# Agent Factory Archive

> Two retired parts of the just-in-time Agent Factory curriculum — the personal AI employee chapter and cloud deployment, chapters 79–90 — preserved exactly as published and no longer maintained.

- name: ag-archive
- build_id: sha256:c8912c3008ae345a7fdc33ace656531ad74f37c065177057c390c7d759f1e970
- source_commit: dad4758bb59919c7b9130444778ade062a2dce3e
- ksor_version: 0.0.47

## Documents

- [Deploying Agent Factories in the Cloud](/docs/deploying-agent-factories-in-the-cloud/overview): Part 7 takes the agent you built in Part 6 and turns it into a production cloud service.
- [Build Your Docker Skill](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/00-build-your-docker-skill): Create your Docker deployment skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 79: Docker for AI Services](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/overview): Build your Docker skill first, then learn to understand and refine it into a production-ready asset
- [Docker Installation & Setup](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/01-docker-installation-and-setup): Containers solve the "works on my machine" problem by packaging applications with their dependencies into portable, isolated units that share the host kernel, making them faster and lighter than VMs.
- [Container Fundamentals: Images, Containers, and Layers](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/02-container-fundamentals): Master Docker's core concepts through hands-on exploration—pulling images, running containers, and understanding how layers enable efficient image sharing.
- [Writing Your First Dockerfile](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/03-writing-your-first-dockerfile): Learn to write a Dockerfile step-by-step, understanding each instruction as you build a containerized FastAPI application
- [Container Lifecycle and Debugging](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/04-container-lifecycle-and-debugging): Master container lifecycle management and debugging techniques using docker logs, docker exec, and docker inspect to troubleshoot containerized FastAPI services
- [Multi-Stage Builds & Optimization](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/05-multi-stage-builds-and-optimization): Reduce Docker image size by 70-85% using multi-stage builds, UV package manager, and Alpine base images
- [Production Hardening](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/06-production-hardening): Secure and harden Docker containers for production deployment with environment variables, health checks, and non-root users
- [Docker Image Builder Skill](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/07-docker-image-builder-skill): Transform Docker knowledge from Lessons 1-6 into a reusable AI skill for consistent, production-ready containerization
- [Capstone: Containerize Your API](/docs/deploying-agent-factories-in-the-cloud/79-docker-for-ai-services/08-capstone-containerize-your-api): Apply specification-first containerization to build a production-ready Docker image for your SQLModel + Neon Task API
- [Build Your Kubernetes Skill](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/00-build-your-kubernetes-skill): Create your Kubernetes deployment skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 80: Kubernetes for AI Services](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/overview): Build your Kubernetes skill first, then learn to understand and refine it into a production-ready asset
- [Kubernetes Architecture and the Declarative Model](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/01-kubernetes-architecture-declarative-model): Kubernetes is a distributed operating system for containers.
- [Enabling Kubernetes (Docker Desktop)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/02-enabling-kubernetes-docker-desktop): Docker Desktop includes a built-in Kubernetes cluster that uses the identical API and architecture as production Kubernetes.
- [Pods: The Atomic Unit](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/03-pods-the-atomic-unit): A Pod is the smallest deployable unit in Kubernetes—one or more containers that share network and storage.
- [Deployments: Self-Healing at Scale](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/04-deployments-self-healing-at-scale): A Deployment is a controller that manages Pods at scale with zero downtime.
- [Services and Networking: Stable Access to Dynamic Pods](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/05-services-and-networking): Services solve the Pod ephemerality problem.
- [Namespaces: Virtual Clusters for AI Workloads](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/06-namespaces-virtual-clusters): Namespaces are virtual cluster partitions that enable multi-tenancy on a single cluster.
- [ConfigMaps and Secrets](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/07-configmaps-and-secrets): ConfigMaps and Secrets decouple configuration from container images.
- [Resource Management and Debugging](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/08-resource-management-and-debugging): Resource requests and limits drive Kubernetes scheduling and eviction decisions.
- [Horizontal Pod Autoscaler for AI Agents](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/09-hpa-autoscaling): Horizontal Pod Autoscaler (HPA) automatically scales Pod replicas up and down based on metrics (CPU, memory, or custom).
- [RBAC: Securing Your Agent Deployments](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/10-rbac-securing-agent-deployments): Role-Based Access Control (RBAC) restricts what Pods can do by connecting ServiceAccounts (identity) to Roles (permissions) via RoleBindings.
- [Health Checks: Liveness, Readiness, Startup Probes](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/11-health-checks-probes): Three health probe types answer different questions: Readiness (is this Pod ready for traffic?), Liveness (is this Pod still alive?), Startup (is initialization complete?).
- [Jobs and CronJobs: Batch Workloads for AI Agents](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/12-jobs-and-cronjobs-batch-workloads): Deployments keep your AI agent running forever.
- [AI-Assisted Kubernetes with kubectl-ai](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/13-ai-assisted-kubernetes-kubectl-ai): kubectl-ai bridges natural language intent to Kubernetes operations—describe what you want, it generates manifests or commands.
- [Capstone: Deploy Your Part 6 Agent to Kubernetes](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/14-capstone-production-ready-agent): Specification-first deployment: write what you're building and why before generating manifests.
- [Test and Refine Your Kubernetes Skill](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/15-building-kubernetes-deployment-skill): Validate skill transferability by applying the Kubernetes skill (built in Lesson 0, refined through Lessons 1-14) to a different application type.
- [Init Containers (Optional)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/16-init-containers-optional): Init containers run before application containers and must complete successfully before the app starts.
- [Sidecar Containers (Optional)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/17-sidecar-containers-optional): Sidecars are helper containers that run in the same Pod as your main app, handling operational concerns independently.
- [Ingress: External Access (Optional)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/18-ingress-optional): Ingress exposes HTTP and HTTPS routes from outside the cluster to services within it.
- [Service Discovery Deep Dive (Optional)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/19-service-discovery-optional): Service discovery is how Kubernetes translates service names (api.services.svc.cluster.local) into IP addresses.
- [StatefulSets (Optional)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/20-statefulsets-optional): StatefulSets guarantee stable Pod identity (pod-0, pod-1, pod-2 remain the same across restarts) and ordered lifecycle (startup and shutdown happen sequentially), making them essential for stateful.
- [Persistent Storage (Optional)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/21-persistent-storage-optional): PersistentVolumes (PVs) and PersistentVolumeClaims (PVCs) decouple storage from container instances, allowing data to survive Pod restarts.
- [Kubernetes Security Deep Dive (Optional)](/docs/deploying-agent-factories-in-the-cloud/80-kubernetes-for-ai-services/22-kubernetes-security-optional): Production-grade security requires multiple layers: non-root execution (SecurityContext), read-only filesystems (emptyDir for writable paths), network isolation (NetworkPolicies), and image scanning.
- [Build Your Helm Skill](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/00-build-your-helm-skill): Create your Helm chart skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 81: Helm Charts for AI Services](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/overview): Build your Helm skill first, then learn to understand and refine it into a production-ready asset
- [Introduction to Helm](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/01-introduction-to-helm): Helm is the package manager for Kubernetes that solves the repetitive YAML problem by templating deployments with parameterized values, enabling consistent multi-environment deployments from a single.
- [Advanced Go Templating](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/02-advanced-go-templating): Go templating enables dynamic Kubernetes manifests through variables, pipelines, conditionals, and iteration, transforming static YAML into adaptive configurations that respond to environment.
- [Named Templates and Helpers](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/03-named-templates-helpers): Named templates (partials) enable DRY principles in Helm charts by defining reusable template fragments in _helpers.tpl that can be included across multiple manifests with consistent labels.
- [Values Deep Dive](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/04-values-deep-dive): Values override precedence hierarchy (values.yaml < -f file < --set) enables multi-environment deployments from a single chart, while schema validation prevents invalid configurations before.
- [Chart Dependencies](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/05-chart-dependencies): Chart dependencies enable composition of production infrastructure by declaring subcharts (PostgreSQL, Redis) in Chart.yaml, so a single helm install deploys your application with all its supporting.
- [Helm Hooks and Lifecycle Management](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/06-helm-hooks-lifecycle): Helm hooks execute Kubernetes Jobs at specific lifecycle points (pre-install, pre-upgrade, post-delete) to automate tasks like database migrations, cache invalidation, and backup creation as part of.
- [Testing Your Charts](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/07-testing-your-charts): Chart testing spans static validation (helm lint, helm template) to runtime verification (test pods, helm test), creating a safety net that catches errors before they reach production.
- [OCI Registries and Distribution](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/08-oci-registries-distribution): Helm charts distribute via OCI-compliant registries (Docker Hub, ECR, ACR) using the same infrastructure and authentication as container images, unifying artifact management with semantic versioning.
- [Library Charts and Organizational Standardization](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/09-library-charts-standardization): Library charts (type: library) encode organizational standards as reusable templates that application charts consume as dependencies, ensuring consistent labels, probes, and security contexts across.
- [AI-Assisted Chart Development](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/10-ai-assisted-chart-development): AI collaboration accelerates chart development through iterative refinement: initial generation, critical evaluation, constraint teaching, and validation produce solutions superior to either AI.
- [Capstone: Production AI Agent Chart](/docs/deploying-agent-factories-in-the-cloud/81-helm-charts/11-capstone-production-agent-chart): Specification-first development produces production-grade Helm charts by establishing clear success criteria and acceptance tests before implementation, then synthesizing all chapter concepts into a.
- [Build Your Kafka Skill](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/00-build-your-kafka-skill): Create your Kafka event schema skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 82: Event-Driven Architecture with Kafka](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/overview): Build your Kafka skill first, then learn to understand and refine it into a production-ready asset
- [From Request-Response to Events](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/01-from-request-response-to-events): Understand why direct API calls between services create tight coupling and how asynchronous events solve temporal, availability, and behavioral coupling problems
- [Event-Driven Architecture Concepts](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/02-event-driven-architecture-concepts): Master the fundamental concepts of event-driven architecture—events vs commands, eventual consistency, and when to use EDA over synchronous APIs.
- [How Kafka Fits: The Mental Model](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/03-kafka-mental-model): Build a clear mental model of Kafka's architecture using visual analogies - topics, partitions, consumer groups, and the message journey
- [Deploying Kafka with Strimzi](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/04-deploying-kafka-with-strimzi): Deploy Apache Kafka on Kubernetes using the Strimzi operator with KRaft mode
- [Your First Producer (Python)](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/05-your-first-producer): Build your first Kafka producer with confluent-kafka-python, learning delivery callbacks, poll(), and flush() patterns
- [Producer Deep Dive: Reliability](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/06-producer-reliability): Master Kafka producer reliability with acks configurations, idempotent producers, and delivery failure handling for production systems
- [Your First Consumer (Python)](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/07-your-first-consumer): Implement Kafka consumers with proper poll loops, offset management, and error handling using confluent-kafka-python
- [Consumer Deep Dive: Groups and Rebalancing](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/08-consumer-groups-rebalancing): Master consumer group mechanics, implement rebalance callbacks, and diagnose consumer lag for reliable event processing
- [Async Producers and Consumers in FastAPI](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/09-async-fastapi-integration): Integrate Kafka with FastAPI using async patterns, lifespan events, and background consumers for production event-driven APIs
- [Message Schemas: Avro and Schema Registry](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/10-message-schemas-avro): Design event schemas with Apache Avro, integrate Confluent Schema Registry for centralized schema management, and implement backward-compatible schema evolution
- [Delivery Semantics Deep Dive](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/11-delivery-semantics): Master at-most-once, at-least-once, and exactly-once delivery semantics in Kafka with practical decision frameworks and idempotent consumer patterns
- [Transactions for Stream Processing](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/12-transactions): Implement exactly-once stream processing with Kafka transactions, transactional producers, and the read-process-write pattern for atomic multi-topic operations
- [Reliability Configuration](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/13-reliability-configuration): Configure min.insync.replicas and tune Kafka for latency versus durability trade-offs in production event-driven systems
- [Kafka Connect: Building Data Pipelines](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/14-kafka-connect): Deploy Kafka Connect on Kubernetes using Strimzi, configure source and sink connectors, and build automated data pipelines without writing custom code
- [Change Data Capture with Debezium](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/15-cdc-debezium): Implement the transactional outbox pattern using Debezium CDC to capture PostgreSQL changes and stream them to Kafka with guaranteed atomicity
- [Agent Event Patterns](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/16-agent-event-patterns): Design event schemas for AI agent communication with correlation tracking, implement agent-to-agent messaging patterns, and build notification fanout systems
- [Saga Pattern for Multi-Step Workflows](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/17-saga-pattern): Implement choreography-based sagas using Kafka events and design compensating transactions for reliable distributed workflows
- [Production Kafka with Strimzi](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/18-production-kafka-strimzi): Configure production-grade Kafka clusters with separate controller and broker node pools, TLS encryption, SCRAM authentication, and proper resource limits
- [Monitoring and Debugging Kafka](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/19-monitoring-debugging): Master consumer lag diagnosis, use Kafka CLI tools for troubleshooting, and configure alerting thresholds for production reliability
- [AI-Assisted Kafka Development](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/20-ai-assisted-kafka-development): Master effective AI collaboration for Kafka development: leverage AI's pattern knowledge, teach it your production constraints, and iterate toward optimal solutions
- [Capstone: Event-Driven Agent Notifications](/docs/deploying-agent-factories-in-the-cloud/82-event-driven-kafka/21-capstone-event-driven-notifications): Build a complete event-driven notification system using spec-driven development, integrating Task API events with notification and audit services
- [Build Your Dapr Skill](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/00-build-your-dapr-skill): Create your Dapr deployment skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 83: Dapr Core - Sidecar Building Blocks](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/overview): Simplify distributed AI agent systems with Dapr's portable building blocks for state, pub/sub, service invocation, and more
- [The Sidecar Pattern](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/01-sidecar-pattern): Understand how the sidecar pattern separates infrastructure concerns from application code, enabling portable and maintainable distributed AI agent systems
- [Building Blocks and Components](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/02-building-blocks-components): Master Dapr's abstraction model—building blocks as portable APIs and components as pluggable implementations. Understand how swapping YAML changes infrastructure without touching code.
- [Deploy Dapr + State Management](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/03-deploy-dapr-state-management): Deploy Dapr control plane on Kubernetes with Helm and implement state management using the Python SDK
- [Service Invocation](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/04-service-invocation): Call services by name with automatic discovery, mTLS, and retry policies using Dapr's service invocation building block
- [Pub/Sub Messaging](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/05-pubsub-messaging): Implement event-driven communication with Dapr pub/sub, CloudEvents format, and programmatic subscriptions using dapr-ext-fastapi
- [Bindings and Triggers](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/06-bindings-triggers): Connect your Dapr applications to external systems with input bindings (cron, webhooks, queues) and output bindings (HTTP, email, storage). Learn when to use bindings vs pub/sub.
- [Jobs API: Scheduled Tasks](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/07-jobs-api): Schedule one-time and recurring jobs with Dapr's Jobs API, backed by the Scheduler service and embedded Etcd storage
- [Secrets and Configuration](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/08-secrets-configuration): Master Dapr's secrets and configuration building blocks for secure credential management and dynamic settings in distributed systems
- [Capstone: Dapr-Enabled Task API](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/09-capstone-dapr-task-api): Refactor the Part 6 Task API to use Dapr for all infrastructure abstraction including state, pub/sub, service invocation, and secrets
- [Finalize Your Dapr Skill](/docs/deploying-agent-factories-in-the-cloud/83-dapr-core/10-finalize-dapr-skill): Complete and test your dapr-deployment skill for production use, adding safety guardrails and validating coverage across all building blocks
- [Build Your GitOps Skill](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/00-build-your-gitops-skill): Create your GitOps deployment skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 84: CI/CD Pipelines & GitOps with ArgoCD](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/overview): Build your GitOps skill first, then learn to understand and refine it into a production-ready asset
- [CI/CD Concepts: The Automated Pipeline](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/01-cicd-concepts-automated-pipeline): Understand pipeline stages, triggers, artifacts, and why automation matters for deployment at scale
- [GitHub Actions Fundamentals](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/02-github-actions-fundamentals): Create automated workflows with triggers, jobs, steps, and secrets
- [Building Docker Images in CI](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/03-building-docker-images-ci): Automate multi-platform Docker builds with GitHub Actions and registry push
- [Testing and Quality Gates](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/04-testing-quality-gates): Implement test stages that block deployment on failure
- [GitOps Principles: Git as Truth](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/05-gitops-principles-git-as-truth): Understand declarative infrastructure, reconciliation loops, and drift detection
- [ArgoCD Architecture & Installation](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/06-argocd-architecture-installation): Install ArgoCD 3.x on Minikube and understand its component architecture
- [Your First ArgoCD Application](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/07-your-first-argocd-application): Create an Application CRD that syncs a Helm chart from Git to your cluster
- [Sync Strategies and Policies](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/08-sync-strategies-policies): Configure auto-sync, auto-prune, self-heal, and sync windows for precise control over ArgoCD deployments
- [Sync Waves and Resource Hooks](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/09-sync-waves-resource-hooks): Control deployment ordering with waves and lifecycle hooks
- [ApplicationSets: Scaling Deployments](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/10-applicationsets-scaling-deployments): Deploy to multiple environments with List, Cluster, Matrix, and Git generators
- [ArgoCD Projects and RBAC](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/11-argocd-projects-rbac): Configure multi-tenancy with Projects, resource restrictions, and role-based access
- [Health Status and Notifications](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/12-health-status-notifications): Monitor application health and configure alerts for deployment events
- [Progressive Delivery Overview](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/13-progressive-delivery-overview): Understand canary and blue-green deployments with Argo Rollouts
- [Secrets Management for GitOps](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/14-secrets-management-gitops): Handle secrets safely without storing them in Git
- [Multi-Cluster Deployments](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/15-multi-cluster-deployments): Deploy to multiple Kubernetes clusters with ArgoCD hub-spoke architecture
- [AI-Assisted GitOps Workflows](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/16-ai-assisted-gitops-workflows): Collaborate with Claude to generate and refine ArgoCD configurations
- [Capstone: End-to-End Agent Pipeline](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/17-capstone-end-to-end-agent-pipeline): Build a complete CI/CD pipeline from code push to running agent using GitHub Actions and ArgoCD
- [Building the GitOps Deployment Skill](/docs/deploying-agent-factories-in-the-cloud/84-cicd-gitops-argocd/18-building-gitops-deployment-skill): Create a reusable skill with Persona, Questions, and Principles
- [Build Your Observability Skill](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/00-build-your-observability-skill): Create your observability and cost engineering skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 85: Observability & Cost Engineering](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/overview): Master the three pillars of observability (metrics, tracing, logging), SRE foundations, and FinOps practices for cloud-native AI applications
- [Three Pillars of Observability](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/01-three-pillars-of-observability): Understand metrics, traces, and logs as complementary signals for debugging AI applications at scale
- [Metrics with Prometheus](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/02-metrics-with-prometheus): Deploy Prometheus in Kubernetes, write PromQL queries for the 4 golden signals, and instrument your Task API with custom metrics using prometheus_client
- [Visualization with Grafana](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/03-visualization-with-grafana): Build production-ready Grafana dashboards that transform raw Prometheus metrics into actionable insights using the 4 golden signals, dashboard variables, and JSON models
- [Distributed Tracing with OpenTelemetry & Jaeger](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/04-distributed-tracing-opentelemetry-jaeger): Learn to instrument FastAPI applications with OpenTelemetry, create custom spans for business operations, deploy Jaeger for trace visualization, and implement sampling strategies for production
- [Centralized Logging with Loki](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/05-centralized-logging-with-loki): Implement log aggregation with Grafana Loki and Promtail, write LogQL queries, configure structured logging in Python, and correlate logs with traces for distributed debugging
- [SRE Foundations: SLIs, SLOs, and Error Budgets](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/06-sre-foundations-slis-slos-error-budgets): Master the reliability dial through Service Level Indicators, Objectives, and Error Budgets for production AI applications
- [Alerting and Incident Response](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/07-alerting-and-incident-response): Implement multi-window, multi-burn-rate alerting based on SLOs, configure Alertmanager routing, and establish incident response runbooks for production AI services
- [Cost Engineering and FinOps](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/08-cost-engineering-and-finops): Implement FinOps practices to gain visibility into Kubernetes costs, identify waste, right-size resources with VPA, and schedule non-production for 75% savings
- [Dapr Observability Integration](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/09-dapr-observability-integration): Configure Dapr-native observability with metrics, tracing, and logging for sidecars, actors, and workflows in your Kubernetes observability stack
- [Capstone: Full Observability Stack for Task API](/docs/deploying-agent-factories-in-the-cloud/85-observability-cost-engineering/10-capstone-full-observability-stack): Deploy complete observability with metrics, traces, logs, SLOs, alerts, and cost monitoring for production AI applications
- [Build Your Traffic Engineering Skill](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/00-build-your-traffic-engineering-skill): Create your traffic engineering skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 86: Traffic Engineering](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/overview): Gateway API, Envoy Gateway, KEDA autoscaling, and Envoy AI Gateway for production traffic management
- [Ingress Fundamentals](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/01-ingress-fundamentals): Understand why Ingress exists, its limitations, and why Gateway API replaces it
- [Traefik Ingress Controller](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/02-traefik-ingress-controller): Deploy Traefik for simpler ingress before learning Gateway API complexity
- [Gateway API - The New Standard](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/03-gateway-api-new-standard): Learn Gateway API as the Kubernetes standard replacing Ingress with role separation and portability
- [Envoy Gateway Setup](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/04-envoy-gateway-setup): Install and configure Envoy Gateway as production-grade Gateway API implementation
- [Traffic Routing with HTTPRoute](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/05-traffic-routing-httproute): Master HTTPRoute matching patterns for production traffic routing
- [Rate Limiting & Circuit Breaking](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/06-rate-limiting-circuit-breaking): Protect services from abuse and cost overruns with BackendTrafficPolicy
- [TLS Termination with CertManager](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/07-tls-termination-certmanager): Secure traffic with TLS and automated certificate management
- [Traffic Splitting Patterns](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/08-traffic-splitting-patterns): Implement canary, blue-green, and A/B testing deployment patterns
- [Autoscaling on Kubernetes: HPA, VPA, KEDA, and Cluster Autoscaler](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/09-autoscaling-hpa-vpa-keda): The four independent autoscalers Kubernetes ships, when each one fires, and how they compose to take an AI Employee service from idle-at-zero to elastic-under-load without burning the cluster bill.
- [Resilience Patterns](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/10-resilience-patterns): Production-grade resilience with retries, timeouts, PDB, and graceful shutdown
- [Envoy AI Gateway for LLM Traffic](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/11-envoy-ai-gateway-llm-traffic): AI-specific traffic management with token-based rate limiting and provider fallback
- [Capstone: Production Traffic for Task API](/docs/deploying-agent-factories-in-the-cloud/86-traffic-engineering/12-capstone-production-traffic-task-api): Integrate all traffic engineering patterns for production-ready Task API
- [Extend Your Dapr Skill](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/00-extend-your-dapr-skill): Extend your existing Dapr skill with actor and workflow patterns using official documentation
- [JIT Chapter 87: Dapr Actors & Workflows](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/overview): Build stateful agents with virtual actors and durable workflows
- [The Actor Model](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/01-the-actor-model): Understand the Actor Model (Hewitt, 1973) as the conceptual foundation for building scalable, stateful AI agents with turn-based concurrency and message-passing
- [Hello Actors - Your First Actor](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/02-hello-actors): Create, register, and invoke your first Dapr Virtual Actor using Python and FastAPI, establishing the foundation for building stateful AI agent systems
- [Chat Actor - Stateful Conversations](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/03-chat-actor): Build a ChatActor that maintains conversation history with Dapr pub/sub integration for message-driven AI agent interactions
- [Actor State Management](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/04-actor-state-management): Master actor state persistence with _state_manager, lifecycle hooks, and turn-based concurrency guarantees
- [Timers and Reminders](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/05-timers-and-reminders): Implement actor timers for lightweight scheduling and reminders for persistent, durable scheduling that survives actor deactivation and system restarts
- [Actor Communication Patterns](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/06-actor-communication-patterns): Implement actor-to-actor communication via ActorProxy for coordination patterns including parent-child delegation and peer-to-peer collaboration
- [Event-Driven Actors](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/07-event-driven-actors): Integrate Dapr actors with pub/sub topics and bindings for reactive, event-driven agent patterns. Learn when to trigger actors from external events vs internal messages.
- [Actors Observability](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/08-actors-observability): Configure distributed tracing with Zipkin and Jaeger, monitor actor metrics with Prometheus, and apply debugging strategies for production actor systems
- [Dapr Workflows Overview](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/09-dapr-workflows-overview): Understand durable workflow execution, event sourcing, and when to use workflows vs actors for AI agent orchestration
- [Workflow Architecture](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/10-workflow-architecture): Understand how Dapr Workflows achieve durability through replay-based execution, state persistence, and strict determinism requirements
- [Authoring Workflows](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/11-authoring-workflows): Learn to implement workflow functions and activities using dapr-ext-workflow, set up WorkflowRuntime, and orchestrate multi-step processes with durable execution
- [Managing Workflows](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/12-managing-workflows): Master workflow lifecycle operations: starting, querying, raising events, and cleaning up workflow instances using both Python SDK and CLI
- [Workflow Patterns: Chaining & Fan-Out](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/13-workflow-patterns-chaining-fanout): Master task chaining for sequential data pipelines and fan-out/fan-in for parallel processing with result aggregation in Dapr Workflows
- [Workflow Patterns: Saga & Monitor](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/14-workflow-patterns-saga-monitor): Implement saga pattern with compensation activities for transactional consistency and monitor pattern with continue_as_new for eternal workflows
- [Combining Actors with Workflows](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/15-combining-actors-workflows): Design hybrid systems using actors for entity state and workflows for orchestration to build stateful, fault-tolerant agent systems
- [Multi-App Workflows](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/16-multi-app-workflows): Implement cross-service workflow orchestration using Dapr's multi-app workflow capabilities, calling activities and child workflows across different services while handling distributed failure scenarios
- [Namespaced Actors for Multi-Tenancy](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/17-namespaced-actors): Configure Dapr actors for multi-tenant SaaS deployments with namespace isolation, separate state stores, and tenant-safe placement
- [Actor Security Essentials](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/18-actor-security): Secure actor state with encryption at rest, verify mTLS for actor-to-actor communication, implement API token authentication, and configure audit logging for production actor deployments.
- [Capstone: Stateful Task Agent with Workflows](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/19-capstone-stateful-agent): Build a complete Digital FTE by integrating TaskActor for entity state, ChatActor for conversations, and TaskProcessingWorkflow with saga compensation on Docker Desktop Kubernetes
- [Finalize Your Dapr Skill](/docs/deploying-agent-factories-in-the-cloud/87-dapr-actors-workflows/20-finalize-dapr-skill): Complete your dapr-deployment skill with actor and workflow patterns, validate code generation, and document your Digital FTE component
- [Build Your Cloud Security Skill](/docs/deploying-agent-factories-in-the-cloud/88-production-security/00-build-your-cloud-security-skill): Create your cloud security skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 88: Production Security & Compliance](/docs/deploying-agent-factories-in-the-cloud/88-production-security/overview): Secure Kubernetes deployments with RBAC, NetworkPolicies, Pod Security Standards, and compliance controls
- [Cloud Native Security Model](/docs/deploying-agent-factories-in-the-cloud/88-production-security/01-cloud-native-security-model): Learn the 4C security model (Cloud, Cluster, Container, Code) and understand why defense in depth is essential for Kubernetes workloads
- [RBAC Deep Dive](/docs/deploying-agent-factories-in-the-cloud/88-production-security/02-rbac-deep-dive): Implement Kubernetes RBAC for Task API with ServiceAccounts, Roles, and RoleBindings following the principle of least privilege
- [NetworkPolicies for Zero-Trust Traffic Control](/docs/deploying-agent-factories-in-the-cloud/88-production-security/03-network-policies): Implement default-deny NetworkPolicies with explicit allow rules to reduce blast radius and control east-west traffic in your Kubernetes cluster
- [Secrets Management](/docs/deploying-agent-factories-in-the-cloud/88-production-security/04-secrets-management): Create and consume Kubernetes Secrets securely using volume mounts, understanding the secrets hierarchy from K8s Secrets to External Secrets Operator
- [Pod Security Standards: Hardening Container Workloads](/docs/deploying-agent-factories-in-the-cloud/88-production-security/05-pod-security-standards): Apply Pod Security Standards (PSS) namespace labels and write compliant pod specifications for the Restricted profile to prevent container escapes and privilege escalation
- [Image Scanning and Supply Chain Security](/docs/deploying-agent-factories-in-the-cloud/88-production-security/06-image-scanning-supply-chain): Scan container images with Trivy, understand vulnerability severity levels, generate SBOMs, and integrate security gates into CI/CD pipelines
- [Dapr Security: mTLS, API Tokens, and Component Scopes](/docs/deploying-agent-factories-in-the-cloud/88-production-security/07-dapr-security): Configure Dapr security features including mTLS verification, API token authentication, and component scopes to isolate your Task API resources in production
- [Compliance Fundamentals: SOC2 and HIPAA Awareness](/docs/deploying-agent-factories-in-the-cloud/88-production-security/08-compliance-fundamentals): Identify Kubernetes controls that support SOC2 and HIPAA compliance requirements, understand audit evidence collection, and map security primitives to regulatory frameworks
- [Capstone: Secure Task API](/docs/deploying-agent-factories-in-the-cloud/88-production-security/09-capstone-secure-task-api): Apply all security patterns from Chapter 88 to produce a production-ready Task API with a 10-point security audit, penetration test scenarios, and comprehensive security documentation
- [Chapter Assessment](/docs/deploying-agent-factories-in-the-cloud/88-production-security/chapter-assessment): Use this assessment to verify Chapter 88 mastery—confirm each security control is understood, applied, and evidenced before moving on.
- [Security Checklist](/docs/deploying-agent-factories-in-the-cloud/88-production-security/security-checklist): The security checklist is a practical verification list to ensure every required control from Chapter 88 is implemented and validated.
- [Build Your Operational Excellence Skill](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/00-build-your-operational-excellence-skill): Create your operational excellence skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 89: Cost & Disaster Recovery](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/overview): Operational excellence for cost management, backup/recovery, and chaos engineering in Kubernetes
- [Cloud Cost Fundamentals](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/01-cloud-cost-fundamentals): Understand the three pillars of cloud costs and the FinOps cycle for managing Kubernetes expenses
- [Right-Sizing with VPA](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/02-right-sizing-with-vpa): Use the Vertical Pod Autoscaler to get recommendations and automatically adjust pod resource requests based on actual usage
- [OpenCost/Kubecost Visibility](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/03-opencost-visibility): Query Kubernetes cost allocation data with OpenCost to understand where cloud spending goes across namespaces, teams, and applications
- [FinOps Practices and Budget Alerts](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/04-finops-practices-budget-alerts): Implement cost allocation labels and progress through the FinOps maturity model from showback to chargeback
- [Backup Fundamentals](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/05-backup-fundamentals): Understand RTO, RPO, and the 3-2-1 backup rule for protecting your Kubernetes workloads from data loss
- [Velero for Kubernetes Backup and Restore](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/06-velero-backup-restore): Implement production-ready backup and restore procedures with Velero, including scheduled backups, database hooks, and recovery verification
- [Chaos Engineering Basics](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/07-chaos-engineering-basics): Learn hypothesis-driven resilience testing with Chaos Mesh to validate your Kubernetes applications recover from failures
- [Data Sovereignty and Compliance](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/08-data-sovereignty-compliance): Understand legal requirements for data residency and design backup strategies that meet regulatory compliance
- [Capstone: Resilient, Cost-Aware Task API](/docs/deploying-agent-factories-in-the-cloud/89-cost-disaster-recovery/09-capstone-resilient-cost-aware-task-api): Integrate VPA, cost allocation, Velero backup, and chaos engineering into a production-ready Task API deployment with verified operational excellence
- [Build Your Cloud Deployment Skill](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/00-build-your-cloud-deployment-skill): Create your multi-cloud-deployer skill in one prompt, then learn to improve it throughout the chapter
- [JIT Chapter 90: Real Cloud Deployment](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/overview): Deploy AI agent services to production Kubernetes clusters on real cloud providers. Master the universal pattern: provision, connect, deploy.
- [Beyond Docker Desktop](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/01-beyond-docker-desktop): Why production deployments require real cloud infrastructure and the managed vs self-managed Kubernetes tradeoffs
- [DigitalOcean Account & doctl Setup](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/02-digitalocean-account-setup): Create a DigitalOcean account, install doctl CLI, and authenticate using API token
- [Provisioning DOKS Cluster](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/03-provisioning-doks-cluster): Create a DigitalOcean Kubernetes cluster using doctl, understand cluster options, and connect kubectl
- [Cloud Load Balancer & DNS](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/04-cloud-load-balancer-dns): Understand how cloud LoadBalancer services differ from local NodePort and configure DNS for real domains
- [Deploying Task API to DOKS](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/05-deploying-task-api-to-doks): Deploy the complete Task API stack with Dapr, Traefik Ingress, and cert-manager TLS to DigitalOcean Kubernetes
- [Production Secrets & Configuration](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/06-production-secrets-configuration): Manage secrets and configuration in cloud environments using Kubernetes Secrets, ConfigMaps, and cloud-native patterns
- [Personal Cloud Lab - Hetzner + K3s](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/07-personal-cloud-lab-hetzner): Set up a budget-friendly ~$5/month personal Kubernetes lab using Hetzner Cloud and hetzner-k3s CLI
- [Production Checklist & Verification](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/08-production-checklist-verification): Validate cloud deployment against production readiness criteria including health checks, resource limits, and monitoring
- [Same Patterns, Different Clouds](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/09-same-patterns-different-clouds): Discover that kubectl, Helm, Dapr, and Ingress commands are identical across cloud providers—only provisioning differs
- [Capstone: Full Production Deployment](/docs/deploying-agent-factories-in-the-cloud/90-real-cloud-deployment/10-capstone-full-production): Complete an end-to-end production deployment using specification-first approach, producing a deployable Digital FTE component
- [Meet Your Personal AI Employee](/docs/meet-your-personal-ai-employee/overview): OpenClaw proved that AI Employees are real, they work, and people want them.
- [The AI Employee Moment](/docs/meet-your-personal-ai-employee/01-ai-employee-moment): Understand what defines an AI Employee across five architectural dimensions, then discover why ownership is the sixth dimension that makes OpenClaw's version a Personal AI Employee.
- [Install & Connect Your Employee](/docs/meet-your-personal-ai-employee/02-install-and-connect): Install OpenClaw from scratch, survive the crash loop, connect WhatsApp/Telegram/Discord, and send your first message to a working AI Employee.
- [Delegate Real Work](/docs/meet-your-personal-ai-employee/03-delegate-real-work): Send two tasks to your AI Employee while watching the dashboard, discover the agent loop through live observation, and hit the boundary that proves this agent has real power under real constraints.
- [Customize Your Employee's Brain](/docs/meet-your-personal-ai-employee/04-customize-your-employees-brain): Edit the workspace files that compose your agent's system prompt, prove with /context list when edits actually take effect, and discover the BOOTSTRAP self-configuration pattern.
- [Memory & Commands](/docs/meet-your-personal-ai-employee/05-memory-and-commands): Store preferences that survive across sessions, verify memory writes on disk and in the dashboard, use memory_search and memory_get to find old notes, learn the three real paths to MEMORY.md (manual, compaction memory flush, dreaming deep phase), enable opt-in dreaming and active memory, and discover slash commands that bypass the model entirely.
- [Install & Author Agent Skills](/docs/meet-your-personal-ai-employee/06-install-skills-discover-ecosystem): Install skills from skills.sh and ClawHub, invoke them as slash commands, author your own with skill-creator, and let Skill Workshop capture procedural memory automatically.
- [Connect External Tools](/docs/meet-your-personal-ai-employee/07-connect-external-tools): Configure the mcp-server-time MCP server with one command, learn gateway-level versus workspace-level config, master the silent failure pattern, and understand the three transport options (stdio for local, SSE and streamable-http for remote).
- [Plugins, Bundles & The Decision Tree](/docs/meet-your-personal-ai-employee/08-plugins-bundles-decision-tree): Discover that channels and model providers ARE plugins, tour the bundled plugin ecosystem, install a bundle plugin for a real domain need, and earn the four-way decision tree for choosing the right extension type.
- [Make It Proactive](/docs/meet-your-personal-ai-employee/09-make-it-proactive): Enable heartbeats and cron jobs to make your agent act on its own schedule. Write a HEARTBEAT.md, understand the Agent OS mental model, and learn why one heartbeat costs less than five cron jobs.
- [Give It a Voice](/docs/meet-your-personal-ai-employee/10-give-it-a-voice): Enable text-to-speech on WhatsApp with three bundled providers, learn the four TTS modes, and discover why letting the agent decide when to speak is the smartest option.
- [Add a Second Agent](/docs/meet-your-personal-ai-employee/11-add-a-second-agent): Create a second agent on the same WhatsApp number, configure channel binding and routing, set agent identity, and understand why session cache means identity changes only apply to new conversations.
- [Connecting Google Workspace](/docs/meet-your-personal-ai-employee/12-connecting-google-workspace): Connect your AI Employee to Gmail, Calendar, and Drive using gog, experience the moment your agent processes real email, and confront the security implications of OAuth access
- [Orchestrate Other Agents](/docs/meet-your-personal-ai-employee/13-orchestrate-other-agents): Delegate tasks with sessions_spawn, control Claude Code via ACP from WhatsApp, understand the two-layer concurrency model, and learn why model quality determines whether orchestration works at all.
- [Gate Your Agent's Tools](/docs/meet-your-personal-ai-employee/14-gate-your-agents-tools): Specify a TypeScript plugin that intercepts tool calls and requires operator approval on WhatsApp, then have your AI Employee build it from a constraint-driven prompt referencing this lesson.
- [Deploy to Production](/docs/meet-your-personal-ai-employee/15-deploy-to-production): Deploy your AI Employee from laptop to a $5/month VPS, survive the paper cuts, and verify production health through an SSH tunnel.
- [Isolate with NemoClaw](/docs/meet-your-personal-ai-employee/16-isolate-with-nemoclaw): Understand NemoClaw's 4-pod architecture where API keys live in a separate process the agent cannot reach, and learn when $10 more per month is worth the security upgrade.
- [Chapter 56: Meet Your Personal AI Employee Quiz](/docs/meet-your-personal-ai-employee/17-chapter-quiz): A 50-question assessment covering AI Employee architecture, OpenClaw platform mastery, security models, deployment patterns, and production readiness across all 17 lessons of Chapter 56.