3 - Advanced AI
Leads to certification
Advanced AI

3 - Advanced AI

Advanced AI is a technical deep-dive for high-automation and technical roles. From advanced LLM and agent fundamentals to the Unique AI SDK, Model Context Protocol, GitHub Actions, and agentic coding with Claude Code — this curriculum equips developers and technical professionals with the skills to build, automate, and deploy AI-powered workflows at scale.

Curriculum content

  •
    This session provides a foundational vocabulary for interacting with large language models, covering just enough theory to ground hands-on work. We'll begin with the core parameters that steer model behavior, such as the context window , temperature , and top_p for controlling output, along with practical knobs like max_tokens and stop sequences . We will also explore the basics of tokenization for effective prompt and response budgeting and differentiate between system and user prompts . Building on this foundation, we'll examine advanced techniques, including Retrieval-Augmented Generation (RAG) for grounding models in external data, function calling for enabling tool use, and the concept of agents that combine these capabilities to autonomously execute complex tasks.

    • Lesson Quick Intro: LLM and Agent Fundamentals

  • This course introduces multi-agent systems and explains how to design and build them on the Unique AI platform. You will learn how a supervisor agent coordinates specialized subagents, when this architecture adds value over a single agent, and how to balance quality, cost, and response time in a real financial research workflow.

  • This course teaches developers how to build AI-powered applications on the Unique AI Platform using the Unique AI Toolkit . Across four modules, you will set up your environment, work with standalone services including the OpenAI-compatible API and Knowledge Base, build event-driven agents, and implement code execution in custom agents.

  • This course introduces the Model Context Protocol (MCP) and shows you how to build production-ready MCP servers using FastMCP. You will learn how AI applications connect to external systems, how to configure tools and resources, and how to implement secure authentication — without prior development experience required.

  • This course teaches developers how to build on the Unique AI platform using the public REST API and Python SDK. You will learn how the platform's four-layer architecture works, when to use the SDK over the Toolkit, and how to manage spaces, benchmarks, analytics, and language models programmatically.

  • This course introduces Unique AI Conduct , an experimental agentic feature for executing multi-step financial workflows, and skills , the  mechanism for encoding desk procedures and team conventions. Together, they enable AI assistants to deliver consistent, governed outputs — from client briefings to risk reports — without manual steering at every step.