diff --git a/agents/30-days-of-agents/day-11.mdx b/agents/30-days-of-agents/day-11.mdx new file mode 100644 index 00000000..b73413e0 --- /dev/null +++ b/agents/30-days-of-agents/day-11.mdx @@ -0,0 +1,216 @@ +--- +title: "Day 11: Finance & Revenue Operations - Stripe Integration" +sidebarTitle: "Day 11: Stripe Integration" +description: + "Build a revenue operations agent that monitors payments, analyzes + subscription metrics, and provides financial insights through Stripe + integration." +--- + + + **Goal**: create a revenue operations agent with Stripe integration + +**Theme**: domain specialization week - financial intelligence + +**Time investment**: ~20 minutes + + + +Welcome to Day 11 and Week 3! You've mastered agent creation and workflows. Now +you'll specialize in **domain-specific agents**—starting with finance and +revenue operations through Stripe integration. + +This week is about building agents that don't just use tools, but understand the +business context and best practices of specific domains. + +## What you'll accomplish today + +- Build a revenue operations agent that understands financial workflows +- Connect Stripe for payment and subscription intelligence +- Create automated revenue reporting and customer insights +- Learn domain-specific patterns for financial agents + + + This builds on your Week 2 agent creation skills. You'll need a Stripe account + with appropriate permissions to complete today's integration. + + +## Step 1: Understanding revenue agent patterns + +Financial agents need specialized knowledge beyond basic tool usage: + +### Domain expertise requirements + +Revenue agents must understand: + +- **Financial metrics**: MRR, churn, LTV, CAC, and their relationships +- **Customer lifecycle**: Trial → paid → expansion → renewal patterns +- **Risk indicators**: Failed payments, cancellations, downgrades +- **Compliance needs**: Data privacy, financial reporting requirements + + + **Domain thinking** your agent should reason like a revenue operations + manager, not just fetch Stripe data. + + +## Step 2: Create your revenue operations agent + +Work with Concierge to build a specialized financial agent: + +```text +I want to create a revenue operations agent that monitors our Stripe payments and subscriptions. + +The agent should: +- Track key revenue metrics (MRR, churn, new vs expansion revenue) +- Identify at-risk customers based on payment patterns +- Generate weekly revenue reports with insights +- Alert on significant revenue events (large cancellations, payment failures) +- Provide customer health scores based on payment history + +It should think like a revenue operations manager who understands SaaS metrics. +``` + +## Step 3: Connect and configure Stripe + +Add Stripe to your agent's connections: + +1. **Navigate to Connections** in your agent settings +2. **Search for Stripe** and click "Add Connection" +3. **Authenticate** with your Stripe account +4. **Select appropriate permissions** (read access to payments, customers, + subscriptions) + +### Key Stripe capabilities for revenue agents + +Your agent can now: + +- **Analyze payment data**: Success rates, failure reasons, retry patterns +- **Monitor subscriptions**: New, upgraded, downgraded, cancelled +- **Track customer behavior**: Payment methods, billing cycles, usage patterns +- **Generate insights**: Revenue trends, cohort analysis, forecasting + +## Step 4: Implement revenue intelligence workflows + +Test your agent with real revenue scenarios: + +```text +Can you analyze our revenue performance this month and identify any concerning trends? +``` + +Your agent should: + +- Pull current month's transaction data from Stripe +- Calculate key metrics (MRR, churn rate, growth rate) +- Identify anomalies or concerning patterns +- Provide actionable recommendations + +### Example revenue analysis + +```text +What's our current MRR and how has it changed this quarter? +Which customers are at risk of churning? +``` + +The agent analyzes: + +- **MRR trends**: Current MRR, growth rate, net new vs expansion +- **Churn indicators**: Failed payments, downgrades, usage decline +- **Customer health**: Payment reliability, engagement, upgrade potential +- **Action items**: Customers needing attention, upsell opportunities + +## Step 5: Create automated revenue workflows + +Build repeatable revenue tasks: + + + **Coming soon** daily and weekly scheduled tasks. For now, you'll need to + interact with your agent through the UI to run these workflows. + + +**Weekly revenue report**: + +```text +Can you analyze last week's revenue performance including: +- New vs lost MRR +- Payment failure rate and recovery +- Top customers by revenue +- Churn risk assessment +- Week-over-week comparison + +Format as an executive summary with key metrics and action items. +``` + +**Customer health monitoring**: + +```text +Can you check for: +- Failed payments needing attention +- Customers with multiple failed attempts +- Sudden usage drops indicating churn risk +- Opportunities for upgrades based on usage + +Alert me only for critical issues needing immediate action. +``` + + + **Pro tip** set calendar reminders to run your revenue report weekly and + health checks daily until automated scheduling is available. + + +## What you've accomplished + +In 20 minutes, you've built a domain-specific revenue operations agent: + +**Financial intelligence** agent that understands revenue metrics and SaaS +business models + +**Stripe integration** connected payment and subscription data for real-time +insights + +**Manual workflows** revenue reporting and customer health monitoring that you +can run on-demand + +**Domain expertise** agent that thinks like a revenue operations manager, not +just a data fetcher + +## The power of domain-specific agents + +Unlike generic agents, domain-specific agents: + +- **Understand context**: Know what metrics matter and why +- **Identify patterns**: Recognize revenue risks before they become problems +- **Provide insights**: Actionable recommendations, not just data dumps +- **Automate expertise**: Scale revenue operations knowledge across your team + + + Development & infrastructure with GitHub and Vercel. Build agents that manage + code, deployments, and development workflows. + + +## Pro tip for today + +Ask your revenue agent: + +```text +Based on our payment patterns, what early warning signs should I watch for to prevent churn? +``` + +This helps your agent develop predictive capabilities specific to your business. + +--- + +**Time to complete** ~20 minutes + +**Skills learned** domain-specific agent design, Stripe integration, revenue +intelligence, automated financial workflows + +**Next** Day 12 - Development & infrastructure agents with GitHub and Vercel + + + **Remember** the best financial agents don't just report numbers—they + understand what those numbers mean for your business and what actions to take. + diff --git a/agents/30-days-of-agents/day-12.mdx b/agents/30-days-of-agents/day-12.mdx new file mode 100644 index 00000000..ccd7d164 --- /dev/null +++ b/agents/30-days-of-agents/day-12.mdx @@ -0,0 +1,382 @@ +--- +title: "Day 12: Development & Infrastructure - GitHub & Vercel Integration" +sidebarTitle: "Day 12: GitHub & Vercel" +description: + "Master development workflows by building agents that manage code + repositories, automate reviews, handle deployments, and coordinate production + releases with GitHub and Vercel." +--- + + + **Goal**: build sophisticated development agents that automate code reviews, manage deployments, and coordinate release workflows + +**Theme**: domain specialization week - development & infrastructure + +**Time investment**: ~30 minutes + + + +Welcome to Day 12! Today you'll specialize in development and infrastructure by +building agents that understand code, deployments, and development workflows. +You'll integrate GitHub for repository management and Vercel for deployment +automation, creating agents that act like senior DevOps engineers. + +This isn't just about connecting tools—it's about building agents that +understand development best practices, can review code intelligently, and manage +production deployments safely. + +## What you'll accomplish today + +- Build a development agent that combines GitHub and Vercel capabilities +- Create intelligent code review workflows that go beyond syntax checking +- Implement automated deployment pipelines with safety checks +- Develop monitoring and rollback capabilities for production systems +- Learn domain-specific patterns for development and infrastructure agents + + + This builds on your Week 2 agent creation skills. You'll need access to GitHub + and Vercel accounts with appropriate permissions to complete today's + exercises. + + +## Step 1: Understanding development agent patterns + +Before building, understand what makes development agents different from +general-purpose agents: + +### Code understanding capabilities + +Development agents need to: + +- **Analyze code quality** beyond just syntax—understanding patterns, security + implications, and performance +- **Understand project context** from README files, documentation, and code + structure +- **Follow coding standards** specific to languages, frameworks, and team + conventions +- **Assess risk levels** for changes based on file criticality and change scope + +### Deployment intelligence + +Infrastructure agents must: + +- **Coordinate deployments** across environments (development, staging, + production) +- **Monitor build status** and understand when deployments are safe +- **Implement rollback strategies** when issues are detected +- **Manage environment variables** and configuration securely + + + **Domain expertise matters** development agents need to understand not just + how to use GitHub and Vercel APIs, but when and why to use specific features + based on development best practices. + + +## Step 2: Create your development agent with Concierge + +Let's build a sophisticated development agent that combines code management and +deployment capabilities: + +**Start with Concierge:** + +```text +I want to create a development and infrastructure agent that helps me manage code reviews and deployments. + +The agent should: +- Review pull requests on GitHub for code quality, security issues, and best practices +- Manage deployments to Vercel with proper staging and production workflows +- Monitor deployment status and performance metrics +- Coordinate releases between code merges and deployments +- Provide intelligent insights about code changes and their potential impact + +I want it to act like a senior DevOps engineer who understands both code quality and production stability. +``` + +### Example agent configuration + +Based on the GitHub Review Bot example from the gallery, enhance your agent with +these capabilities: + +**Core responsibilities:** + +- Automated code review with actionable feedback +- Deployment coordination with safety checks +- Performance monitoring and alerting +- Release note generation +- Rollback automation when issues detected + +**Key integrations needed:** + +- **GitHub**: Repository access, PR management, issue tracking +- **Vercel**: Deployment management, environment configuration, monitoring +- **Slack** (optional): Team notifications for important events + +## Step 3: Implement intelligent code review workflows + +Your development agent should go beyond basic linting. Drawing from the GitHub +Review Bot example: + +**Configure advanced review capabilities:** + +```text +When reviewing pull requests, analyze: + +1. Code Quality Patterns: + - Clean code principles and readability + - DRY (Don't Repeat Yourself) violations + - Function complexity and refactoring opportunities + - Consistent naming conventions + +2. Security Analysis: + - Hardcoded secrets or API keys + - SQL injection vulnerabilities + - Cross-site scripting (XSS) risks + - Dependency vulnerabilities + +3. Performance Considerations: + - Database query optimization + - Memory leak potential + - Unnecessary re-renders (for React) + - Bundle size impact + +4. Testing Coverage: + - Missing test cases + - Edge case handling + - Integration test requirements + +Provide specific line numbers and code examples for all feedback. +Use severity levels: Critical, High, Medium, Low. +Always include positive feedback for well-written code sections. +``` + +### Example code review interaction + +```text +You: Review PR #142 in our main repository - it's adding a new authentication system. + +Agent: I've completed the review of PR #142 - "Implement OAuth 2.0 authentication system". Here's my analysis: + +**Overall Score: 8/10** + +**Critical Issues:** +• Line 45 in auth.js: Hardcoded client secret should be moved to environment variables +• Line 128 in middleware.js: Missing input validation for JWT tokens could lead to injection attacks + +**Security Recommendations:** +• Add rate limiting to login endpoints (auth.js:67-89) +• Implement refresh token rotation for enhanced security +• Consider adding PKCE flow for public clients + +**Performance Optimizations:** +• Token validation is happening on every request - implement caching (middleware.js:34) +• Database queries in getUserProfile() could be optimized with indexes + +**Positive Highlights:** +• Excellent test coverage at 94% +• Clean separation of auth and authorization logic +• Proper error handling without leaking sensitive info + +**Deployment Considerations:** +• Will need to update Vercel environment variables before deployment +• Database migrations required for refresh_tokens table +• Consider feature flag for gradual rollout + +Ready to proceed with deployment after addressing critical issues. +``` + +## Step 4: Automate deployment workflows with Vercel + +Now let's add sophisticated deployment capabilities: + +**Configure deployment intelligence:** + +```text +For deployment workflows, implement: + +1. Pre-deployment Checks: + - All CI/CD tests passing + - No critical security issues in code review + - Database migrations ready if needed + - Environment variables configured + +2. Staging Deployment First: + - Deploy to staging environment + - Run smoke tests automatically + - Check performance metrics + - Verify no errors in logs + +3. Production Deployment: + - Only after staging validation + - Implement canary or blue-green deployment + - Monitor error rates and performance + - Automatic rollback if error threshold exceeded + +4. Post-deployment Monitoring: + - Track Core Web Vitals + - Monitor error rates + - Check API response times + - Alert on anomalies +``` + +### Example deployment workflow + +```text +You: The PR has been approved. Deploy the authentication changes to production. + +Agent: I'll coordinate the deployment of the authentication system to production. Let me start with our safety checks: + +**Pre-deployment Validation:** +✅ All GitHub Actions tests passing (last run: 2 minutes ago) +✅ Critical security issues from code review have been addressed +✅ PR #142 merged to main branch +✅ Vercel preview deployment successful + +**Staging Deployment:** +Deploying to staging environment... +✅ Deployment successful: https://app-staging.vercel.app +✅ Running automated smoke tests... + - Login flow: PASS (avg 230ms) + - Token refresh: PASS (avg 145ms) + - Logout flow: PASS (avg 89ms) +✅ No errors in staging logs (monitored for 5 minutes) + +**Production Deployment Plan:** +I'll use a canary deployment strategy: +1. Deploy to 10% of traffic first +2. Monitor for 15 minutes +3. If metrics are stable, deploy to 100% + +Shall I proceed with the canary deployment to production? + +[After confirmation] + +**Production Deployment Progress:** +🚀 Deploying to production (10% canary)... +✅ Canary deployment live +📊 Monitoring metrics for 15 minutes... + - Error rate: 0.01% (baseline: 0.02%) ✅ + - Response time: 122ms (baseline: 118ms) ✅ + - CPU usage: 34% (baseline: 32%) ✅ + +All metrics look healthy. Promoting to 100% traffic... +✅ Full production deployment complete! + +**Deployment Summary:** +- URL: https://app.vercel.app +- Build ID: dpl_Fk3j2k4j2k3j4 +- Duration: 18 minutes total +- Features: OAuth 2.0 authentication system + +**Next Steps:** +1. Monitor error rates for next 24 hours +2. Review user feedback on new auth flow +3. Plan gradual feature flag rollout for existing users + +I'll continue monitoring and alert you if any issues arise. +``` + +## Step 5: Create development best practices automation + +Extend your agent to enforce and automate development best practices: + +**Advanced automation patterns:** + +```text +Implement these automated workflows: + +1. Dependency Management: + - Weekly dependency update PRs + - Security vulnerability scanning + - Breaking change detection + - Automated testing of updates + +2. Documentation Sync: + - Update API docs when endpoints change + - Generate changelog from PR descriptions + - Keep README synchronized with actual setup + - Create architecture diagrams from code + +3. Performance Budget Enforcement: + - Block deployments exceeding bundle size limits + - Warn on significant performance regressions + - Track and report Core Web Vitals trends + - Suggest optimization opportunities + +4. Release Coordination: + - Generate release notes from merged PRs + - Coordinate database migrations with deployments + - Manage feature flags for gradual rollouts + - Schedule deployments for optimal times +``` + +## What you've accomplished + +In 30 minutes, you've built a sophisticated development and infrastructure agent +that: + +**Code intelligence** reviews code with understanding of quality, security, and +performance implications beyond basic syntax + +**Deployment orchestration** manages complex deployment workflows with staging +validation, canary releases, and automatic rollbacks + +**Production monitoring** tracks system health, detects anomalies, and takes +corrective action when needed + +**Best practices automation** enforces development standards, manages +dependencies, and coordinates releases + +**Domain expertise** acts like a senior DevOps engineer, understanding not just +how to use tools but when and why + +## The power of domain-specific development agents + +Development agents that truly understand code and infrastructure can: + +**Reduce deployment risk** catch issues before they reach production through +intelligent analysis + +**Accelerate development** automate repetitive tasks while maintaining quality +standards + +**Improve code quality** provide consistent, actionable feedback on every change + +**Enable continuous deployment** safe, automated releases with confidence + +**Scale expertise** every developer gets access to senior-level DevOps knowledge + + + Data & Analytics with Neo4j and MongoDB. Build agents that understand graph + relationships and document structures for complex data analysis. + + +## Pro tip for today + +After building your development agent, test it with real scenarios: + +```text +What development workflows in our team are most error-prone or time-consuming? +How can we enhance your capabilities to better handle these specific patterns? +``` + +This helps you identify additional automation opportunities specific to your +team's needs. + +--- + +**Time to complete** ~30 minutes + +**Skills learned** code review intelligence, deployment orchestration, +production monitoring, rollback automation, development best practices + +**Next** day 13 - Data & Analytics agents with Neo4j and MongoDB + + + **Remember** the best development agents don't just execute commands—they + understand the why behind development practices and make intelligent decisions + about code quality, deployment safety, and system reliability. + diff --git a/agents/30-days-of-agents/day-13.mdx b/agents/30-days-of-agents/day-13.mdx new file mode 100644 index 00000000..2f65f1ed --- /dev/null +++ b/agents/30-days-of-agents/day-13.mdx @@ -0,0 +1,210 @@ +--- +title: "Day 13: Project Management & Documentation - Linear & Notion" +sidebarTitle: "Day 13: Linear & Notion" +description: + "Build a project management agent that coordinates tasks, tracks progress, and + maintains documentation across Linear and Notion." +--- + + + **Goal**: create a project coordination agent with Linear and Notion + +**Theme**: domain specialization week - project intelligence + +**Time investment**: ~20 minutes + + + +Welcome to Day 13! Today you'll build a **project management agent** that +bridges task tracking in Linear with documentation in Notion. This agent +understands how modern teams work across multiple tools. + +## What you'll accomplish today + +- Build a project management agent that coordinates across tools +- Connect Linear for issue tracking and sprint management +- Integrate Notion for documentation and knowledge management +- Create workflows that keep projects and docs in sync + + + You'll need access to Linear and Notion workspaces with appropriate + permissions to complete today's exercises. + + +## Step 1: Understanding project management patterns + +Project agents need to understand: + +### Cross-tool coordination + +- **Task lifecycle**: From idea in Notion → issue in Linear → documentation + update +- **Status synchronization**: Keep project status consistent across platforms +- **Knowledge capture**: Document decisions and outcomes, not just track tasks +- **Team collaboration**: Different tools for different team members + + + **Multi-tool thinking**: your agent should understand that Linear tracks work + while Notion captures knowledge—and keep both synchronized. + + +## Step 2: Create your project management agent + +Work with Concierge to build a cross-platform coordinator: + +```text +I want to create a project management agent that coordinates between Linear and Notion. + +The agent should: +- Track sprint progress in Linear and update project docs in Notion +- Create Linear issues from Notion meeting notes and planning docs +- Generate weekly project summaries combining task data and documentation +- Ensure technical decisions in Linear are documented in Notion +- Keep project roadmaps synchronized across both platforms + +It should act like a technical project manager who ensures nothing falls through the cracks. +``` + +## Step 3 connect Linear and Notion + +Add both connections to your agent: + +**Linear connection**: + +- Issue management and creation +- Sprint tracking and velocity +- Project status and milestones +- Team workload visibility + +**Notion connection**: + +- Documentation reading and updates +- Meeting notes processing +- Knowledge base management +- Project wiki maintenance + +## Step 4: Implement coordination workflows + +### Workflow 1: Sprint documentation + +```text +At the end of each sprint, can you: +1. Summarize completed Linear issues +2. Extract key decisions and technical changes +3. Update our Notion sprint retrospective doc +4. Identify undocumented features that need wiki updates +``` + +Your agent coordinates: + +- Pulls completed issues from Linear +- Identifies important decisions and changes +- Updates Notion with structured summaries +- Flags documentation gaps + +### Workflow 2: Meeting to task conversion + +```text +I just finished a planning meeting. The notes are in Notion under "Product Planning." +Can you create Linear issues for all the action items we discussed? +``` + +The agent: + +- Reads meeting notes from Notion +- Identifies concrete action items +- Creates properly labeled Linear issues +- Links back to source documentation + +## Step 5: Build reusable coordination tasks + + + **Coming soon** daily scheduled tasks and automated workflows. For now, you'll + need to interact with your agent through the UI to trigger these workflows. + + +**Daily standup prep**: + +```text +Can you prepare a standup summary that includes: +- Yesterday's completed Linear issues +- Today's priorities from Linear +- Any blockers mentioned in Linear comments +- Related Notion docs for context + +Post this in our Notion daily standups page. +``` + +**Documentation health check**: + +```text +Can you analyze: +- Linear issues marked "Done" without linked documentation +- Notion pages that reference outdated Linear issues +- Technical decisions in Linear not captured in Notion +- Project timelines that have diverged between tools + +Create a "Documentation Debt" report in Notion. +``` + + + **Pro tip** set a reminder to run these workflows daily or weekly until + automated scheduling becomes available. + + +## What you've accomplished + +In 20 minutes, you've built a cross-platform project management agent: + +**Multi-tool coordination** agent that understands Linear for execution and +Notion for knowledge + +**Manual synchronization** keeps tasks and documentation aligned when you run +the workflows + +**Workflow intelligence** converts between different information formats + +**Gap identification** finds where documentation doesn't match execution + +## The power of multi-tool agents + +Project management agents that span tools can: + +- **Prevent information silos** by connecting execution with documentation +- **Reduce context switching** by bringing information together +- **Capture institutional knowledge** automatically from task execution +- **Improve team alignment** through consistent cross-tool updates + + + Data & analytics with Neo4j and MongoDB. Build agents that understand complex + data relationships. + + +## Pro tip for today + +Ask your project agent: + +```text +What patterns do you notice between our Linear velocity and our Notion documentation quality? +How can we improve both? +``` + +This helps your agent develop insights about your team's work patterns. + +--- + +**Time to complete**: ~20 minutes + +**Skills learned** multi-tool coordination, Linear integration, Notion +automation, project intelligence + +**Next** Day 14 - Data & analytics agents with Neo4j and MongoDB + + + **Remember** the best project agents don't just move data between tools—they + understand how your team works and help improve processes. + diff --git a/agents/30-days-of-agents/day-14.mdx b/agents/30-days-of-agents/day-14.mdx new file mode 100644 index 00000000..84492438 --- /dev/null +++ b/agents/30-days-of-agents/day-14.mdx @@ -0,0 +1,219 @@ +--- +title: "Day 14: Data & Analytics Intelligence - Neo4j & MongoDB" +sidebarTitle: "Day 14: Neo4j & MongoDB" +description: + "Build data analysis agents that understand graph relationships in Neo4j and + document structures in MongoDB for complex business intelligence." +--- + + + **Goal**: create data intelligence agents for graph and document databases + +**Theme**: domain specialization week - data & analytics + +**Time investment**: ~20 minutes + + + +Welcome to Day 14! Today you'll build **data intelligence agents** that work +with modern databases—Neo4j for graph relationships and MongoDB for document +structures. These agents understand complex data patterns, not just queries. + +## What you'll accomplish today + +- Build agents that understand graph relationships and document structures +- Connect Neo4j for relationship analysis and pattern detection +- Integrate MongoDB for flexible document querying +- Create insights from complex, interconnected data + + + You'll need access to Neo4j and/or MongoDB instances to complete today's + hands-on exercises. The concepts apply to any modern database. + + +## Step 1: Understanding modern data patterns + +Data intelligence agents must grasp: + +### Graph intelligence Neo4j + +- **Relationship mapping**: How entities connect and influence each other +- **Pattern detection**: Finding hidden connections in networks +- **Path analysis**: Shortest paths, influence chains, impact radius +- **Community detection**: Clusters, groups, and anomalies + +### Document intelligence MongoDB + +- **Schema flexibility**: Varying document structures and embedded data +- **Aggregation patterns**: Complex queries across nested documents +- **Time-series analysis**: Historical patterns and trends +- **X insights**: Location-based patterns and relationships + + + **Beyond SQL thinking** modern data agents understand relationships and + document structures, not just tables and rows. + + +## Step 2: Create specialized data agents + +### Graph intelligence agent (Neo4j) + +```text +I want to create a customer intelligence agent using our Neo4j graph database. + +The agent should: +- Analyze customer relationship networks and referral chains +- Identify influential customers based on connection patterns +- Find communities and clusters in our user base +- Detect unusual relationship patterns that might indicate fraud +- Recommend connections that could drive growth + +Think like a network analyst who understands social dynamics and graph theory. +``` + +### Document analytics agent (MongoDB) + +```text +I want to create a product analytics agent using our MongoDB database. + +The agent should: +- Analyze product usage patterns across different user segments +- Track feature adoption through nested event documents +- Identify user journeys from unstructured activity logs +- Find patterns in customer feedback and support tickets +- Generate insights from varying document schemas + +Think like a data scientist working with semi-structured data. +``` + +## Step 3: Connect and explore your databases + +### Neo4j connection capabilities + +Your agent can: + +- **Traverse relationships**: Follow connections multiple degrees deep +- **Find patterns**: Match complex relationship structures +- **Calculate centrality**: Identify important nodes in networks +- **Detect communities**: Find natural groupings and clusters + +### MongoDB connection capabilities + +Your agent can: + +- **Query nested documents**: Access deeply embedded data +- **Aggregate flexibly**: Group, filter, and transform documents +- **Handle variety**: Work with different document structures +- **Process time-series**: Analyze temporal patterns + +## Step 4: Implement data intelligence workflows + +### Graph analysis example (Neo4j) + +```text +Who are our most influential customers based on referral networks? +How can we leverage these relationships for growth? +``` + +Your agent analyzes: + +- Referral chains and their success rates +- Network effects from key customers +- Community structures and growth patterns +- Opportunities for connection strategies + +### Document analysis example (MongoDB) + +```text +What user behavior patterns predict successful feature adoption? +Which segments are struggling with our new features? +``` + +Your agent examines: + +- Feature usage sequences in activity logs +- Correlation between user properties and adoption +- Time-to-value patterns across segments +- Drop-off points in user journeys + +## Step 5: Create advanced data workflows + +**Network health monitoring** (Neo4j): + +```text +Weekly, analyze our customer network for: +- Growing communities that might need dedicated support +- Isolated users who could benefit from connections +- Referral chains that have gone cold +- Emerging influencers based on connection growth + +Provide actionable recommendations for community management. +``` + +**Behavioral intelligence** (MongoDB): + +```text +Daily, process user activity documents to identify: +- Unusual usage patterns indicating potential issues +- Feature combinations that drive engagement +- User segments with declining activity +- Success patterns we should replicate + +Focus on actionable insights, not just statistics. +``` + +## What you've accomplished + +In 20 minutes, you've built sophisticated data intelligence agents: + +**Graph understanding** Agents that see relationships, not just data points + +**Document flexibility** working with varied, nested, and complex structures + +**Pattern recognition** finding insights in connected and unstructured data + +**Actionable intelligence** recommendations based on data patterns, not just +queries + +## The power of modern data agents + +Data agents that understand modern databases can: + +- **Reveal hidden connections** in relationship networks +- **Find patterns in chaos** of unstructured documents +- **Predict behaviors** from historical patterns +- **Enable data democracy** without query language expertise + + + Customer relationship management with Attio and Google Sheets. Build agents + for sales intelligence and spreadsheet automation. + + +## Pro tip for today + +Challenge your data agents: + +```text +What non-obvious patterns in our data could give us a competitive advantage? +Show me connections or trends I wouldn't think to look for. +``` + +This pushes agents beyond basic queries to true intelligence. + +--- + +**Time to complete**: ~20 minutes + +**Skills learned** graph database intelligence, document database analytics, +pattern recognition, modern data workflows + +**Next** Day 15 - CRM and spreadsheet intelligence with Attio and Google Sheets + + + **Remember** the best data agents don't just run queries—they understand the + meaning behind the data and find patterns humans might miss. + diff --git a/agents/30-days-of-agents/day-15.mdx b/agents/30-days-of-agents/day-15.mdx new file mode 100644 index 00000000..53671da9 --- /dev/null +++ b/agents/30-days-of-agents/day-15.mdx @@ -0,0 +1,216 @@ +--- +title: "Day 15: Customer Intelligence & Data Operations - Attio & Google Sheets" +sidebarTitle: "Day 15: Attio & Google Sheets" +description: + "Build sales intelligence agents that manage CRM data in Attio and operational + data in Google Sheets, creating unified customer insights and automated + workflows." +--- + + + **Goal**: create customer intelligence agents with CRM and spreadsheet mastery + +**Theme**: domain specialization week - customer & operational intelligence + +**Time investment**: ~20 minutes + + + +Welcome to Day 15! You'll complete Week 3 by building **customer intelligence +agents** that bridge modern CRM (Attio) with operational spreadsheets (Google +Sheets). These agents transform disconnected data into unified customer +insights. + +## What you'll accomplish today + +- Build agents that understand customer relationships and sales processes +- Connect Attio for modern CRM intelligence +- Integrate Google Sheets for operational data and reporting +- Create unified views across sales and operational systems + + + You'll need access to Attio and Google Sheets to complete today's exercises. + The patterns apply to any CRM and spreadsheet combination. + + +## Step 1: Understanding customer intelligence patterns + +Customer intelligence agents must understand: + +### CRM intelligence (Attio) + +- **Relationship mapping**: Companies, contacts, and their interactions +- **Pipeline dynamics**: Deal flow, conversion rates, and bottlenecks +- **Activity patterns**: What actions correlate with successful outcomes +- **Data enrichment**: Combining CRM data with external intelligence + +### Operational intelligence (Google sheets) + +- **Flexible reporting**: Custom metrics and calculations +- **Data bridging**: Information that lives outside the CRM +- **Historical tracking**: Trends and patterns over time +- **Team accessibility**: Shared operational dashboards + + + **Unified thinking** your agent should understand that CRMs track + relationships while spreadsheets often contain the operational truth. + + +## Step 2: Create customer intelligence agents + +Work with Concierge to build a unified intelligence agent: + +```text +I want to create a customer intelligence agent that works with Attio and Google Sheets. + +The agent should: +- Monitor deal pipeline in Attio and update forecasting sheets +- Enrich CRM data with operational metrics from spreadsheets +- Generate unified customer health scores combining both sources +- Alert on mismatches between CRM pipeline and operational data +- Create executive dashboards that merge relationship and operational insights + +It should think like a revenue operations analyst who sees the full picture. +``` + +## Step 3: Connect Attio and Google Sheets + +### Attio capabilities + +Your agent can: + +- **Manage relationships**: Create and update companies, contacts, deals +- **Track activities**: Log interactions, meetings, and touchpoints +- **Analyze pipelines**: Deal stages, conversion rates, and velocity +- **Custom attributes**: Work with your specific data model + +### Google sheets capabilities + +Your agent can: + +- **Read/write data**: Update cells, ranges, and formulas +- **Create reports**: Generate new sheets with formatted data +- **Process calculations**: Run complex operational metrics +- **Maintain history**: Track changes over time + +## Step 4: Implement unified workflows + +### Workflow 1: Pipeline-to-forecast synchronization + +```text +Can you analyze our current Attio pipeline and update our revenue forecast sheet? +Include deal probability based on stage and historical conversion rates. +``` + +Your agent: + +- Pulls current pipeline from Attio +- Calculates weighted revenue by stage +- Updates forecast spreadsheet with breakdown +- Highlights changes from last update + +### Workflow 2: Customer health scoring + +```text +Create a unified customer health score combining: +- Attio: engagement frequency, deal value, relationship strength +- Sheets: product usage, support tickets, payment history + +Identify at-risk accounts that need attention. +``` + +The agent: + +- Merges relationship data with operational metrics +- Calculates composite health scores +- Flags accounts with declining indicators +- Suggests intervention strategies + +## Step 5: Build automated intelligence tasks + +**Weekly sales intelligence report**: + +```text +Every Monday, create a sales intelligence report that: +1. Summarizes pipeline changes in Attio +2. Updates win rate calculations in our metrics sheet +3. Identifies deals stuck in stages too long +4. Compares CRM pipeline to operational forecasts +5. Highlights data discrepancies needing cleanup + +Format for our executive team meeting. +``` + +**Customer success automation**: + +```text +Daily, monitor for: +- New deals closed in Attio → Create onboarding checklist in Sheets +- Usage drops in Sheets data → Update account status in Attio +- Support tickets in Sheets → Log activities in Attio +- Payment issues in Sheets → Flag deals at risk in Attio + +Keep both systems synchronized for accurate customer view. +``` + +## What you've accomplished + +In 20 minutes, you've built comprehensive customer intelligence: + +**Unified data view** agents that bridge CRM and operational data + +**Automated synchronization** keep multiple systems aligned automatically + +**Intelligent insights** combine relationship and operational intelligence + +**Proactive alerts** catch issues before they impact revenue + +## Week 3 complete: Domain specialization achieved + +You've completed Week 3 and mastered domain-specific agent development: + +- **Day 11**: Financial intelligence with Stripe +- **Day 12**: Development workflows with GitHub and Vercel +- **Day 13**: Project coordination with Linear and Notion +- **Day 14**: Data analytics with Neo4j and MongoDB +- **Day 15**: Customer intelligence with Attio and Google Sheets + +## The power of domain expertise + +Your agents now: + +- **Understand business context**, not just tool APIs +- **Think like domain experts** in their specialized areas +- **Connect disparate systems** into unified intelligence +- **Provide actionable insights**, not just data movement + + + **Production deployment and optimization** - Take your agents from development + to business-critical production systems with monitoring, scaling, and + performance optimization. + + +## Pro tip for Week 3 + +Ask any of your domain agents: + +```text +What patterns have you noticed that could fundamentally change how we operate? +What would a 10x improvement look like in your domain? +``` + +This pushes agents beyond automation to transformation. + +--- + +**Time to complete** ~20 minutes + +**Skills learned** CRM intelligence, spreadsheet automation, unified customer +view, cross-system synchronization + +**Week 3 complete** you're now a domain-specific agent builder! + + + **Remember** the best domain agents don't just use tools—they embody the + expertise and judgment of seasoned professionals in their field. + diff --git a/agents/30-days-of-agents/domain-specific-agents.mdx b/agents/30-days-of-agents/domain-specific-agents.mdx new file mode 100644 index 00000000..443ec32c --- /dev/null +++ b/agents/30-days-of-agents/domain-specific-agents.mdx @@ -0,0 +1,79 @@ +--- +title: "Week 3: Domain-Specific Agents" +sidebarTitle: "Choose your path" +description: + "Dive into domain-specific agents. Learn how to build agents tailored to + specific tasks and industries, enhancing their effectiveness and efficiency." +--- + +![Agents Bootcamp: domain specific agents - Week 3](/images/agents/30-days-of-agents/bootcamp-week-3.png) + +Welcome to Week 3! You've mastered the fundamentals with Sidekick and built +custom agents with Concierge. Now it's time to **specialize**. + +This week focuses on domain-specific agents—AI that understands the nuances of +specific business functions and tools. You'll learn to build agents that don't +just use tools, but truly understand the workflows and best practices of +different domains. + +## Choose your learning path + +Week 3 offers **specialized domain tracks** based on your role and interests. +You can follow domains that match your work, or complete multiple tracks to +become an **Agent Super Builder**. + + + + **Day 11 Stripe Integration** + + Build agents that handle payments, subscriptions, and financial workflows with deep business intelligence. + + *Perfect for: Revenue Operations, Finance Teams, SaaS Businesses* + + + + + **Day 12 GitHub & Vercel Integration** Create agents that manage code + repositories, deployments, and development workflows with engineering + expertise. + +Perfect for developers, DevOps teams, Platform engineers + + + + + **Day 13 Linear & Notion Integration** Build agents that coordinate tasks, + track progress, and maintain documentation across project tools. + +Perfect for project managers, engineering teams, product teams + + + + + **Day 14 Neo4j & MongoDB Integration** Build agents that work with graph + databases and document stores for complex data analysis and insights. + +Perfect for: data engineers, analytics teams, backend developers + + + + + **Day 15 Attio CRM & Google Sheets Integration** + Develop agents that manage customer relationships and operational data for unified business intelligence. + +Perfect for: sales Teams, Customer Success, Revenue Operations + + + diff --git a/docs.json b/docs.json index 1621e380..cd378c08 100644 --- a/docs.json +++ b/docs.json @@ -107,6 +107,17 @@ "agents/30-days-of-agents/day-9", "agents/30-days-of-agents/day-10" ] + }, + { + "group": "Week 3", + "pages": [ + "agents/30-days-of-agents/domain-specific-agents", + "agents/30-days-of-agents/day-11", + "agents/30-days-of-agents/day-12", + "agents/30-days-of-agents/day-13", + "agents/30-days-of-agents/day-14", + "agents/30-days-of-agents/day-15" + ] } ] }, diff --git a/styles/config/vocabularies/general/accept.txt b/styles/config/vocabularies/general/accept.txt index 4c92d7c8..57a0ea7a 100644 --- a/styles/config/vocabularies/general/accept.txt +++ b/styles/config/vocabularies/general/accept.txt @@ -183,4 +183,15 @@ I'm GTM chatbots enablement -[lL]uma \ No newline at end of file +[lL]uma +CRM +CRMs +touchpoints +Neo4j +Geospatial +Linear +MRR +LTV +CAC +upsell +will \ No newline at end of file