Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

In production LLM applications, quality depends less on a single "good prompt" than on what information reaches the model on each call and in what order. The course treats prompts as software components: layered system prompts, templating, few-shot example selection, placement of retrieved content and conversation memory, the context cost of tool definitions, and separating instructions from user data.

Tools such as Langfuse are used for prompt versioning and management, and promptfoo for eval-driven iteration that measures the impact of changes. Participants design a documented context architecture for one of their organisation's applications.

Who Should Attend?

  • Software and AI engineers building LLM applications
  • Architects responsible for the technical design of assistants and agents
  • Product and content teams accountable for prompt quality
  • Prerequisite: basic experience building applications with LLM APIs

Key Takeaways

  • Design layered, maintainable system prompts and templates
  • Budget the context window across instructions, examples, data and memory
  • Version, test and roll back prompts like code
  • Reduce the prompt injection surface by separating instructions from data
  • Base prompt decisions on measured impact using eval sets

Curriculum

From Prompt Engineering to Context Engineering
  • Components of an LLM call and their effect on quality
  • Instruction, example, data and memory layers
System Prompt and Template Design
  • Structuring role, rules, output format and boundaries
  • Variable injection and template libraries
Few-Shot Examples and Dynamic Context
  • Example selection and dynamic few-shot
  • Placing retrieved content and memory summaries
Context Budget and Prompt Security
  • Token budget, ordering and the cost of tool definitions
  • Instruction–data separation, delimiters and injection defences
Prompt Management, Versioning and Evals
  • Prompt registry and version tracking with Langfuse
  • Comparative testing and regression checks with promptfoo
Hands-On: Context Architecture Document
  • Designing context layers for an organisational application
  • Validating the design with eval results

Other Courses in This Category

  • 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
  • Small Language Models (SLMs) for Enterprise Applications

    Building fast, low-cost enterprise solutions with 1B–14B Small Language Models (Llama, Qwen, Gemma, Phi, Ministral) for classification, extraction and routing, including distillation and task adaptation.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View

Get in touch