Agentic AI Engineering

Build practical AI agents that use Python, APIs, n8n, on-premise systems, and event-driven multi-agent orchestration - 2 days

Agentic AI is becoming a practical engineering discipline, not just a prompting technique. Technical teams are now expected to build systems where AI can interpret tasks, call tools, interact with APIs, automate workflows, coordinate with other agents, and operate within real enterprise constraints. Modern agent frameworks now emphasize tools, handoffs, guardrails, tracing, and structured execution, while automation platforms such as n8n provide AI-agent workflow capabilities with connected tools and memory. For on-premise environments, local inference platforms such as vLLM and Ollama support OpenAI-compatible interfaces, making it easier to connect enterprise agents to internal infrastructure without depending entirely on public cloud APIs. Apache Kafka and similar pub-sub systems remain suitable foundations for event-driven coordination between distributed services and agents.

This 2-day course is built for technical professionals who need to design and implement agentic AI solutions in practical environments. The course focuses on Python-based agent development, API integration, n8n automation, on-premise deployment considerations, and multi-agent orchestration using a pub-sub system such as Kafka. Kafka will be used only as a coordination mechanism; the course will not teach Kafka administration or internals.

The instructor has over 30 years of industry experience and will use real industry-demanded content instead of treating the subject as an academic exercise. The emphasis is on how agentic AI systems are actually designed, integrated, controlled, and operated in technical environments.

Learning Outcomes

By the end of this course, participants will be able to:

Understand the architecture and behavior of agentic AI systems
Design practical single-agent and multi-agent workflows
Build Python-based agents that use tools and APIs
Integrate agents with n8n workflows and webhooks
Connect agentic systems to internal and external APIs
Understand on-premise agent deployment requirements
Use a pub-sub system such as Kafka for multi-agent coordination
Design message contracts for agent-to-agent communication
Identify operational risks in production agentic AI systems

Prerequisites

Good Python scripting knowledge
Experience with REST APIs and JSON
Working understanding of Linux or server-side environments
Experience working with LLMs, prompts, and model APIs
Working knowledge of workflow automation concepts
Good understanding of enterprise IT or application environments

Training Outline

Agentic AI Fundamentals
1. What Agentic AI Means
  1. Agents versus chatbots
  2. Agents versus scripts
  3. Agents versus traditional automation
  4. Autonomy and control boundaries
  5. Planning, acting, observing, and correcting
2. Core Agent Architecture
  1. Model layer
  2. Instruction layer
  3. Tool layer
  4. Memory and context layer
  5. State layer
  6. Guardrail layer
  7. Observability layer
3. Practical Technical Use Cases
  1. IT operations automation
  2. API-driven task execution
  3. Internal support assistants
  4. Workflow triage
  5. Incident enrichment
  6. Report generation
  7. Infrastructure request handling
Python-Based Agent Development
1. Python Environment Setup
  1. Virtual environments
  2. Dependency management
  3. Environment variables
  4. Configuration files
  5. Secrets handling
  6. Logging structure
2. Building Agents in Python
  1. Agent instructions
  2. Model client configuration
  3. Tool registration
  4. Function calling
  5. Structured inputs
  6. Structured outputs
  7. Runtime control
  8. Error handling
3. Agent Tool Design
  1. Tool purpose definition
  2. Tool input schema
  3. Tool output schema
  4. Tool validation
  5. Tool execution logging
  6. Tool failure handling
  7. Tool permission boundaries
API Integration for Agents
1. REST API Concepts for Agentic Systems
  1. HTTP methods
  2. Headers
  3. Authentication
  4. JSON payloads
  5. Response codes
  6. Pagination
  7. Rate limits
  8. Error responses
2. Agent-to-API Integration
  1. API client design
  2. API wrapper functions
  3. Request validation
  4. Response parsing
  5. Retry handling
  6. Timeout handling
  7. Result normalization
  8. Audit logging
3. Enterprise API Considerations
  1. Internal service endpoints
  2. API gateways
  3. Service accounts
  4. Access control
  5. Certificates
  6. Firewall rules
  7. Sensitive data handling
n8n for Agentic Workflow Automation
1. n8n Workflow Foundations
  1. Trigger nodes
  2. Action nodes
  3. Conditional branches
  4. Data mapping
  5. Webhooks
  6. Credentials
  7. Execution history
  8. Error paths
2. n8n AI Agent Workflows
  1. AI agent node concepts
  2. Prompt configuration
  3. Tool connections
  4. Memory usage
  5. Input mapping
  6. Output mapping
  7. Human approval steps
  8. Workflow retries
3. Python and n8n Integration
  1. Calling Python services from n8n
  2. Calling n8n webhooks from Python
  3. Passing JSON between systems
  4. Managing correlation IDs
  5. Handling callbacks
  6. Coordinating execution status
On-Premise Agentic AI Architecture
1. On-Premise Deployment Drivers
  1. Data residency
  2. Internal security policies
  3. Restricted networks
  4. Latency requirements
  5. Cost control
  6. Enterprise integration needs
2. On-Premise Components
  1. Local model serving
  2. Agent runtime services
  3. n8n automation layer
  4. API gateway
  5. Pub-sub layer
  6. Secrets management
  7. Logging and monitoring
  8. Storage and state
3. Local Model Serving
  1. OpenAI-compatible endpoints
  2. vLLM integration considerations
  3. Ollama integration considerations
  4. Model endpoint configuration
  5. Context limits
  6. Latency considerations
  7. Capacity planning
4. Security and Operations
  1. Network segmentation
  2. TLS and certificates
  3. Credential storage
  4. Service accounts
  5. Access review
  6. Audit logging
  7. Backup considerations
  8. Change control
Multi-Agent System Design
1. Multi-Agent Concepts
  1. Agent specialization
  2. Agent delegation
  3. Coordinator agents
  4. Worker agents
  5. Validator agents
  6. Human escalation agents
  7. Shared versus private state
2. Multi-Agent Interaction Patterns
  1. Sequential handoff
  2. Parallel task execution
  3. Supervisor-worker pattern
  4. Planner-executor pattern
  5. Reviewer pattern
  6. Human-in-the-loop pattern
  7. Event-driven pattern
3. Agent Communication Design
  1. Message structure
  2. Task identifiers
  3. Correlation identifiers
  4. Agent identifiers
  5. Status fields
  6. Error fields
  7. Audit metadata
Multi-Agent Orchestration with Pub-Sub
1. Pub-Sub Role in Agentic Systems
  1. Event-driven coordination
  2. Producer agents
  3. Consumer agents
  4. Topic-based routing
  5. Asynchronous processing
  6. Decoupled execution
  7. Task queues
  8. Result queues
2. Kafka Usage Scope
  1. Kafka as an event transport
  2. Kafka as a coordination backbone
  3. Kafka topics for agent tasks
  4. Kafka producers for agent outputs
  5. Kafka consumers for agent workers
3. Event Flow for Multi-Agent Workloads
  1. Task request event
  2. Task accepted event
  3. Task progress event
  4. Tool execution event
  5. Agent handoff event
  6. Validation event
  7. Approval request event
  8. Completion event
  9. Failure event
4. Failure Handling
  1. Retry events
  2. Timeout handling
  3. Duplicate message handling
  4. Dead-letter topic concepts
  5. Partial failure handling
  6. Agent unavailability handling
  7. Human escalation

Disclaimer

This course outline is provided as a professional planning guideline and does not constitute a fixed or binding delivery specification. The trainer reserves the right to amend, restructure, expand, reduce, replace, or adjust any topic, sequence, tool, demonstration, exercise, or technical emphasis without prior notice, based on participant readiness, classroom progress, available infrastructure, technology changes, operational constraints, and the trainer’s professional judgment.

Practical, connected learning

My wider training approach brings hands-on implementation and systems thinking together, connecting technology with real operational needs.

Agentic AI Engineering