We’re excited to partner with General Assembly to offer a curated selection of AI training courses on our pre-conference day, Monday, August 3, 2026. There are two distinct tracks available — one designed for business leaders and one tailored for technical attendees.
These courses are available as an add-on to your Ai4 2026 conference pass.
Please note:
- You must be fully registered for the Ai4 2026 conference before purchasing a training course ticket.
- If you purchase a training course but do not secure a valid conference pass, you will not be able to attend the training.
Schedule
Monday, August 3rd
Option 1: Business Track
Option 2: Technical Track
9:00AM
Conference Registration Opens
1:00PM – 5:00PM
Non-Technical Course: Gen AI & AI Agents for Business & Product Leaders
Technical Course: Agentic Ops & Retrieval-Augmented Generation (RAG) in Practice
5:00PM – 6:30PM
Industry Meetups & Kickoff Reception Begins
Monday, August 3rd
Option 1: Business Track
9:00AM
Conference Registration Opens
1:00PM – 5:00PM
Non-Technical Course: Gen AI & AI Agents for Business & Product Leaders
5:00PM – 6:30PM
Industry Meetups & Kickoff Reception Begins
Option 2: Technical Track
9:00AM
Conference Registration Opens
1:00PM – 5:00PM
Technical Course: Agentic Ops & Retrieval-Augmented Generation (RAG) in Practice
5:00PM – 6:30PM
Industry Meetups & Kickoff Reception Begins
Course Details
Choose the training track that best fits your role and experience.
Option 1: Business Track
Non-Technical Course:
Gen AI & AI Agents for Business & Product Leaders
Beginner-Intermediate, Non-Technical | 4 hours | $395
Monday, August 3, 1:00PM – 5:00 PM
Course Length: 4 Hours
Course Description: Beginner-Intermediate, Non-Technical
AI is reshaping product roadmaps across every industry. This workshop equips product leaders with the strategic toolkit to evaluate AI opportunities, run experiments, mitigate risk, and communicate clearly with engineering and executive stakeholders. You’ll explore AI-driven feature development, pricing implications, customer research patterns, and responsible rollout frameworks.
In this course, we’ll cover:
- How AI shifts product-market fit and competitive differentiation
- Frameworks for identifying and validating AI-powered features
- How to forecast impact and prioritize AI initiatives in your roadmap
- Responsible AI practices for trust, transparency, and ongoing model evaluation
Who Should Attend:
- Product managers, product directors, and heads of product
- Founders or operators building AI-enabled products
- Business leaders in charge of implementing AI strategy
Pre-Reqs: None. This is a non-technical track and requires no previous experience.
Option 2: Technical Track
Technical Track:
Agentic Ops & Retrieval-Augmented Generation (RAG) in Practice
Intermediate–Advanced, Technical | 4 hours | $395
Monday, August 3, 1:00PM – 5:00 PM
Course Length: 4 Hours
Course Description: Intermediate–Advanced, Technical
Format: Hands-on workshop (participants will be actively coding throughout)
Agentic Ops & Retrieval-Augmented Generation (RAG) has become one of the most powerful patterns in applied AI—but building a high-performing, production-ready RAG pipeline requires more than plugging documents into a vector store. This intensive 4-hour session is designed for technical practitioners who want to refine their RAG architectures, evaluate tradeoffs, and implement advanced techniques that meaningfully improve accuracy, latency, and reliability.
Participants will code along with instructors to experiment with embeddings, chunking strategies, routing, hybrid search, retrieval fusion, and evaluation frameworks. You’ll leave with working notebooks, templates you can adapt for real systems, and a deep mental model of what actually moves performance.
In this course, we’ll cover:
- Architecting Robust RAG Pipelines
- Dense vs. sparse retrieval, hybrid ranking stacks, and retrieval routing
- Designing multi-stage pipelines (pre-filter → retrieve → rerank → generate)
- Latency budgets and system-level performance consideration
- Advanced Chunking, Embeddings & Indexing
- Adaptive chunking heuristics for structured vs. unstructured data
- Embedding model selection criteria (domain specificity, multilingual, cost/perf)
- Indexing patterns: HNSW, IVF-Flat, PQ, hybrid indices, memory optimization
- Retrieval & Reranking Techniques (Hands-On)
- Implementing cross-encoder rerankers
- Experimenting with ColBERT-style late interaction
- Vector store configuration tuning (Faiss, Milvus, Weaviate, Elastic)
- Guardrails, Observability & Evaluation
- Hallucination mitigation strategies using retrieval-level signals
- Automated RAG evaluation: answer correctness, grounding, context utilization
- Live instrumentation: tracing, latency tracking, prompt/response logging
- Putting It Together: Build & Benchmark an Advanced RAG Stack
- Small-group coding challenge building an end-to-end RAG system
- Benchmark across multiple retrieval configurations
- Discuss tradeoffs, scalability, and deployment pathways
Who Should Attend:
- Machine Learning Engineers
- Applied AI Engineers / LLM Engineers
- Data Scientists working with unstructured data
- Backend engineers implementing AI-powered features
Pre-Reqs:
Participants should be comfortable with….
- Python
- Working in notebooks (Jupyter/Colab)
- Basic vector database usage
- Familiarity with embeddings + simple RAG concepts