Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

Running a prompt in a playground is easy; turning the same flow into a reliable, observable and cost-controlled service is a separate engineering job. The course covers what the OpenAI Responses API, Anthropic Messages API and Gemini API share and where they differ, the official SDKs, streaming, conversation history, timeouts, retries, rate limits and API key security.

Throughout the course participants build a near-production LLM application on a scenario adapted to their organisation, including a provider abstraction, error and fallback design, and a basic eval set.

Who Should Attend?

  • Backend and full-stack developers adding LLM features to existing products
  • AI engineers turning prototypes into services
  • Platform teams responsible for integration and API standards
  • Prerequisite: experience building REST APIs in Python or TypeScript

Key Takeaways

  • Use the three major providers' APIs behind a common interface
  • Handle streaming responses and multi-turn conversation state correctly
  • Implement retries, exponential backoff, timeouts and fallbacks
  • Log and report token usage, cost and latency
  • Set up a development loop that validates changes against a basic eval set

Curriculum

Anatomy of LLM APIs
  • Comparing OpenAI Responses, Anthropic Messages and the Gemini API
  • Message roles, parameters and usage information
SDKs, Streaming and Conversation State
  • Streaming responses with the Python and TypeScript SDKs
  • Storing and trimming history in multi-turn conversations
Resilience: Errors, Retries and Fallbacks
  • Handling rate limits, timeouts and 5xx errors
  • Exponential backoff and switching to an alternative model
Provider Abstraction and Security
  • A common interface for multiple providers and gateways such as LiteLLM
  • API key management, personal data masking and KVKK considerations
Logging, Cost Tracking and Basic Evals
  • Recording token, cost and latency metrics
  • Regression checks with a small eval set
Project: A Near-Production LLM Application
  • Building an end-to-end service for an organisational scenario
  • Code review and a pre-production checklist

Other Courses in This Category

  • Structured Outputs with LLMs: JSON Schema, Pydantic and Constrained Decoding

    Getting reliable JSON from LLMs with JSON Schema, OpenAI Structured Outputs, Gemini response schemas, Pydantic/Zod, Instructor and constrained decoding, plus validation, repair loops and document data extraction.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • LLM Tool Use and Function Calling

    How to let LLMs safely call APIs, databases and internal systems via tool/function calling: tool schema design, parallel calls, MCP servers, error handling and permission boundaries.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • 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

Get in touch