tinkerchat.com — Audited Product Plan

What This Project Is

• The live implementation is a single-page AI chat interface.
• Based on the audit, the current problem is not missing infrastructure but weak product identity and weak differentiation.

Evidence From The Audit

• site-audit.md says the live page is branded Ucok AI Chat, not TinkerChat.
• The audit says the current implementation is effectively a static single-page chat demo with no real product funnel.
• The main issues are brand mismatch, generic positioning, and lack of a real experimental-product story.

Actual Planning Priority

• Fix the product definition before planning backend complexity.
• Decide whether this domain is:
• a demo page
• an experimental local-AI lab
• a real product brand

Sensible Cloudflare Direction

• Cloudflare is still the right delivery target.
• The likely starting architecture is lightweight:
• Pages for the product shell
• Functions/Workers only for waitlist, beta intake, feature flags, or experiment APIs
• D1 only if experiments, accounts, or saved sessions become real product features

What Should Not Be Assumed

• Do not build a heavy chat architecture until the product wedge is clear.
• Do not treat the current live page as proof that a full application stack is required.
• Do not expand runtime complexity before brand and funnel are fixed.

Implementation Sequence

• Rebrand the live experience consistently as TinkerChat or move it off the domain.
• Replace the generic chat framing with an explicit experimentation-lab positioning.
• Add a real product funnel: waitlist, beta capture, experiment catalog, or release notes.
• Add runtime services only after the product model is chosen.

Definition of Done

• The plan reflects the actual live state: one chat page with positioning problems.
• Product identity is fixed before infrastructure expands.
• Cloudflare delivery stays lightweight until real product needs justify more.

⚙ HARD CONSTRAINTS (enforced for all sites)

This domain MUST operate within these constraints — no exceptions:

• 100% Cloudflare serverless — Workers + D1 + R2 + KV + Workers AI + Vectorize. NEVER PM2, NEVER VPS, NEVER Docker in production path.
• 100% AI-automated — every customer interaction, every moderation decision, every transaction reconcile = AI. No manual queue, no live human chat support, no physical fulfillment.
• 1-operator solo — one person can run the entire operation from a phone. No team meetings, no shared inbox, no shift rotation.
• WhatsApp AI bot for all support (24/7, instant response, no SLA promises that need humans).
• Mayar QRIS for all Indonesian payments (subscription auto-renew, no manual invoicing).
• Indonesian UI primary — bahasa-first, English fallback only where unavoidable.
• Privacy — opt-in only, delete-on-request honored within 24h (cron-driven).
• No physical goods, no inventory — digital products + affiliate referrals only.

If the plan above describes any flow that violates these constraints, treat the plan as ASPIRATIONAL only and rework before building. The constraint trifecta wins.