Bringing the power of AI to your application.

Stop treating LLMs like a machine learning problem. A GitHub engineer shows you how to integrate AI into your app like any other powerful API.

#1about 4 minutes

A software developer's perspective on building AI prototypes

This talk focuses on the practical process of building AI application prototypes, distinct from deep machine learning research or full-scale product deployment.

#2about 4 minutes

Understanding the basics of large language models

Large language models are general-purpose, probabilistic systems that predict the next word, requiring careful guidance to perform specific tasks.

#3about 4 minutes

Crafting effective prompts to steer AI behavior

Prompt engineering involves defining a persona, describing the task, and using techniques like few-shot prompting or chain of thought to guide the model's output.

#4about 2 minutes

Enhancing AI responses with retrieval augmented generation

Retrieval augmented generation (RAG) is the process of pulling relevant, personalized context from various data sources to include in the prompt for better results.

#5about 4 minutes

How to observe and measure AI system performance

Since AI models are probabilistic, performance is measured at scale using offline evaluation frameworks and online A/B testing with user telemetry.

#6about 5 minutes

Designing user experiences with a human in the loop

Effective AI user experience design prioritizes user control, allows for error correction, and balances model accuracy with system latency.

#7about 2 minutes

Exploring common AI user interface patterns

AI interfaces range from inline suggestions and text transformations to chat, each with different implications for user workflow and control.

#8about 4 minutes

Building structured AI workflows for better control

Structured, multi-step AI workflows like Copilot Workspace give users control at key stages, improving accuracy and trust over a simple chat interface.

#9about 3 minutes

Considering the ethical responsibility of building AI systems

Developers have a responsibility to question whether AI is appropriate for a given application, especially in sensitive domains like finance or healthcare.