Generative AI in the Enterprise — RAG & AI Agents
Build real enterprise AI systems — a grounded RAG search, then AI agents, then a multi-agent setup — all with no-code tools, on one deliberately messy simulated company.
A hands-on course that takes you from "what is generative AI" to a working multi-agent system in seven weeks — using no-code tools like Dify and Claude Cowork, not a programming language. It's not a theory seminar: every class you build, on a single simulated company. You progress through foundations → enterprise search (RAG) → agents → production, and the architecture you learn outlasts the tool names that change every month.
Who it's for — Knowledge workers who want to build serious enterprise AI systems — RAG, agents, and evaluations — without writing code. Ambitious and technical in spirit, but no programming required.
- Build and tune a production-grade RAG system over messy enterprise data
- Design chunking, hybrid search, reranking, and evaluation for retrieval quality
- Build AI agents that use tools and SQL via MCP, with least-privilege design
- Orchestrate multi-agent systems with delegation, guardrails, and observability
- Evaluate agents against held-out question sets and surface data-quality issues
- Apply enterprise guardrails, governance, and EU AI Act basics
You leave with A multi-agent system where a CEO orchestrator delegates to specialist sales and finance analysts.
These aren't demos — they're working agents you build hands-on and tailor to your own role, data, and custom spec.
Sales Analyst Agent (V0→V5)
An agent built version by version that answers tabular, narrative, and compound sales questions by writing its own SQL and routing to a RAG skill—while auditing the data for duplicate keys and typo-twin records rather than trusting the surface numbers.
Financial Controller Agent
An agent that reconciles raw sales data against the CFO's published quarterly results and surfaces the figures that don't match.
CEO Orchestrator Agent
A supervisor agent holding no data tools of its own that answers from a scoped email/Slack knowledge base and delegates every sales and finance question to the specialist agents over two-way MCP—a least-privilege multi-agent system.
How you build them, class by class
Foundations
- Neural nets, transformers, inference, tokens, context windows
- Embeddings and cosine similarity; why models hallucinate
- Prompting, chain-of-thought, and context engineering
- Token economics and the enterprise AI landscape
Enterprise Search (RAG)
- RAG: ingestion, chunking, vector databases, metadata
- Hybrid search, rerankers, contextual retrieval, Graph & Agentic RAG
- The LLM Wiki: synthesis across documents
- Evaluation, guardrails, and the EU AI Act
AI Agents
- Agent architecture, tools, MCP and A2A protocols, skills
- Build the your Sales Analyst agent version by version (V0→V5)
- Rebuild it in Claude Cowork; Claude Code in practice
- Agent patterns, failure modes, and self-improving agents
Multi-Agent & Production
- Multi-agent systems, agency, and orchestration
- Security, governance, and the agentic enterprise landscape
- Final: a multi-agent CEO-style assistant for an enterprise, connected over MCP
- Least-privilege design and snapshot-before-write safety
Your hands-on capstone: a multi-agent CEO-style assistant for an enterprise — an orchestrator that delegates sales questions to your Sales Analyst Agent and finance questions to a Controller Agent, connected over MCP under least-privilege design. It's the work your certificate is based on, and a portfolio-grade system you can show an employer.
Your certificate is based on what you build — not attendance.
Ready to build your AI agent?
A small, high-quality cohort for leaders — fully online, hands-on from minute one.