=== STRATEGY STATE ===" && \
+ls knowledge/syntheses/strategy-state.yaml && \
+echo "=== BLOCKER PLAYBOOKS ===" && \
+ls knowledge/sources/blocker-playbooks.yaml && \
+echo "=== NEW TRIGGERS ===" && \
+ls schedules/triggers/meeting-action-capture.md schedules/triggers/meeting-prep.md && \
+echo "=== NEW PLISTS ===" && \
+ls scripts/local-triggers/plists/ai.adaptic.sophie-meeting-*.plist
+```
+
+Expected: All files listed without error.
+
+- [ ] **Step 2: Verify modified trigger prompts have new content**
+
+```bash
+grep -l "scorecard\|SLA\|sla_status\|drift\|coherence\|cadence.*audit\|blocker.*playbook\|loop.*closure\|decision.*detection" schedules/triggers/*.md
+```
+
+Expected: Should match morning-brief, midday-sweep, evening-wrap, weekly-strategic-memo, weekly-execution, inbox-processor.
+
+- [ ] **Step 3: Verify meeting daemons are loaded**
+
+```bash
+launchctl list | grep "sophie-meeting"
+```
+
+Expected: Both `ai.adaptic.sophie-meeting-action-capture` and `ai.adaptic.sophie-meeting-prep` listed.
+
+- [ ] **Step 4: Verify CLAUDE.md has Phase 1 sections**
+
+```bash
+grep "Control Tower 1\|Control Tower 2\|Control Tower 3" CLAUDE.md
+```
+
+Expected: All three control tower headings found.
+
+- [ ] **Step 5: Final commit if fixes needed**
+
+```bash
+git add -A && git commit -m "fix: address issues found during Phase 1 verification"
+```
+
+---
+
+## Summary
+
+| Task | Component                         | Files                  | Commits |
+| ---- | --------------------------------- | ---------------------- | ------- |
+| 1    | Strategy scorecard + SLA defaults | 2 new YAML files       | 1       |
+| 2    | Decision library + strategy state | 3 new files            | 1       |
+| 3    | Blocker playbooks                 | 1 new YAML file        | 1       |
+| 4    | Meeting action capture trigger    | 1 new MD file          | 1       |
+| 5    | Meeting prep trigger              | 1 new MD file          | 1       |
+| 6    | Enhanced morning brief            | 1 modified MD file     | 1       |
+| 7    | Enhanced midday sweep             | 1 modified MD file     | 1       |
+| 8    | Enhanced evening wrap             | 1 modified MD file     | 1       |
+| 9    | Enhanced strategic memo           | 1 modified MD file     | 1       |
+| 10   | Enhanced execution + inbox        | 2 modified MD files    | 1       |
+| 11   | Meeting trigger daemons           | 2 new plists + install | 1       |
+| 12   | CLAUDE.md documentation           | 1 modified file        | 1       |
+| 13   | Verification                      | 0 new files            | 0-1     |
+
+**Total: 13 tasks, ~15 files (10 new + 5 modified), ~12 commits**