This is a concise map of how I scaffolded Rally end to end: stack choices, research rhythm, and where AI fits without skipping product discipline. The timeline below is the structure I return to when starting from zero.
Choose your stack
Foundation infrastructure — frontend, database, UI, AI, observability
Framework & hostingNext.jsGitHub
UI component libraryShadCN
AI SDK — standardized interface to modelsVercel AI SDKOpenAIAnthropic
Observability & evalsBraintrust
Iterate across models, run prompt evals, monitor logs — critical for AI products
Coding environment & data sources
Tooling, reuse patterns, and external data ingestion
Coding toolsCursorClaude Code
Project reuse patternOnce one project is running, copy-paste the working scaffold into the next app — avoids re-configuring from scratch
External data (for data-intensive products)Third-party TikTok API via Apify
Rally fetches TikTok data via a vendor API rather than the official TikTok API — necessary when platform access is restricted
UX, data & AI flow mapping most important
Traditional UX design process adapted for AI products
User flow
Interview users, analyze onboarding calls, map every step. Find what can be automated, augmented, or replaced by an agent.
Data flow
What data comes from the user as context? What does AI need to process? What feeds the learning loop? What does the agent need as memory?
AI agent flow
Design the agent architecture. General manager model (less visibility) vs micro-managed (more control). Directly tied to UX and what users see.
AI was used to analyze interview transcripts and onboarding recordings to surface patterns — then map those patterns to the three flows above
Research & PRD drafting
Competitive landscape + spec creation
InputsCompetitive researchPeer product analysisExisting design patterns
ProcessClaude Plan Mode / Cursor→brainstorm →PRD draft→iterate →Final spec
Talk it out with AI first — draft the user flow, key behaviors, and step-by-step experience before writing formal requirements
Prototyping
Generate multiple design variants, iterate fast
AI prototyping toolsFigma AILovableClaude Desktopv0
Run multiple tools in parallel to generate design variants, then consolidate into one direction. Speed over fidelity at this stage.
Build → Refactor → Enforce
Scaffold fast, rebuild clean, lock the foundation
Timeline (Rally experience)Week 1 — scaffold
AI-generated prototype scaffolded at speed. Everything works technically, but quality is uneven.
Weeks 2–3 — refactor
Near full rebuild. Inconsistent UI, component drift, and no shared patterns required major rework.
Lessons learnedEnforce design system from day 1
Forcing AI codegen to use one design system from the initial build minimizes UI refactors later. The faster the initial build, the more important this constraint is.
Refine & polish
Elevate UI quality once the foundation is stable
ApproachUse skills
Skills are curated interaction and animation references that help lift UI quality quickly — study motion patterns, copy techniques, and apply them to your components once the scaffold is locked.