Course Objective & Scope
Not every process needs a fully autonomous agent; in most enterprise scenarios the most reliable results come from workflows that carefully combine deterministic steps with LLM decisions. Starting from process analysis, the programme teaches proven patterns such as prompt chaining, routing, parallelisation, orchestrator–worker and evaluator–optimizer.
Participants model a process chosen from their own organisation (for example request classification and response drafting), build a working flow in n8n or Power Automate, insert human approval steps and produce a design document and checklist for the flow.
Who Should Attend?
- Process owners, business analysts and process excellence teams
- Automation (RPA, low-code) developers
- Solution architects designing agent solutions
- Prerequisite: basic experience with a workflow or automation tool is helpful
Key Takeaways
- Separate the steps in a process that need an LLM from those that need rules
- Select the right agentic workflow pattern for a task
- Build a working agentic flow in n8n or Power Automate
- Add human approval, error branches and quality checks to the flow
- Prepare the flow's design document and success criteria
Curriculum
Process Analysis and Agent Suitability
- Process mapping, decision points and exceptions
- Workflow or agent? Decision criteria
Core Agentic Patterns
- Prompt chaining, routing and parallelisation
- Orchestrator–worker and evaluator–optimizer
Implementation with Workflow Tools
- LLM and agent nodes in n8n and Power Automate
- Triggers, data transformations and integrations
Human Approval and Exception Handling
- Approval steps, escalation and fallback paths
- Error branches and safe defaults
Quality, Cost and Monitoring
- Output checks and example-based testing
- Tracking token cost and run logs
Case Study and Design Document
- Turning an organisational process into an end-to-end flow
- Design document and checklist
Other Courses in This Category
-
Developer programme on building autonomous agents with LangGraph, the OpenAI Agents SDK and the Claude Agent SDK: state management, tool integration, loop control, tracing and a deployment-ready agent for an organisational case.
- Live Course
- 6 modules
-
Technical programme on how agents plan and execute multi-step tasks: ReAct, plan-and-execute, task decomposition, reflection and replanning, using reasoning models, and loop termination strategies.
- Live Course
- 6 modules
-
Agent memory and context management for long-horizon tasks and multi-session interactions: working memory, episodic and semantic long-term memory, context compaction, and persistent memory architecture with Mem0 and LangGraph Store.
- Live Course
- 5 modules
-
Multi-agent architectures that split complex work across specialised agents: supervisor, hierarchical and swarm patterns, comparing LangGraph, CrewAI and AutoGen, the A2A protocol and shared state management.
- Live Course
- 5 modules
-
Human-in-the-loop agent architecture that preserves human oversight on critical actions: interrupt/resume flows, risk-based approval thresholds, escalation queues and agents that improve from human feedback.
- Live Course
- 5 modules
-
Connecting enterprise databases, APIs and internal systems to LLMs and agents cleanly and securely with Model Context Protocol (MCP): MCP server/client development, authorisation and enterprise integration architecture.
- Live Course
- 5 modules
Get in touch
