Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

Tool calling turns an LLM from a text generator into a component that can act on enterprise systems, but poorly designed tools lead to wrong calls, loops and security holes. The course covers the function calling flow in OpenAI, Claude and Gemini, tool description and parameter schema design, tool choice settings, parallel calls and feeding tool errors back to the model.

Participants write a Model Context Protocol (MCP) server to standardise tools, and work hands-on with confirmation steps for side-effecting actions, least privilege and prompt injection risks arriving through tool outputs.

Who Should Attend?

  • Software developers connecting LLMs to internal systems and APIs
  • AI engineers running agent and assistant projects
  • Platform teams responsible for integration and security policies
  • Prerequisite: LLM API usage and REST API knowledge

Key Takeaways

  • Write clear tool definitions and parameter schemas the model can select correctly
  • Implement multi-step and parallel tool calling loops with safe limits
  • Expose an existing internal service as an MCP server
  • Design confirmation and authorisation checks for side-effecting actions
  • Measure tool selection accuracy with test scenarios

Curriculum

The Function Calling Flow
  • The message loop between model, application and tool
  • Tool choice and parallel calls in OpenAI, Claude and Gemini
Tool Design and Schema Quality
  • Naming, descriptions and parameter design
  • Keeping selection accuracy as the number of tools grows
Error Handling and Loop Control
  • Returning tool errors to the model meaningfully
  • Maximum steps, timeouts and idempotency
Standardised Tools with the Model Context Protocol (MCP)
  • MCP server and client architecture
  • Publishing an internal service as an MCP server
Security and Authorisation
  • Least privilege, user-context authorisation and confirmation steps
  • Prompt injection via tool output and OWASP LLM risks
Hands-On: An Assistant Connected to Internal Systems
  • An assistant using multiple tools on an organisational scenario
  • A test set for tool selection accuracy

Other Courses in This Category

  • Prompt and Context Architecture for LLM Applications

    Context engineering for LLM applications: designing how system prompts, templates, few-shot examples, retrieved content, memory and tool definitions fill the context window, with versioning and eval-driven iteration.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Long-Context LLM Engineering and Context Window Management

    Solving lost-in-the-middle degradation, KV cache cost and latency in large context windows through context compression, hierarchical memory, prompt caching and needle-in-a-haystack evaluation.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Model Routing and Multi-Model Architecture Design

    Engineering programme on dynamic model routing, cascades, fallbacks and LLM gateways to balance quality, cost and latency across frontier and small models without single-provider lock-in.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Building Multimodal LLM Applications: Vision, Documents and Audio

    Hands-on programme for building multimodal LLM applications that process images, scanned documents, charts, audio and video using frontier VLM APIs, open-weight vision models and structured extraction.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Mixture of Experts (MoE) LLMs: Architecture, Serving and Fine-Tuning

    Advanced programme on sparse Mixture of Experts (MoE) LLMs, covering gating networks, active vs total parameters, VRAM sizing, expert parallelism in vLLM/SGLang and MoE fine-tuning.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Streaming and Real-Time AI Application Engineering

    Building low-latency streaming text, partial structured output and bidirectional voice AI applications using SSE, WebSockets and WebRTC, with TTFT optimisation, barge-in handling and concurrency control.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View

Get in touch