{ "project": { "title": "Drafting Product Specifications", "icon": { "type": "emoji", "value": "📋" } }, "prompts": [ { "title": "Drafting Product Specifications", "icon": { "type": "emoji", "value": "📝" }, "config": { "settings": {}, "provider": "openai", "model": "gpt-4o" }, "messages": [ { "role": "system", "content": [ { "modality": "text", "value": "You are an expert Product Manager specializing in creating comprehensive product specifications. Generate a well-structured product specification document that includes:\n\n- Executive Summary with clear objectives\n- Target User Analysis with personas\n- Detailed Feature Specifications with user stories\n- Technical Requirements and Success Metrics\n- Implementation Timeline and Risk Assessment\n\nFormat with clear headings and actionable details ready for team review. Keep it comprehensive yet concise." } ] }, { "role": "user", "content": [ { "modality": "text", "value": "Create a product specification:\n\n- **Product Name:** {{product_name}}\n- **Key Features:** {{feature_list}}\n- **Target Users:** {{target_users}}\n- **Success Metrics:** {{success_metrics}}" } ] } ], "tools": [], "variables": { "product_name": { "modality": "text", "value": "", "linkedDataset": "Product Spec - Dataset", "linkedDatasetColumn": "product_name" }, "feature_list": { "modality": "text", "value": "", "linkedDataset": "Product Spec - Dataset", "linkedDatasetColumn": "feature_list" }, "target_users": { "modality": "text", "value": "", "linkedDataset": "Product Spec - Dataset", "linkedDatasetColumn": "target_users" }, "success_metrics": { "modality": "text", "value": "", "linkedDataset": "Product Spec - Dataset", "linkedDatasetColumn": "success_metrics" } }, "playgrounds": [ { "messages": [ { "role": "assistant", "content": [ { "modality": "text", "value": "Product Specification: FoodSnap - AI Recipe Generator\n\n## Executive Summary\nFoodSnap is an AI-powered mobile app that transforms ingredient photos into personalized recipe recommendations, targeting busy professionals who want quick, tailored cooking solutions.\n\n## Target User Analysis\n**Primary Persona:** Busy Professional Cook (Age 25-40)\n- Goals: Quick meal ideas, use existing ingredients, healthy eating\n- Pain Points: Lack of cooking inspiration, food waste, time constraints\n\n## Feature Specifications\n1. **AI Ingredient Recognition**\n - User Story: \"As a user, I want to snap a photo of my fridge contents and get recipe suggestions\"\n - Requirements: Computer vision API, ingredient database, accuracy >90%\n\n2. **Personalized Recipe Engine**\n - User Story: \"As a user, I want recipes that match my dietary preferences and skill level\"\n - Requirements: User preference profiling, recipe difficulty scoring, dietary filters\n\n3. **Smart Shopping Lists**\n - User Story: \"As a user, I want to generate shopping lists for missing ingredients\"\n - Requirements: Recipe parsing, inventory tracking, grocery store integration\n\n## Technical Requirements\n- Platform: iOS/Android native apps\n- Backend: Cloud-based ML models, recipe database API\n- Performance: <3 second photo processing, offline recipe viewing\n\n## Success Metrics\n- User Retention: 80% after 30 days\n- Engagement: 3+ recipes generated per user weekly\n- Satisfaction: 4.5+ app store rating\n- Conversion: 25% of users upgrade to premium within 60 days\n\n## Implementation Timeline\n- Phase 1 (Months 1-2): Core photo recognition, basic recipe database\n- Phase 2 (Months 3-4): Personalization engine, dietary filters\n- Phase 3 (Months 5-6): Shopping list integration, premium features\n\n## Risk Assessment\n- Technical: AI accuracy may vary with photo quality\n - Mitigation: Extensive training data, user feedback loop\n- Market: Competitive recipe app landscape\n - Mitigation: Focus on unique photo-to-recipe workflow" } ] } ], "config": { "settings": {}, "provider": "openai", "model": "gpt-4o" }, "connectedDataset": "Product Spec - Dataset" } ], "evaluators": [ { "title": "Structural Completeness", "state": "active", "weight": 1, "threshold": 0.7, "value": { "type": "llm-as-a-judge", "group": "ai-powered", "value": "Goal: The product specification must include all required sections.\n\nChecks:\n- Executive Summary with clear objectives is present\n- Target User Analysis with at least one persona is present\n- Feature Specifications with user stories are present\n- Technical Requirements are present\n- Success Metrics are defined and measurable\n- Implementation Timeline with phases is present\n- Risk Assessment with mitigations is present\n\nScoring guidance:\n- 1: Missing 3 or more required sections.\n- 2: Missing 2 required sections.\n- 3: All sections present but some are superficial or lack detail.\n- 4: All sections present with good detail; minor gaps.\n- 5: All sections fully present, well-structured, and detailed." }, "connectedDataset": "Product Spec - Dataset", "runContinuously": true, "continuousSampleRate": 1 }, { "title": "Actionability & Specificity", "state": "active", "weight": 1, "threshold": 0.7, "value": { "type": "llm-as-a-judge", "group": "ai-powered", "value": "Goal: The product specification must be specific and actionable enough for a cross-functional team to act on immediately.\n\nChecks:\n- Features are written as user stories (\"As a [user], I want to [action]\")\n- Success metrics are measurable and quantified (e.g., percentages, numbers, timeframes)\n- Technical requirements reference specific platforms, APIs, or performance benchmarks\n- Timeline includes concrete phases with durations\n- Risk items include specific mitigation strategies, not generic statements\n\nScoring guidance:\n- 1: Generic, vague output — could apply to any product.\n- 2: Some specific details but most content is generic.\n- 3: Adequately specific; team could act on it with some clarification needed.\n- 4: Mostly specific and actionable; minor vague areas.\n- 5: Fully actionable — every section has measurable, specific, team-ready details." }, "connectedDataset": "Product Spec - Dataset", "runContinuously": true, "continuousSampleRate": 1 }, { "title": "Response Length", "state": "active", "weight": 1, "threshold": 0.7, "value": { "type": "response-length", "group": "performance", "value": { "value": "1000", "unit": "tokens", "operator": "less" } }, "connectedDataset": "Product Spec - Dataset", "runContinuously": true, "continuousSampleRate": 1 } ] } ], "datasets": [ { "title": "Product Spec - Dataset", "icon": { "type": "emoji", "value": "💾" }, "columns": [ { "name": "product_name", "settings": { "type": "static" } }, { "name": "feature_list", "settings": { "type": "static" } }, { "name": "target_users", "settings": { "type": "static" } }, { "name": "success_metrics", "settings": { "type": "static" } } ], "rows": [ { "product_name": "FoodSnap - AI Recipe Generator", "feature_list": "Photo-based ingredient recognition, personalized recipe suggestions, dietary restriction filters, shopping list generation", "target_users": "Busy professionals aged 25-40 who cook at home but lack inspiration and time for meal planning", "success_metrics": "80% user retention after 30 days, average 3 recipes generated per user per week, 4.5+ app store rating" }, { "product_name": "ContractFlow - AI Contract Management", "feature_list": "AI-powered contract drafting, automated clause extraction, approval workflow automation, e-signature integration, contract expiry alerts", "target_users": "Legal and procurement teams at mid-market companies (100-500 employees) spending 10+ hours per week managing contracts manually", "success_metrics": "Reduce contract turnaround time by 60%, 90% of contracts processed without manual intervention, NPS score above 45, 85% renewal rate at 12 months" }, { "product_name": "OnboardIQ - Employee Onboarding Platform", "feature_list": "Automated onboarding task assignment, document collection and verification, role-based training path generation, manager progress dashboard, HRIS integration", "target_users": "HR teams at enterprises with 500+ employees hiring 50+ people per month, currently managing onboarding via email and spreadsheets", "success_metrics": "Reduce time-to-productivity from 90 to 45 days, 95% task completion rate for new hires in first 2 weeks, reduce HR admin time on onboarding by 70%" }, { "product_name": "TaxLayer API - Real-Time Tax Calculation Engine", "feature_list": "Real-time tax rate lookup by jurisdiction, multi-country VAT/GST support, transaction-level tax calculation, audit trail generation, webhook notifications for rate changes", "target_users": "Engineering teams at e-commerce and fintech companies needing accurate real-time tax calculations across jurisdictions without building in-house tax logic", "success_metrics": "99.99% API uptime SLA, <100ms average response time, support for 50+ countries at launch, developer integration time under 2 hours, 95% tax rate calculation accuracy" } ] } ] }