kalei/docs/codex phase documents/phase-3-launch-readiness-an...

4.0 KiB

Phase 3 - Launch Readiness and Hardening

Duration: 2-4 weeks Primary owner: Full stack + operations focus

1. Objective

Prepare Kalei for real users with production safeguards:

  • safety policy completion and crisis flow readiness
  • subscription and entitlement reliability
  • app and API operational stability
  • privacy and compliance basics for app store approval

2. Entry Criteria

Phase 2 exit checklist complete.

3. Scope

3.1 Safety and Trust Hardening

Tasks:

  1. finalize crisis keyword and pattern sets
  2. validate crisis response templates and regional resources
  3. add safety dashboards and alerting
  4. add audit trail for safety decisions

Validation goals:

  • crisis path returns under 1 second in most cases
  • no crisis path returns reframing output

3.2 Billing and Entitlements

Tasks:

  1. complete App Store Server Notifications ingestion
  2. complete Google Play RTDN ingestion
  3. build reconciliation jobs for both stores (entitlements sync)
  4. test expired, canceled, trial, billing retry, and restore scenarios
  5. add paywall gating in all required clients

Validation goals:

  • entitlement state converges within minutes after billing changes
  • no premium endpoint access for expired plans

3.3 Reliability Engineering

Tasks:

  1. finalize health checks and readiness probes
  2. add backup and restore procedures for Postgres
  3. add Redis persistence strategy for critical counters if required
  4. define incident severity levels and on-call workflow

Validation goals:

  • verified DB restore from backup in staging
  • runbook exists for API outage, DB outage, AI provider outage

3.4 Security and Compliance Baseline

Tasks:

  1. secrets rotation policy and documented process
  2. verify transport security and secure headers
  3. verify account deletion and data export flows
  4. prepare privacy policy and terms for submission

Validation goals:

  • basic security checklist signed off
  • app store privacy disclosures map to real data flows

3.5 Observability and Cost Control

Tasks:

  1. define alerts for latency, error rate, and AI spend thresholds
  2. implement monthly spend cap and automatic degradation rules
  3. monitor feature-level token cost dashboards

Validation goals:

  • alert thresholds tested in staging
  • degradation path verified (Lens fallback first)

3.6 Beta and Release Pipeline

Tasks:

  1. set up TestFlight internal/external testing
  2. set up Android internal testing track
  3. run beta cycle with scripted feedback collection
  4. triage and fix launch-blocking defects

Validation goals:

  • no unresolved launch-blocking defects
  • release checklist complete for both stores

4. Suggested Execution Plan

Week 1:

  • safety hardening and billing reconciliation
  • initial reliability runbooks

Week 2:

  • security/compliance checks
  • backup and restore drills
  • full observability alert tuning

Week 3:

  • TestFlight and Play internal beta
  • defect triage and fixes

Week 4 (if needed):

  • final store submission materials
  • go/no-go readiness review

5. Release Checklists

5.1 API release checklist

  • migration plan reviewed
  • rollback plan documented
  • dashboards green
  • error budget acceptable

5.2 Mobile release checklist

  • build reproducibility verified
  • crash-free session baseline from beta acceptable
  • paywall and entitlement states correct
  • copy and metadata final

5.3 Business and policy checklist

  • privacy policy URL live
  • terms URL live
  • support contact available
  • crisis resources configured for launch regions

6. Exit Criteria

You can exit Phase 3 when:

  • app is store-ready with stable entitlement behavior
  • safety flow is verified and monitored
  • operations runbooks and alerts are live
  • backup and restore are proven in practice

7. Risks To Watch

  • Risk: entitlement mismatch from webhook delays.
    • Mitigation: scheduled reconciliation and idempotent webhook handling.
  • Risk: launch-day AI latency spikes.
    • Mitigation: timeout limits and graceful fallback behavior.
  • Risk: compliance gaps discovered late.
    • Mitigation: complete privacy mapping before store submission.