AI for Technology Teams

Learning outcomes

What you will learn

• Audit your team's existing toolchain to identify where LLMs, embeddings, and retrieval systems could replace or augment current processes
• Write and iterate structured prompts for code review, incident summarization, and sprint planning using chain-of-thought and few-shot techniques
• Chunk, embed, and index an internal documentation corpus (Confluence, Notion, or Markdown repos) into a vector store such as Pinecone or pgvector
• Deploy an AI-assisted code review bot into a CI/CD pipeline using a GitHub Actions or GitLab CI webhook connected to an LLM API
• Design a layered architecture diagram for an internal AI tool covering ingestion, retrieval, generation, caching, and logging components
• Build a task-decomposition agent that breaks a product requirements document into discrete engineering tickets using tool-use and function-calling APIs
• Assemble a domain-specific evaluation dataset from internal engineering artifacts and run automated evals using an LLM-as-judge framework
• Map your team's AI systems against the Artificial Intelligence and Data Act (AIDA) high-impact system criteria to determine which products require formal compliance documentation
• Establish an internal AI review board charter with defined membership, escalation paths, and a decision log process for approving new AI use cases

Ideal participant

Who this program is for

Program features

What's included