./browse/prompts

# KPI Dashboard Design Comprehensive patterns for designing effective Key Performance Indicator (KPI) dashboards that drive business decisions. ## When to Use This Skill - Designing executive dashboards - Selecting meaningful KPIs - Building real-time monitoring displays - Creating department-specific metrics views - Improving existing dashboard layouts - Establishing metric governance ## Core Concepts ### 1. KPI Framework | Level | Focus | Update Frequency | Audience | | --------------- | ---------------- | ----------------- | ---------- | | **Strategic** | Long-term goals | Monthly/Quarterly | Executives | | **Tactical** | Department goals | Weekly/Monthly | Managers | | **Operational** | Day-to-day | Real-time/Daily | Teams | ### 2. SMART KPIs ``` Specific: Clear definition Measurable: Quantifiable Achievable: Realistic targets Relevant: Aligned to goals Time-bound: Defined period ``` ### 3. Dashboard Hierarchy ``` ├── Executive Summary (1 page) │ ├── 4-6 headline KPIs │ ├── Trend indicators │ └── Key alerts ├── Department Views │ ├── Sales Dashboard │ ├── Marketing Dashboard │ ├── Operations Dashboard │ └── Finance Dashboard └── Detailed Drilldowns ├── Individual metrics └── Root cause analysis ``` ## Common KPIs by Department ### Sales KPIs ```yaml Revenue Metrics: - Monthly Recurring Revenue (MRR) - Annual Recurring Revenue (ARR) - Average Revenue Per User (ARPU) - Revenue Growth Rate Pipeline Metrics: - Sales Pipeline Value - Win Rate - Average Deal Size - Sales Cycle Length Activity Metrics: - Calls/Emails per Rep - Demos Scheduled - Proposals Sent - Close Rate ``` ### Marketing KPIs ```yaml Acquisition: - Cost Per Acquisition (CPA) - Customer Acquisition Cost (CAC) - Lead Volume - Marketing Qualified Leads (MQL) Engagement: - Website Traffic - Conversion Rate - Email Open/Click Rate - Social Engagement ROI: - Marketing ROI - Campaign Performance - Channel Attribution - CAC Payback Period ``` ### Product KPIs ```yaml Usage: - Daily/Monthly Active Users (DAU/MAU) - Session Duration - Feature Adoption Rate - Stickiness (DAU/MAU) Quality: - Net Promoter Score (NPS) - Customer Satisfaction (CSAT) - Bug/Issue Count - Time to Resolution Growth: - User Growth Rate - Activation Rate - Retention Rate - Churn Rate ``` ### Finance KPIs ```yaml Profitability: - Gross Margin - Net Profit Margin - EBITDA - Operating Margin Liquidity: - Current Ratio - Quick Ratio - Cash Flow - Working Capital Efficiency: - Revenue per Employee - Operating Expense Ratio - Days Sales Outstanding - Inventory Turnover ``` ## Dashboard Layout Patterns ### Pattern 1: Executive Summary ``` ┌─────────────────────────────────────────────────────────────┐ │ EXECUTIVE DASHBOARD [Date Range ▼] │ ├─────────────┬─────────────┬─────────────┬─────────────────┤ │ REVENUE │ PROFIT │ CUSTOMERS │ NPS SCORE │ │ $2.4M │ $450K │ 12,450 │ 72 │ │ ▲ 12% │ ▲ 8% │ ▲ 15% │ ▲ 5pts │ ├─────────────┴─────────────┴─────────────┴─────────────────┤ │ │ │ Revenue Trend │ Revenue by Product │ │ ┌───────────────────────┐ │ ┌──────────────────┐ │ │ │ /\ /\ │ │ │ ████████ 45% │ │ │ │ / \ / \ /\ │ │ │ ██████ 32% │ │ │ │ / \/ \ / \ │ │ │ ████ 18% │ │ │ │ / \/ \ │ │ │ ██ 5% │ │ │ └───────────────────────┘ │ └──────────────────┘ │ │ │ ├─────────────────────────────────────────────────────────────┤ │ 🔴 Alert: Churn rate exceeded threshold (>5%) │ │ 🟡 Warning: Support ticket volume 20% above average │ └─────────────────────────────────────────────────────────────┘ ``` ### Pattern 2: SaaS Metrics Dashboard ``` ┌─────────────────────────────────────────────────────────────┐ │ SAAS METRICS Jan 2024 [Monthly ▼] │ ├──────────────────────┬──────────────────────────────────────┤ │ ┌────────────────┐ │ MRR GROWTH │ │ │ MRR │ │ ┌────────────────────────────────┐ │ │ │ $125,000 │ │ │ /── │ │ │ │ ▲ 8% │ │ │ /────/ │ │ │ └────────────────┘ │ │ /────/ │ │ │ ┌────────────────┐ │ │ /────/ │ │ │ │ ARR │ │ │ /────/ │ │ │ │ $1,500,000 │ │ └────────────────────────────────┘ │ │ │ ▲ 15% │ │ J F M A M J J A S O N D │ │ └────────────────┘ │ │ ├──────────────────────┼──────────────────────────────────────┤ │ UNIT ECONOMICS │ COHORT RETENTION │ │ │ │ │ CAC: $450 │ Month 1: ████████████████████ 100% │ │ LTV: $2,700 │ Month 3: █████████████████ 85% │ │ LTV/CAC: 6.0x │ Month 6: ████████████████ 80% │ │ │ Month 12: ██████████████ 72% │ │ Payback: 4 months │ │ ├──────────────────────┴──────────────────────────────────────┤ │ CHURN ANALYSIS │ │ ┌──────────┬──────────┬──────────┬──────────────────────┐ │ │ │ Gross │ Net │ Logo │ Expansion │ │ │ │ 4.2% │ 1.8% │ 3.1% │ 2.4% │ │ │ └──────────┴──────────┴──────────┴──────────────────────┘ │ └─────────────────────────────────────────────────────────────┘ ``` ### Pattern 3: Real-time Operations ``` ┌─────────────────────────────────────────────────────────────┐ │ OPERATIONS CENTER Live ● Last: 10:42:15 │ ├────────────────────────────┬────────────────────────────────┤ │ SYSTEM HEALTH │ SERVICE STATUS │ │ ┌──────────────────────┐ │ │ │ │ CPU MEM DISK │ │ ● API Gateway Healthy │ │ │ 45% 72% 58% │ │ ● User Service Healthy │ │ │ ███ ████ ███ │ │ ● Payment Service Degraded │ │ │ ███ ████ ███ │ │ ● Database Healthy │ │ │ ███ ████ ███ │ │ ● Cache Healthy │ │ └──────────────────────┘ │ │ ├────────────────────────────┼────────────────────────────────┤ │ REQUEST THROUGHPUT │ ERROR RATE │ │ ┌──────────────────────┐ │ ┌──────────────────────────┐ │ │ │ ▁▂▃▄▅▆▇█▇▆▅▄▃▂▁▂▃▄▅ │ │ │ ▁▁▁▁▁▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁ │ │ │ └──────────────────────┘ │ └──────────────────────────┘ │ │ Current: 12,450 req/s │ Current: 0.02% │ │ Peak: 18,200 req/s │ Threshold: 1.0% │ ├────────────────────────────┴────────────────────────────────┤ │ RECENT ALERTS │ │ 10:40 🟡 High latency on payment-service (p99 > 500ms) │ │ 10:35 🟢 Resolved: Database connection pool recovered │ │ 10:22 🔴 Payment service circuit breaker tripped │ └─────────────────────────────────────────────────────────────┘ ``` ## Implementation Patterns ### SQL for KPI Calculations ```sql -- Monthly Recurring Revenue (MRR) WITH mrr_calculation AS ( SELECT DATE_TRUNC('month', billing_date) AS month, SUM( CASE subscription_interval WHEN 'monthly' THEN amount WHEN 'yearly' THEN amount / 12 WHEN 'quarterly' THEN amount / 3 END ) AS mrr FROM subscriptions WHERE status = 'active' GROUP BY DATE_TRUNC('month', billing_date) ) SELECT month, mrr, LAG(mrr) OVER (ORDER BY month) AS prev_mrr, (mrr - LAG(mrr) OVER (ORDER BY month)) / LAG(mrr) OVER (ORDER BY month) * 100 AS growth_pct FROM mrr_calculation; -- Cohort Retention WITH cohorts AS ( SELECT user_id, DATE_TRUNC('month', created_at) AS cohort_month FROM users ), activity AS ( SELECT user_id, DATE_TRUNC('month', event_date) AS activity_month FROM user_events WHERE event_type = 'active_session' ) SELECT c.cohort_month, EXTRACT(MONTH FROM age(a.activity_month, c.cohort_month)) AS months_since_signup, COUNT(DISTINCT a.user_id) AS active_users, COUNT(DISTINCT a.user_id)::FLOAT / COUNT(DISTINCT c.user_id) * 100 AS retention_rate FROM cohorts c LEFT JOIN activity a ON c.user_id = a.user_id AND a.activity_month >= c.cohort_month GROUP BY c.cohort_month, EXTRACT(MONTH FROM age(a.activity_month, c.cohort_month)) ORDER BY c.cohort_month, months_since_signup; -- Customer Acquisition Cost (CAC) SELECT DATE_TRUNC('month', acquired_date) AS month, SUM(marketing_spend) / NULLIF(COUNT(new_customers), 0) AS cac, SUM(marketing_spend) AS total_spend, COUNT(new_customers) AS customers_acquired FROM ( SELECT DATE_TRUNC('month', u.created_at) AS acquired_date, u.id AS new_customers, m.spend AS marketing_spend FROM users u JOIN marketing_spend m ON DATE_TRUNC('month', u.created_at) = m.month WHERE u.source = 'marketing' ) acquisition GROUP BY DATE_TRUNC('month', acquired_date); ``` ### Python Dashboard Code (Streamlit) ```python import streamlit as st import pandas as pd import plotly.express as px import plotly.graph_objects as go st.set_page_config(page_title="KPI Dashboard", layout="wide") # Header with date filter col1, col2 = st.columns([3, 1]) with col1: st.title("Executive Dashboard") with col2: date_range = st.selectbox( "Period", ["Last 7 Days", "Last 30 Days", "Last Quarter", "YTD"] ) # KPI Cards def metric_card(label, value, delta, prefix="", suffix=""): delta_color = "green" if delta >= 0 else "red" delta_arrow = "▲" if delta >= 0 else "▼" st.metric( label=label, value=f"{prefix}{value:,.0f}{suffix}", delta=f"{delta_arrow} {abs(delta):.1f}%" ) col1, col2, col3, col4 = st.columns(4) with col1: metric_card("Revenue", 2400000, 12.5, prefix="$") with col2: metric_card("Customers", 12450, 15.2) with col3: metric_card("NPS Score", 72, 5.0) with col4: metric_card("Churn Rate", 4.2, -0.8, suffix="%") # Charts col1, col2 = st.columns(2) with col1: st.subheader("Revenue Trend") revenue_data = pd.DataFrame({ 'Month': pd.date_range('2024-01-01', periods=12, freq='M'), 'Revenue': [180000, 195000, 210000, 225000, 240000, 255000, 270000, 285000, 300000, 315000, 330000, 345000] }) fig = px.line(revenue_data, x='Month', y='Revenue', line_shape='spline', markers=True) fig.update_layout(height=300) st.plotly_chart(fig, use_container_width=True) with col2: st.subheader("Revenue by Product") product_data = pd.DataFrame({ 'Product': ['Enterprise', 'Professional', 'Starter', 'Other'], 'Revenue': [45, 32, 18, 5] }) fig = px.pie(product_data, values='Revenue', names='Product', hole=0.4) fig.update_layout(height=300) st.plotly_chart(fig, use_container_width=True) # Cohort Heatmap st.subheader("Cohort Retention") cohort_data = pd.DataFrame({ 'Cohort': ['Jan', 'Feb', 'Mar', 'Apr', 'May'], 'M0': [100, 100, 100, 100, 100], 'M1': [85, 87, 84, 86, 88], 'M2': [78, 80, 76, 79, None], 'M3': [72, 74, 70, None, None], 'M4': [68, 70, None, None, None], }) fig = go.Figure(data=go.Heatmap( z=cohort_data.iloc[:, 1:].values, x=['M0', 'M1', 'M2', 'M3', 'M4'], y=cohort_data['Cohort'], colorscale='Blues', text=cohort_data.iloc[:, 1:].values, texttemplate='%{text}%', textfont={"size": 12}, )) fig.update_layout(height=250) st.plotly_chart(fig, use_container_width=True) # Alerts Section st.subheader("Alerts") alerts = [ {"level": "error", "message": "Churn rate exceeded threshold (>5%)"}, {"level": "warning", "message": "Support ticket volume 20% above average"}, ] for alert in alerts: if alert["level"] == "error": st.error(f"🔴 {alert['message']}") elif alert["level"] == "warning": st.warning(f"🟡 {alert['message']}") ``` ## Best Practices ### Do's - **Limit to 5-7 KPIs** - Focus on what matters - **Show context** - Comparisons, trends, targets - **Use consistent colors** - Red=bad, green=good - **Enable drilldown** - From summary to detail - **Update appropriately** - Match metric frequency ### Don'ts - **Don't show vanity metrics** - Focus on actionable data - **Don't overcrowd** - White space aids comprehension - **Don't use 3D charts** - They distort perception - **Don't hide methodology** - Document calculations - **Don't ignore mobile** - Ensure responsive design ## Resources - [Stephen Few's Dashboard Design](https://www.perceptualedge.com/articles/visual_business_intelligence/rules_for_using_color.pdf) - [Edward Tufte's Principles](https://www.edwardtufte.com/tufte/) - [Google Data Studio Gallery](https://datastudio.google.com/gallery)

# Context-Driven Development Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project documentation. ## When to Use This Skill - Setting up new projects with Conductor - Understanding the relationship between context artifacts - Maintaining consistency across AI-assisted development sessions - Onboarding team members to an existing Conductor project - Deciding when to update context documents - Managing greenfield vs brownfield project contexts ## Core Philosophy Context-Driven Development treats project context as a first-class artifact managed alongside code. Instead of relying on ad-hoc prompts or scattered documentation, establish a persistent, structured foundation that informs all AI interactions. Key principles: 1. **Context precedes code**: Define what you're building and how before implementation 2. **Living documentation**: Context artifacts evolve with the project 3. **Single source of truth**: One canonical location for each type of information 4. **AI alignment**: Consistent context produces consistent AI behavior ## The Workflow Follow the **Context → Spec & Plan → Implement** workflow: 1. **Context Phase**: Establish or verify project context artifacts exist and are current 2. **Specification Phase**: Define requirements and acceptance criteria for work units 3. **Planning Phase**: Break specifications into phased, actionable tasks 4. **Implementation Phase**: Execute tasks following established workflow patterns ## Artifact Relationships ### product.md - Defines WHAT and WHY Purpose: Captures product vision, goals, target users, and business context. Contents: - Product name and one-line description - Problem statement and solution approach - Target user personas - Core features and capabilities - Success metrics and KPIs - Product roadmap (high-level) Update when: - Product vision or goals change - New major features are planned - Target audience shifts - Business priorities evolve ### product-guidelines.md - Defines HOW to Communicate Purpose: Establishes brand voice, messaging standards, and communication patterns. Contents: - Brand voice and tone guidelines - Terminology and glossary - Error message conventions - User-facing copy standards - Documentation style Update when: - Brand guidelines change - New terminology is introduced - Communication patterns need refinement ### tech-stack.md - Defines WITH WHAT Purpose: Documents technology choices, dependencies, and architectural decisions. Contents: - Primary languages and frameworks - Key dependencies with versions - Infrastructure and deployment targets - Development tools and environment - Testing frameworks - Code quality tools Update when: - Adding new dependencies - Upgrading major versions - Changing infrastructure - Adopting new tools or patterns ### workflow.md - Defines HOW to Work Purpose: Establishes development practices, quality gates, and team workflows. Contents: - Development methodology (TDD, etc.) - Git workflow and commit conventions - Code review requirements - Testing requirements and coverage targets - Quality assurance gates - Deployment procedures Update when: - Team practices evolve - Quality standards change - New workflow patterns are adopted ### tracks.md - Tracks WHAT'S HAPPENING Purpose: Registry of all work units with status and metadata. Contents: - Active tracks with current status - Completed tracks with completion dates - Track metadata (type, priority, assignee) - Links to individual track directories Update when: - New tracks are created - Track status changes - Tracks are completed or archived See [references/artifact-templates.md](references/artifact-templates.md) for copy-paste starter templates. ## Context Maintenance Principles ### Keep Artifacts Synchronized Ensure changes in one artifact reflect in related documents: - New feature in product.md → Update tech-stack.md if new dependencies needed - Completed track → Update product.md to reflect new capabilities - Workflow change → Update all affected track plans ### Update tech-stack.md When Adding Dependencies Before adding any new dependency: 1. Check if existing dependencies solve the need 2. Document the rationale for new dependencies 3. Add version constraints 4. Note any configuration requirements ### Update product.md When Features Complete After completing a feature track: 1. Move feature from "planned" to "implemented" in product.md 2. Update any affected success metrics 3. Document any scope changes from original plan ### Verify Context Before Implementation Before starting any track: 1. Read all context artifacts 2. Flag any outdated information 3. Propose updates before proceeding 4. Confirm context accuracy with stakeholders ## Greenfield vs Brownfield Handling ### Greenfield Projects (New) For new projects: 1. Run `/conductor:setup` to create all artifacts interactively 2. Answer questions about product vision, tech preferences, and workflow 3. Generate initial style guides for chosen languages 4. Create empty tracks registry Characteristics: - Full control over context structure - Define standards before code exists - Establish patterns early ### Brownfield Projects (Existing) For existing codebases: 1. Run `/conductor:setup` with existing codebase detection 2. System analyzes existing code, configs, and documentation 3. Pre-populate artifacts based on discovered patterns 4. Review and refine generated context Characteristics: - Extract implicit context from existing code - Reconcile existing patterns with desired patterns - Document technical debt and modernization plans - Preserve working patterns while establishing standards ## Benefits ### Team Alignment - New team members onboard faster with explicit context - Consistent terminology and conventions across the team - Shared understanding of product goals and technical decisions ### AI Consistency - AI assistants produce aligned outputs across sessions - Reduced need to re-explain context in each interaction - Predictable behavior based on documented standards ### Institutional Memory - Decisions and rationale are preserved - Context survives team changes - Historical context informs future decisions ### Quality Assurance - Standards are explicit and verifiable - Deviations from context are detectable - Quality gates are documented and enforceable ## Directory Structure ``` conductor/ ├── index.md # Navigation hub linking all artifacts ├── product.md # Product vision and goals ├── product-guidelines.md # Communication standards ├── tech-stack.md # Technology preferences ├── workflow.md # Development practices ├── tracks.md # Work unit registry ├── setup_state.json # Resumable setup state ├── code_styleguides/ # Language-specific conventions │ ├── python.md │ ├── typescript.md │ └── ... └── tracks/ └── <track-id>/ ├── spec.md ├── plan.md ├── metadata.json └── index.md ``` ## Context Lifecycle 1. **Creation**: Initial setup via `/conductor:setup` 2. **Validation**: Verify before each track 3. **Evolution**: Update as project grows 4. **Synchronization**: Keep artifacts aligned 5. **Archival**: Document historical decisions ## Context Validation Checklist Before starting implementation on any track, validate context: ### Product Context - [ ] product.md reflects current product vision - [ ] Target users are accurately described - [ ] Feature list is up to date - [ ] Success metrics are defined ### Technical Context - [ ] tech-stack.md lists all current dependencies - [ ] Version numbers are accurate - [ ] Infrastructure targets are correct - [ ] Development tools are documented ### Workflow Context - [ ] workflow.md describes current practices - [ ] Quality gates are defined - [ ] Coverage targets are specified - [ ] Commit conventions are documented ### Track Context - [ ] tracks.md shows all active work - [ ] No stale or abandoned tracks - [ ] Dependencies between tracks are noted ## Common Anti-Patterns Avoid these context management mistakes: ### Stale Context Problem: Context documents become outdated and misleading. Solution: Update context as part of each track's completion process. ### Context Sprawl Problem: Information scattered across multiple locations. Solution: Use the defined artifact structure; resist creating new document types. ### Implicit Context Problem: Relying on knowledge not captured in artifacts. Solution: If you reference something repeatedly, add it to the appropriate artifact. ### Context Hoarding Problem: One person maintains context without team input. Solution: Review context artifacts in pull requests; make updates collaborative. ### Over-Specification Problem: Context becomes so detailed it's impossible to maintain. Solution: Keep artifacts focused on decisions that affect AI behavior and team alignment. ## Integration with Development Tools ### IDE Integration Configure your IDE to display context files prominently: - Pin conductor/product.md for quick reference - Add tech-stack.md to project notes - Create snippets for common patterns from style guides ### Git Hooks Consider pre-commit hooks that: - Warn when dependencies change without tech-stack.md update - Remind to update product.md when feature branches merge - Validate context artifact syntax ### CI/CD Integration Include context validation in pipelines: - Check tech-stack.md matches actual dependencies - Verify links in context documents resolve - Ensure tracks.md status matches git branch state ## Session Continuity Conductor supports multi-session development through context persistence: ### Starting a New Session 1. Read index.md to orient yourself 2. Check tracks.md for active work 3. Review relevant track's plan.md for current task 4. Verify context artifacts are current ### Ending a Session 1. Update plan.md with current progress 2. Note any blockers or decisions made 3. Commit in-progress work with clear status 4. Update tracks.md if status changed ### Handling Interruptions If interrupted mid-task: 1. Mark task as `[~]` with note about stopping point 2. Commit work-in-progress to feature branch 3. Document any uncommitted decisions in plan.md ## Best Practices 1. **Read context first**: Always read relevant artifacts before starting work 2. **Small updates**: Make incremental context changes, not massive rewrites 3. **Link decisions**: Reference context when making implementation choices 4. **Version context**: Commit context changes alongside code changes 5. **Review context**: Include context artifact reviews in code reviews 6. **Validate regularly**: Run context validation checklist before major work 7. **Communicate changes**: Notify team when context artifacts change significantly 8. **Preserve history**: Use git to track context evolution over time 9. **Question staleness**: If context feels wrong, investigate and update 10. **Keep it actionable**: Every context item should inform a decision or behavior

# Prompt Engineering Patterns Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability. ## When to Use This Skill - Designing complex prompts for production LLM applications - Optimizing prompt performance and consistency - Implementing structured reasoning patterns (chain-of-thought, tree-of-thought) - Building few-shot learning systems with dynamic example selection - Creating reusable prompt templates with variable interpolation - Debugging and refining prompts that produce inconsistent outputs - Implementing system prompts for specialized AI assistants - Using structured outputs (JSON mode) for reliable parsing ## Core Capabilities ### 1. Few-Shot Learning - Example selection strategies (semantic similarity, diversity sampling) - Balancing example count with context window constraints - Constructing effective demonstrations with input-output pairs - Dynamic example retrieval from knowledge bases - Handling edge cases through strategic example selection ### 2. Chain-of-Thought Prompting - Step-by-step reasoning elicitation - Zero-shot CoT with "Let's think step by step" - Few-shot CoT with reasoning traces - Self-consistency techniques (sampling multiple reasoning paths) - Verification and validation steps ### 3. Structured Outputs - JSON mode for reliable parsing - Pydantic schema enforcement - Type-safe response handling - Error handling for malformed outputs ### 4. Prompt Optimization - Iterative refinement workflows - A/B testing prompt variations - Measuring prompt performance metrics (accuracy, consistency, latency) - Reducing token usage while maintaining quality - Handling edge cases and failure modes ### 5. Template Systems - Variable interpolation and formatting - Conditional prompt sections - Multi-turn conversation templates - Role-based prompt composition - Modular prompt components ### 6. System Prompt Design - Setting model behavior and constraints - Defining output formats and structure - Establishing role and expertise - Safety guidelines and content policies - Context setting and background information ## Quick Start ```python from langchain_anthropic import ChatAnthropic from langchain_core.prompts import ChatPromptTemplate from pydantic import BaseModel, Field # Define structured output schema class SQLQuery(BaseModel): query: str = Field(description="The SQL query") explanation: str = Field(description="Brief explanation of what the query does") tables_used: list[str] = Field(description="List of tables referenced") # Initialize model with structured output llm = ChatAnthropic(model="claude-sonnet-4-6") structured_llm = llm.with_structured_output(SQLQuery) # Create prompt template prompt = ChatPromptTemplate.from_messages([ ("system", """You are an expert SQL developer. Generate efficient, secure SQL queries. Always use parameterized queries to prevent SQL injection. Explain your reasoning briefly."""), ("user", "Convert this to SQL: {query}") ]) # Create chain chain = prompt | structured_llm # Use result = await chain.ainvoke({ "query": "Find all users who registered in the last 30 days" }) print(result.query) print(result.explanation) ``` ## Key Patterns ### Pattern 1: Structured Output with Pydantic ```python from anthropic import Anthropic from pydantic import BaseModel, Field from typing import Literal import json class SentimentAnalysis(BaseModel): sentiment: Literal["positive", "negative", "neutral"] confidence: float = Field(ge=0, le=1) key_phrases: list[str] reasoning: str async def analyze_sentiment(text: str) -> SentimentAnalysis: """Analyze sentiment with structured output.""" client = Anthropic() message = client.messages.create( model="claude-sonnet-4-6", max_tokens=500, messages=[{ "role": "user", "content": f"""Analyze the sentiment of this text. Text: {text} Respond with JSON matching this schema: {{ "sentiment": "positive" | "negative" | "neutral", "confidence": 0.0-1.0, "key_phrases": ["phrase1", "phrase2"], "reasoning": "brief explanation" }}""" }] ) return SentimentAnalysis(**json.loads(message.content[0].text)) ``` ### Pattern 2: Chain-of-Thought with Self-Verification ```python from langchain_core.prompts import ChatPromptTemplate cot_prompt = ChatPromptTemplate.from_template(""" Solve this problem step by step. Problem: {problem} Instructions: 1. Break down the problem into clear steps 2. Work through each step showing your reasoning 3. State your final answer 4. Verify your answer by checking it against the original problem Format your response as: ## Steps [Your step-by-step reasoning] ## Answer [Your final answer] ## Verification [Check that your answer is correct] """) ``` ### Pattern 3: Few-Shot with Dynamic Example Selection ```python from langchain_voyageai import VoyageAIEmbeddings from langchain_core.example_selectors import SemanticSimilarityExampleSelector from langchain_chroma import Chroma # Create example selector with semantic similarity example_selector = SemanticSimilarityExampleSelector.from_examples( examples=[ {"input": "How do I reset my password?", "output": "Go to Settings > Security > Reset Password"}, {"input": "Where can I see my order history?", "output": "Navigate to Account > Orders"}, {"input": "How do I contact support?", "output": "Click Help > Contact Us or email support@example.com"}, ], embeddings=VoyageAIEmbeddings(model="voyage-3-large"), vectorstore_cls=Chroma, k=2 # Select 2 most similar examples ) async def get_few_shot_prompt(query: str) -> str: """Build prompt with dynamically selected examples.""" examples = await example_selector.aselect_examples({"input": query}) examples_text = "\n".join( f"User: {ex['input']}\nAssistant: {ex['output']}" for ex in examples ) return f"""You are a helpful customer support assistant. Here are some example interactions: {examples_text} Now respond to this query: User: {query} Assistant:""" ``` ### Pattern 4: Progressive Disclosure Start with simple prompts, add complexity only when needed: ```python PROMPT_LEVELS = { # Level 1: Direct instruction "simple": "Summarize this article: {text}", # Level 2: Add constraints "constrained": """Summarize this article in 3 bullet points, focusing on: - Key findings - Main conclusions - Practical implications Article: {text}""", # Level 3: Add reasoning "reasoning": """Read this article carefully. 1. First, identify the main topic and thesis 2. Then, extract the key supporting points 3. Finally, summarize in 3 bullet points Article: {text} Summary:""", # Level 4: Add examples "few_shot": """Read articles and provide concise summaries. Example: Article: "New research shows that regular exercise can reduce anxiety by up to 40%..." Summary: • Regular exercise reduces anxiety by up to 40% • 30 minutes of moderate activity 3x/week is sufficient • Benefits appear within 2 weeks of starting Now summarize this article: Article: {text} Summary:""" } ``` ### Pattern 5: Error Recovery and Fallback ```python from pydantic import BaseModel, ValidationError import json class ResponseWithConfidence(BaseModel): answer: str confidence: float sources: list[str] alternative_interpretations: list[str] = [] ERROR_RECOVERY_PROMPT = """ Answer the question based on the context provided. Context: {context} Question: {question} Instructions: 1. If you can answer confidently (>0.8), provide a direct answer 2. If you're somewhat confident (0.5-0.8), provide your best answer with caveats 3. If you're uncertain (<0.5), explain what information is missing 4. Always provide alternative interpretations if the question is ambiguous Respond in JSON: {{ "answer": "your answer or 'I cannot determine this from the context'", "confidence": 0.0-1.0, "sources": ["relevant context excerpts"], "alternative_interpretations": ["if question is ambiguous"] }} """ async def answer_with_fallback( context: str, question: str, llm ) -> ResponseWithConfidence: """Answer with error recovery and fallback.""" prompt = ERROR_RECOVERY_PROMPT.format(context=context, question=question) try: response = await llm.ainvoke(prompt) return ResponseWithConfidence(**json.loads(response.content)) except (json.JSONDecodeError, ValidationError) as e: # Fallback: try to extract answer without structure simple_prompt = f"Based on: {context}\n\nAnswer: {question}" simple_response = await llm.ainvoke(simple_prompt) return ResponseWithConfidence( answer=simple_response.content, confidence=0.5, sources=["fallback extraction"], alternative_interpretations=[] ) ``` ### Pattern 6: Role-Based System Prompts ```python SYSTEM_PROMPTS = { "analyst": """You are a senior data analyst with expertise in SQL, Python, and business intelligence. Your responsibilities: - Write efficient, well-documented queries - Explain your analysis methodology - Highlight key insights and recommendations - Flag any data quality concerns Communication style: - Be precise and technical when discussing methodology - Translate technical findings into business impact - Use clear visualizations when helpful""", "assistant": """You are a helpful AI assistant focused on accuracy and clarity. Core principles: - Always cite sources when making factual claims - Acknowledge uncertainty rather than guessing - Ask clarifying questions when the request is ambiguous - Provide step-by-step explanations for complex topics Constraints: - Do not provide medical, legal, or financial advice - Redirect harmful requests appropriately - Protect user privacy""", "code_reviewer": """You are a senior software engineer conducting code reviews. Review criteria: - Correctness: Does the code work as intended? - Security: Are there any vulnerabilities? - Performance: Are there efficiency concerns? - Maintainability: Is the code readable and well-structured? - Best practices: Does it follow language idioms? Output format: 1. Summary assessment (approve/request changes) 2. Critical issues (must fix) 3. Suggestions (nice to have) 4. Positive feedback (what's done well)""" } ``` ## Integration Patterns ### With RAG Systems ```python RAG_PROMPT = """You are a knowledgeable assistant that answers questions based on provided context. Context (retrieved from knowledge base): {context} Instructions: 1. Answer ONLY based on the provided context 2. If the context doesn't contain the answer, say "I don't have information about that in my knowledge base" 3. Cite specific passages using [1], [2] notation 4. If the question is ambiguous, ask for clarification Question: {question} Answer:""" ``` ### With Validation and Verification ```python VALIDATED_PROMPT = """Complete the following task: Task: {task} After generating your response, verify it meets ALL these criteria: ✓ Directly addresses the original request ✓ Contains no factual errors ✓ Is appropriately detailed (not too brief, not too verbose) ✓ Uses proper formatting ✓ Is safe and appropriate If verification fails on any criterion, revise before responding. Response:""" ``` ## Performance Optimization ### Token Efficiency ```python # Before: Verbose prompt (150+ tokens) verbose_prompt = """ I would like you to please take the following text and provide me with a comprehensive summary of the main points. The summary should capture the key ideas and important details while being concise and easy to understand. """ # After: Concise prompt (30 tokens) concise_prompt = """Summarize the key points concisely: {text} Summary:""" ``` ### Caching Common Prefixes ```python from anthropic import Anthropic client = Anthropic() # Use prompt caching for repeated system prompts response = client.messages.create( model="claude-sonnet-4-6", max_tokens=1000, system=[ { "type": "text", "text": LONG_SYSTEM_PROMPT, "cache_control": {"type": "ephemeral"} } ], messages=[{"role": "user", "content": user_query}] ) ``` ## Best Practices 1. **Be Specific**: Vague prompts produce inconsistent results 2. **Show, Don't Tell**: Examples are more effective than descriptions 3. **Use Structured Outputs**: Enforce schemas with Pydantic for reliability 4. **Test Extensively**: Evaluate on diverse, representative inputs 5. **Iterate Rapidly**: Small changes can have large impacts 6. **Monitor Performance**: Track metrics in production 7. **Version Control**: Treat prompts as code with proper versioning 8. **Document Intent**: Explain why prompts are structured as they are ## Common Pitfalls - **Over-engineering**: Starting with complex prompts before trying simple ones - **Example pollution**: Using examples that don't match the target task - **Context overflow**: Exceeding token limits with excessive examples - **Ambiguous instructions**: Leaving room for multiple interpretations - **Ignoring edge cases**: Not testing on unusual or boundary inputs - **No error handling**: Assuming outputs will always be well-formed - **Hardcoded values**: Not parameterizing prompts for reuse ## Success Metrics Track these KPIs for your prompts: - **Accuracy**: Correctness of outputs - **Consistency**: Reproducibility across similar inputs - **Latency**: Response time (P50, P95, P99) - **Token Usage**: Average tokens per request - **Success Rate**: Percentage of valid, parseable outputs - **User Satisfaction**: Ratings and feedback ## Resources - [Anthropic Prompt Engineering Guide](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering) - [Claude Prompt Caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching) - [OpenAI Prompt Engineering](https://platform.openai.com/docs/guides/prompt-engineering) - [LangChain Prompts](https://python.langchain.com/docs/concepts/prompts/)

# Grafana Dashboards Create and manage production-ready Grafana dashboards for comprehensive system observability. ## Purpose Design effective Grafana dashboards for monitoring applications, infrastructure, and business metrics. ## When to Use - Visualize Prometheus metrics - Create custom dashboards - Implement SLO dashboards - Monitor infrastructure - Track business KPIs ## Dashboard Design Principles ### 1. Hierarchy of Information ``` ┌─────────────────────────────────────┐ │ Critical Metrics (Big Numbers) │ ├─────────────────────────────────────┤ │ Key Trends (Time Series) │ ├─────────────────────────────────────┤ │ Detailed Metrics (Tables/Heatmaps) │ └─────────────────────────────────────┘ ``` ### 2. RED Method (Services) - **Rate** - Requests per second - **Errors** - Error rate - **Duration** - Latency/response time ### 3. USE Method (Resources) - **Utilization** - % time resource is busy - **Saturation** - Queue length/wait time - **Errors** - Error count ## Dashboard Structure ### API Monitoring Dashboard ```json { "dashboard": { "title": "API Monitoring", "tags": ["api", "production"], "timezone": "browser", "refresh": "30s", "panels": [ { "title": "Request Rate", "type": "graph", "targets": [ { "expr": "sum(rate(http_requests_total[5m])) by (service)", "legendFormat": "{{service}}" } ], "gridPos": { "x": 0, "y": 0, "w": 12, "h": 8 } }, { "title": "Error Rate %", "type": "graph", "targets": [ { "expr": "(sum(rate(http_requests_total{status=~\"5..\"}[5m])) / sum(rate(http_requests_total[5m]))) * 100", "legendFormat": "Error Rate" } ], "alert": { "conditions": [ { "evaluator": { "params": [5], "type": "gt" }, "operator": { "type": "and" }, "query": { "params": ["A", "5m", "now"] }, "type": "query" } ] }, "gridPos": { "x": 12, "y": 0, "w": 12, "h": 8 } }, { "title": "P95 Latency", "type": "graph", "targets": [ { "expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le, service))", "legendFormat": "{{service}}" } ], "gridPos": { "x": 0, "y": 8, "w": 24, "h": 8 } } ] } } ``` **Reference:** See `assets/api-dashboard.json` ## Panel Types ### 1. Stat Panel (Single Value) ```json { "type": "stat", "title": "Total Requests", "targets": [ { "expr": "sum(http_requests_total)" } ], "options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"] }, "orientation": "auto", "textMode": "auto", "colorMode": "value" }, "fieldConfig": { "defaults": { "thresholds": { "mode": "absolute", "steps": [ { "value": 0, "color": "green" }, { "value": 80, "color": "yellow" }, { "value": 90, "color": "red" } ] } } } } ``` ### 2. Time Series Graph ```json { "type": "graph", "title": "CPU Usage", "targets": [ { "expr": "100 - (avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)" } ], "yaxes": [ { "format": "percent", "max": 100, "min": 0 }, { "format": "short" } ] } ``` ### 3. Table Panel ```json { "type": "table", "title": "Service Status", "targets": [ { "expr": "up", "format": "table", "instant": true } ], "transformations": [ { "id": "organize", "options": { "excludeByName": { "Time": true }, "indexByName": {}, "renameByName": { "instance": "Instance", "job": "Service", "Value": "Status" } } } ] } ``` ### 4. Heatmap ```json { "type": "heatmap", "title": "Latency Heatmap", "targets": [ { "expr": "sum(rate(http_request_duration_seconds_bucket[5m])) by (le)", "format": "heatmap" } ], "dataFormat": "tsbuckets", "yAxis": { "format": "s" } } ``` ## Variables ### Query Variables ```json { "templating": { "list": [ { "name": "namespace", "type": "query", "datasource": "Prometheus", "query": "label_values(kube_pod_info, namespace)", "refresh": 1, "multi": false }, { "name": "service", "type": "query", "datasource": "Prometheus", "query": "label_values(kube_service_info{namespace=\"$namespace\"}, service)", "refresh": 1, "multi": true } ] } } ``` ### Use Variables in Queries ``` sum(rate(http_requests_total{namespace="$namespace", service=~"$service"}[5m])) ``` ## Alerts in Dashboards ```json { "alert": { "name": "High Error Rate", "conditions": [ { "evaluator": { "params": [5], "type": "gt" }, "operator": { "type": "and" }, "query": { "params": ["A", "5m", "now"] }, "reducer": { "type": "avg" }, "type": "query" } ], "executionErrorState": "alerting", "for": "5m", "frequency": "1m", "message": "Error rate is above 5%", "noDataState": "no_data", "notifications": [{ "uid": "slack-channel" }] } } ``` ## Dashboard Provisioning **dashboards.yml:** ```yaml apiVersion: 1 providers: - name: "default" orgId: 1 folder: "General" type: file disableDeletion: false updateIntervalSeconds: 10 allowUiUpdates: true options: path: /etc/grafana/dashboards ``` ## Common Dashboard Patterns ### Infrastructure Dashboard **Key Panels:** - CPU utilization per node - Memory usage per node - Disk I/O - Network traffic - Pod count by namespace - Node status **Reference:** See `assets/infrastructure-dashboard.json` ### Database Dashboard **Key Panels:** - Queries per second - Connection pool usage - Query latency (P50, P95, P99) - Active connections - Database size - Replication lag - Slow queries **Reference:** See `assets/database-dashboard.json` ### Application Dashboard **Key Panels:** - Request rate - Error rate - Response time (percentiles) - Active users/sessions - Cache hit rate - Queue length ## Best Practices 1. **Start with templates** (Grafana community dashboards) 2. **Use consistent naming** for panels and variables 3. **Group related metrics** in rows 4. **Set appropriate time ranges** (default: Last 6 hours) 5. **Use variables** for flexibility 6. **Add panel descriptions** for context 7. **Configure units** correctly 8. **Set meaningful thresholds** for colors 9. **Use consistent colors** across dashboards 10. **Test with different time ranges** ## Dashboard as Code ### Terraform Provisioning ```hcl resource "grafana_dashboard" "api_monitoring" { config_json = file("${path.module}/dashboards/api-monitoring.json") folder = grafana_folder.monitoring.id } resource "grafana_folder" "monitoring" { title = "Production Monitoring" } ``` ### Ansible Provisioning ```yaml - name: Deploy Grafana dashboards copy: src: "{{ item }}" dest: /etc/grafana/dashboards/ with_fileglob: - "dashboards/*.json" notify: restart grafana ``` ## Reference Files - `assets/api-dashboard.json` - API monitoring dashboard - `assets/infrastructure-dashboard.json` - Infrastructure dashboard - `assets/database-dashboard.json` - Database monitoring dashboard - `references/dashboard-design.md` - Dashboard design guide ## Related Skills - `prometheus-configuration` - For metric collection - `slo-implementation` - For SLO dashboards