AR collections action plan · risk 3

01 / Trigger 02 / Context + preconditions 03 / HITL gate (Mike approves) 04 / Fan-out cascade 05 / Post actions (log_run + reflexion + events) 06 / Verify (SQL / R2 / HTTP checks) How this workflow gets kicked off. Could be a chat-tool invocation, a cron tick, an inbound event (e.g. price.changed), or Mike clicking 'execute' from an admin page. TRIGGER kind: cron cron: 0 6 * * * tz: America/New_York invoker: Mike (single-admin) risk_level: 3i Manual Mike invokes risk 3 Before deciding anything, pull related data from D1 (the local mirror of NetSuite). Each query loads a slice of the entity's current state so the AI and Mike can review before any writes happen. LOAD CONTEXT (D1 queries before fan-out) aging: SELECT customer_id, customer_name, SUM(amount) AS total_open, MAX(days_overdue)… prior_actions: SELECT customer_name, MAX(proposed_at) FROM proposed_actions WHERE action_type=…i Load context 2 D1 queries Safety checks that must pass before any writes. 'block' severity halts the run; 'warn' surfaces a warning but continues. Without these, a bad input could cascade into NetSuite. PRECONDITIONS (checked before fan-out) [warn] aging_data_fresh: MAX(sync_log.completed_at WHERE sync_type='scheduled_hot_customer_payments') > …i Preconditions 1 check The HITL (Human-In-The-Loop) gate. The workflow stages a proposed_action and waits for Mike to approve in /proposed-actions.html. Only fires when risk_level >= 3. This is the invariant: no NS write happens without Mike's go-ahead. HITL GATE (Mike approves before fan-out) action_type: workflow_ar_aging_action_plan entity_ref: workflow:ar_aging_action_plan:run_<run_id> approver: mike (single-admin) risk_gate: >= 3 (this workflow = 3) approval window: typical <= 60 min envelope: proposed_actions row staged by runneri Mike approves stage_proposed_action risk ≥ 3 gate Repeat the same fan-out for each item in a collection (recipients, aging buckets, sub-workflows). STUB today. FAN-OUT #draft_per_tier -> multiple (loop) kind: loop_over_aging action: stage proposed_action with tier-specific draft body status: STUB (src/lib/workflow_runner.ts)i draft_per_tier loop_over_aging STUB Set a follow-up flag on a row (e.g., 'needs_review') so a downstream cron or human picks it up later. STUB today. FAN-OUT #pause_on_hold_check -> flag: stage propose_customer_program with type=service_hold kind: flag if: customer.days_overdue > 90 AND customer.total_open > 25000 action: stage propose_customer_program with type=service_hold status: STUB (src/lib/workflow_runner.ts)i pause_on_hold_check flag STUB Draft an email and stage it as a proposed_action for Mike's review. The email is NOT sent - only drafted + queued. STUB today. FAN-OUT #sales_rep_notify -> email draft kind: hitl_email_draft tool: propose_email_to_customer status: STUB (src/lib/workflow_runner.ts)i sales_rep_notify hitl_email_draft STUB Always-runs at the end of every workflow execution: writes a row to workflow_run_log with status, duration, step counts, and errors. Real implementation. POST ACTION: log_run -> D1: workflow_run_log fields: run_id, workflow_type, status, started_at, completed_at, summary_json source: runner automatic (always)i log_run workflow_run_log REAL Writes an entry to reflexion_log so the AI 'remembers' what happened. Only fires if the contract has reflexion_enabled=1. Future workflows can search this log for prior context. Real implementation. POST ACTION: reflexion -> D1: reflexion_log tags: ar_aging_action_plan reflexion_enabled: True fields: run_id, narrative, tags source: runner automatic (when reflexion_enabled=1)i reflexion reflexion_log REAL Fires a workflow.completed / workflow.partial / workflow.failed event into the event ledger so downstream subscriptions can react. Uses an idempotency_key so producer retries collapse. Real implementation (R564). POST ACTION: event -> Event ledger (recordEvent) types: workflow.completed | workflow.partial | workflow.failed idempotency_key per run_id source: runner automatici event workflow.completed REAL A post-execution sanity check. The runner stages this with status='pending'; the verify-scheduler cron (every :08 and :38 hourly) wakes up after the configured window (e.g. +24h) and executes the sql_check, then flips status to pass/fail/timeout. Real implementation (R564). VERIFY: actions_staged window: 10s sql_check: SELECT COUNT(*) FROM proposed_actions WHERE action_type='collection_action' AND… scheduler: verify cron @ :08/:38 (R563) result row: workflow_verify_resultsi actions_staged ≤60m Legend User UI Agent logic Policy Tool action Context / trace

Contract

  • • Type: ar_aging_action_plan
  • • Risk: 3
  • • Trigger: manual
  • • Fan-out: 3 targets

HITL semantics

  • • risk ≥ 3 ⇒ stage_proposed_action
  • • Mike approves before fan-out
  • • REAL = solid green · STUB = dashed

Post actions

  • • log_run → workflow_run_log
  • • reflexion → reflexion_log
  • • event → workflow.completed
  • • verify × 1

Workflow diagram • Built with Archify • Press T for theme and E for export