Skip to main content

Documentation Index

Fetch the complete documentation index at: https://www.adaline.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Writing a product spec manually takes hours and still ends up inconsistent. Many teams skip or rush it. And when specs are weak, the wrong product gets built, the design lacks context, and PMs spend more time in meetings than shipping. This prompt fixes that. Just fill in 4 inputs about your product and get a structured, team-ready spec in seconds, complete with personas, user stories, requirements, a timeline, and a risk assessment, every time.

​
How the prompt works

The system prompt gives the LLM a clear role: that of an expert Product Manager. It then requires six specific sections in every response. This structure is intentional. Without it, models default to a generic summary rather than a document a team can act on. The user prompt is kept short; just four variables that capture what any product needs without a long brief.

​
System prompt

Sets the LLM’s role and defines the six sections it must always include in the output. 
You are an expert Product Manager specializing in creating comprehensive product
specifications. Generate a well-structured product specification document that includes:

- Executive Summary with clear objectives.
- Target User Analysis with personas.
- Detailed Feature Specifications with user stories.
- Technical Requirements and Success Metrics.
- Implementation Timeline and Risk Assessment.

Format with clear headings and actionable details ready for team review.
Keep it comprehensive yet concise.

​
User prompt

The four variables a user fills in to describe their product. Kept short so it’s easy to use without a long brief. 
Create a product specification:

- Product Name: {{product_name}}
- Key Features: {{feature_list}}
- Target Users: {{target_users}}
- Success Metrics: {{success_metrics}}
Product Specification: FoodSnap - AI Recipe GeneratorExecutive SummaryFoodSnap is an AI-powered mobile app that transforms ingredient photos into personalized recipe recommendations, targeting busy professionals who want quick, tailored cooking solutions.Target User AnalysisPrimary Persona: Busy Professional Cook (Age 25-40)
  • Goals: Quick meal ideas, use existing ingredients, healthy eating
  • Pain Points: Lack of cooking inspiration, food waste, time constraints
Feature Specifications
  1. AI Ingredient Recognition
    • User Story: “As a user, I want to snap a photo of my fridge contents and get recipe suggestions”
    • Requirements: Computer vision API, ingredient database, accuracy over 90%
  2. Personalized Recipe Engine
    • User Story: “As a user, I want recipes that match my dietary preferences and skill level”
    • Requirements: User preference profiling, recipe difficulty scoring, dietary filters
  3. Smart Shopping Lists
    • User Story: “As a user, I want to generate shopping lists for missing ingredients”
    • Requirements: Recipe parsing, inventory tracking, grocery store integration
Technical Requirements
  • Platform: iOS/Android native apps
  • Backend: Cloud-based ML models, recipe database API
  • Performance: Under 3 second photo processing, offline recipe viewing
Success Metrics
  • User Retention: 80% after 30 days
  • Engagement: 3+ recipes generated per user weekly
  • Satisfaction: 4.5+ app store rating
  • Conversion: 25% of users upgrade to premium within 60 days
Implementation Timeline
  • Phase 1 (Months 1-2): Core photo recognition, basic recipe database
  • Phase 2 (Months 3-4): Personalization engine, dietary filters
  • Phase 3 (Months 5-6): Shopping list integration, premium features
Risk Assessment
  • Technical: AI accuracy may vary with photo quality | Mitigation: Extensive training data, user feedback loop
  • Market: Competitive recipe app landscape | Mitigation: Focus on unique photo-to-recipe workflow

​
Import into Adaline

This prompt comes with a ready-to-import Adaline project file. It includes the prompt, dataset, and evaluators, all pre-configured.
Download & import into Adaline

​
Evaluations and dataset

Each prompt in the library ships with a dataset and evaluators so you can test quality before deploying.

​
Evaluators

This use case comes with three evaluators: two LLM-as-a-judge prompts and one performance rule. Copy any to use in your own eval pipeline.

​
Structural completeness

Checks that all six required sections are present in every output. 
Goal: The product specification must include all required sections.

Checks:
- Executive Summary with clear objectives is present
- Target User Analysis with at least one persona is present
- Feature Specifications with user stories are present
- Technical Requirements are present
- Success Metrics are defined and measurable
- Implementation Timeline with phases is present
- Risk Assessment with mitigations is present

Scoring guidance:
- 1: Missing 3 or more required sections.
- 2: Missing 2 required sections.
- 3: All sections present but some are superficial or lack detail.
- 4: All sections present with good detail; minor gaps.
- 5: All sections fully present, well-structured, and detailed.

​
Actionability and specificity

Checks that the output is specific enough for a team to act on immediately. 
Goal: The product specification must be specific and actionable enough for a cross-functional team to act on immediately.

Checks:
- Features are written as user stories ("As a [user], I want to [action]")
- Success metrics are measurable and quantified (e.g., percentages, numbers, timeframes)
- Technical requirements reference specific platforms, APIs, or performance benchmarks
- Timeline includes concrete phases with durations
- Risk items include specific mitigation strategies, not generic statements

Scoring guidance:
- 1: Generic, vague output — could apply to any product.
- 2: Some specific details but most content is generic.
- 3: Adequately specific; team could act on it with some clarification needed.
- 4: Mostly specific and actionable; minor vague areas.
- 5: Fully actionable — every section has measurable, specific, team-ready details.

​
Response length

Guards against bloated output. A good spec is thorough but still easy to scan. 
Rule: Output must be less than 1,000 tokens.

​
Dataset

Four product types across different industries, each row maps directly to the four variables in the user prompt.
ProductKey featuresTarget usersSuccess metrics
FoodSnap: AI Recipe GeneratorPhoto-based ingredient recognition, personalized recipe suggestions, dietary restriction filters, shopping list generation.Busy professionals aged 25–40 who cook at home but lack inspiration and time for meal planning.80% user retention after 30 days, avg 3 recipes/user/week, 4.5+ app store rating.
ContractFlow: AI Contract ManagementAI-powered contract drafting, automated clause extraction, approval workflow automation, e-signature integration, contract expiry alerts.Legal and procurement teams at mid-market companies (100–500 employees) spending 10+ hours/week on contracts.60% faster turnaround, 90% processed without manual intervention, NPS above 45, 85% renewal at 12 months.
OnboardIQ: Employee Onboarding PlatformAutomated task assignment, document collection, role-based training paths, manager dashboard, and HRIS integration.HR teams at enterprises with 500+ employees hiring 50+ people/month, currently on email and spreadsheets.90 to 45 day time-to-productivity, 95% task completion in first 2 weeks, 70% less HR admin time.
TaxLayer: Real-Time Tax Calculation EngineReal-time tax rate lookup, multi-country VAT/GST support, transaction-level calculation, audit trail, and webhook notifications.Engineering teams at e-commerce and fintech companies needing accurate real-time tax calculations across jurisdictions.99.99% uptime SLA, under 100ms response, 50+ countries at launch, integration under 2 hours, 95% accuracy.