The build prompt for an on-demand app with customer, provider and operator roles: matching, live tracking, payments and ratings.
Built for: Startups building local services marketplaces
On-demand products are really three apps: the customer app, the provider app and the operations dashboard. The matching algorithm, real-time location and the payment/commission flow are the hardest parts of the product.
The prompt defines the request-matching state machine, driver/provider onboarding, live tracking and payouts in a mobile-first architecture.
Each expert adds its own task block, constraints and success criteria to the prompt. Default selection for On-Demand Uber-like:
Design the system architecture. Edge-first, 100ms p95. DB schema, API contract, caching strategy, multi-tenancy, RLS, idempotency. Explain why the chosen backend + DB combination is the right call, and write the scaling plan.
Write a flawless PRD. User stories (Jobs-to-be-Done), acceptance criteria, edge cases, metrics (North Star, activation, retention); prioritize the roadmap with RICE. Scope an MVP that ships in 7 days.
Build the design system: Tailwind tokens, shadcn/ui, dark mode only, Linear-like density, command palette, keyboard-first. Describe wireframes for the 3 critical flows.
Pricing: Freemium vs. Free Trial, 3 tiers ($19/$49/$149), 20% annual discount, credit system. Hybrid flow with the selected payment providers. Churn-reduction tactics.
Deployment and operations plan: CI/CD pipeline (preview + production), IaC, secrets management, observability (logs, traces, alerts), SLO/SLA definitions, incident runbook, cost estimate and scaling thresholds.
Preloaded in step 2 of the Studio; change any of the 7 layers.
Every feature appears in the prompt as a "Spec + API + UI + Tests" line.
Sample idea: "An on-demand matching app for home care and cleaning services". Below are the master prompt's header and the first expert's block; the Studio generates the full text as 5 experts × 8 steps.
# On-Demand Uber-like - MASTER BUILD PROMPT Stack: Next.js 16 (App Router), Hono + CF Workers Goal: An on-demand matching app for home care and cleaning services This prompt builds a full-stack On-Demand Uber-like in 8 steps. Each step consumes the previous step's output. 5 experts' knowledge combined. Steps: 1. PRD & User Stories 2. Design System (Figma tokens) 3. DB Schema & API Contract 4. Auth & Billing Implementation 5. Core Features Build 6. AI Integration (RAG + Agents) 7. SEO/AEO & Analytics 8. Launch & Growth Checklist --- <prompt> <role name="Staff Engineer / CTO" org="ex-Stripe, ex-Vercel" specialty="System Architecture" experience="12y"> You are a Staff Engineer / CTO with 12 years of experience. Specialty: System Architecture. You have shipped world-class products at the level of Stripe, Linear and Vercel. </role> <context> Project: On-Demand Uber-like - An on-demand matching app for home care and cleaning services Type: On-Demand Uber-like Vision: Customers post a request and get matched with nearby providers; live tracking and messaging, card payments and commission, two-way ratings, an operations dashboard and a dispute flow. Target user: Startups building local services marketplaces - Pain: - Budget: Competitors: USP: Monetization: Commission % | Payments: Stripe Tech Stack: Next.js 16 (App Router), Hono + CF Workers, Supabase, Supabase Auth, Resend Features: Social OAuth (Google/Github), Realtime Presence, Chat + Video Call, Ratings & Reviews, Notifications Center, Admin Panel + Impersonate, Analytics Charts Compliance: KVKK/GDPR, 3D Secure Lang: EN </context> <task> Design the system architecture. Edge-first, 100ms p95. DB schema, API contract, caching strategy, multi-tenancy, RLS, idempotency. Explain why the chosen backend + DB combination is the right call, and write the scaling plan. General: production quality, copy-paste ready level of detail. </task> <technical_architecture> - Frontend: Next.js 16 (App Router) - App Router, Server Components, partial prerendering - Backend: Hono + CF Workers - Edge runtime, RPC, zod validation - DB: Supabase - pgvector for semantic search, type-safe ORM, RLS policies - Auth: Supabase Auth - Passkeys first, org/team model - Search: - typo-tolerant, faceted - Realtime: Resend - presence, CRDT-ready Payment flow: Stripe -> Webhook -> Background job -> Entitlement update -> Audit log </technical_architecture> <feature_matrix> - [ ] Social OAuth (Google/Github) -> Spec + API + UI + Tests - [ ] Realtime Presence -> Spec + API + UI + Tests …
With simple scoring weighted by distance, availability and rating; the prompt adds data-collection constraints so you can move to a learning model over time.
A single React Native (Expo) codebase is the default; the prompt defines the web operations dashboard separately in Next.js.
Claude Code, Cursor, Windsurf, v0, Lovable, Bolt and ChatGPT. You pick the output format (Claude XML, ChatGPT Markdown, Cursor Rules, v0, Lovable/Bolt) in step 4 of the Studio, and you can also download it as .cursorrules or CLAUDE.md.
Yes. On the Free plan you generate unlimited prompts with 3 experts and 2 formats — no card required. 18 experts, the Mega Chain and Export to Builders come with Monster Pro ($29/mo).
The build prompt for an LMS with course creation, video lessons, quizzes, progress tracking, certificates and subscriptions.
A privacy-first build prompt for a telemedicine product with appointments, video visits, patient records, e-prescriptions and payments.
The build prompt for a real estate platform with property listings, map search, virtual tours, an agent CRM and a rental flow.
The build prompt for a logistics product with shipment creation, courier/vehicle tracking, route optimization, proof of delivery and customer alerts.
The build prompt for a booking SaaS with calendars, availability rules, an online booking page, reminders and payments or deposits.
The build prompt for a CRM/ERP with customer records, a sales pipeline, a quote-to-order-to-invoice flow, tasks and reports.
Experts, stack and features come preloaded like on this page — you add the name and the idea. Free, no card required.