Cursor for Product Managers

Build a production-ready AI-native SaaS for product teams that helps them decide what to build — not just how to build it. Core vision: Create a “Cursor for product management”: a system that continuously ingests customer conversations, feedback, and usage data, synthesizes insights, and recommends what the team should build next — with clear reasoning and implementation breakdowns. The system must support the full product discovery loop: 1. Aggregate evidence 2. Identify unmet needs 3. Prioritize opportunities 4. Propose product changes 5. Generate implementation-ready specs 6. Track outcomes post-launch Core capabilities: Customer and data ingestion layer: - Upload customer interview transcripts - Import support tickets (Intercom, Zendesk, Slack) - Sync feature requests and feedback boards - Connect product analytics (PostHog, Amplitude, Mixpanel) - Import NPS surveys and churn feedback - Ingest session replay metadata - Provide an API for custom data ingestion All data should be normalized into structured insight objects. Insight and clustering engine: - Automatically cluster recurring user pain points - Identify frequency and severity signals - Detect unmet needs across segments - Surface representative customer quotes as evidence - Highlight contradictions or conflicting signals - Track changes in pain patterns over time Output should be ranked opportunity areas with supporting evidence. “What should we build next?” mode: The user can ask: “Given our current data, what should we build next?” The system must: - Recommend specific feature or product changes - Provide reasoning backed by evidence - Show source citations (transcripts, tickets, metrics) - Estimate potential impact (retention, revenue, activation) - Flag assumptions and risks - Present alternative hypotheses Opportunity scoring system: Each proposed initiative receives: - Frequency score - Revenue impact estimate - Retention impact estimate - Strategic alignment score - Effort estimate - Confidence score Allow customization of weighting formulas. Spec and implementation generator: Once an initiative is selected, generate: - PRD - User stories - Acceptance criteria - Edge cases - Non-functional requirements - Data model changes - API contracts - UI flows - QA checklist - Engineering tickets Output must be structured, versioned, and clean enough for handoff to coding agents or engineers. Iterative AI collaboration: - Edit and refine specs via conversational AI - Version history with diff and rollback - Side-by-side comparisons - “Readiness score” to flag missing edge cases, validation rules, and non-functional gaps - Automated gap detection Multi-tenant and collaboration: - Organizations and team workspaces - Roles: org-owner, product-manager, engineer, reviewer - Comment threads - Mentions - Approvals - Status workflows - Full audit logs - Notifications for review and approval events Post-launch feedback loop: After a feature ships: - Track adoption and usage metrics - Compare predicted impact versus actual results - Identify unexpected side effects - Feed performance data back into the opportunity scoring model - Continuously refine prioritization Data model: - organizations - users - projects - data-sources - raw-evidence - clustered-insights - opportunities - opportunity-scores - product-prompts - prompt-versions - generated-artifacts - approvals - comments - audit-events - outcome-metrics Dashboards: - Top unmet needs by segment - Opportunity pipeline - Idea to approved spec cycle time - Prediction accuracy (forecast versus actual) - Insight quality score - Unresolved blocker count Operational requirements: - Full audit log - Clear workflow boundaries - Deterministic automation rules - Secure tenant isolation - SOC2-ready architecture - API-first design Positioning summary: This is not just a PRD generator. It is an AI-native product decision engine that continuously analyzes customer evidence, recommends what to build, explains why, generates how to implement it, and measures outcomes afterward. Create a modern startup design inspired by Y Combinator (YC) companies. Choose one bright primary color and build a clean, minimal color scheme around it. The design should feel bold, simple, and product-focused with strong typography, generous whitespace, and clear hierarchy.