# Build Timeline & Execution Phases

Last updated: 2026-02-22

This folder contains the sequential build plan for developing Kalei. All features ship together in a single v1 release. The phases below represent an execution timeline for managing development complexity, not separate product phases.

Read in order:

1. `phase-0-groundwork-and-dev-environment.md`
2. `phase-1-platform-foundation.md`
3. `phase-2-core-experience-build.md`
4. `phase-3-launch-readiness-and-hardening.md`
5. `phase-4-spectrum-and-scale.md`

## Build Timeline Overview

These phases organize the work sequentially for manageable development and testing. All features — including Spectrum — are built toward a unified v1 launch.

- Phase 0: Groundwork and Dev Environment
  - Goal: stable tooling, accounts, repo standards, and local infrastructure.
- Phase 1: Platform Foundation
  - Goal: production-quality backend skeleton, auth, entitlements, core data model.
- Phase 2: Core Experience Build
  - Goal: ship Mirror, Turn, Lens, Ritual, Evidence Wall end-to-end.
- Phase 3: Launch Readiness and Hardening
  - Goal: Spectrum integration, safety, billing, reliability, compliance, app store readiness.
- Phase 4: Post-Launch Scale
  - Goal: analytics pipeline, feature enhancements, growth optimization, scaling controls.

## Development Gate Rules

Do not move to the next build phase until the current phase exit checklist is complete.

If a phase slips, reduce scope but do not skip quality gates for:

- security
- safety
- observability
- data integrity

## Product vs. Build Phases

**Important distinction:** These build phases are execution timelines, not product tiers. The product launches with all features (Mirror, Turn, Lens, Ritual, Evidence Wall, Guide, Spectrum) in a single v1 release. Free tier and Prism subscription tier have feature limits, but both versions of v1 include all features at launch.

## Tooling policy

These phase docs assume an open-source-first stack:

- Gitea for source control and CI
- GlitchTip for error tracking
- PostHog self-hosted for product analytics
- Ollama (local) and vLLM (staging/prod) for open-weight model serving

Platform exceptions remain for mobile distribution and push:

- Apple App Store and Google Play billing/distribution APIs
- APNs and FCM delivery infrastructure