← All speakers

Bio, Work & Ideas

Christina Warren

Conference affiliation: GitHub · 2024

Christina Warren is a senior developer advocate at GitHub, former technology journalist, and co-host of MacBreak Weekly. She helps programmers make practical use of AI-assisted software development, drawing on experience at Microsoft, Google DeepMind, and GitHub.

From technology reporting to developer relations

Warren learned HTML and built websites before covering technology and digital culture for Mashable and Gizmodo. She moved into developer advocacy at Microsoft, working with Linux and open-source communities, and was a senior developer advocate there by 2021. By 2023, she held that role at GitHub, helping developers understand Copilot, Codespaces, and other developer tools.

During most of 2025, Warren worked in developer relations at Google DeepMind and co-hosted Google’s People of AI podcast, which featured developers, founders, and researchers building with AI. Her Seattle Gemini workshop extended that work into hands-on instruction. She returned to GitHub during the final weeks of 2025.

  • Context-aware coding assistance. Warren teaches developers to ground coding assistants in relevant files, selected code, descriptive names, explicit requirements, and representative examples. Better context produces more useful suggestions; vague instructions invite generic answers.
  • Developer judgment remains central. Experienced programmers often benefit most because they understand established codebase patterns and can assess generated tests, boilerplate, explanations, and potential fixes. At the AI Engineer World’s Fair, Warren emphasized revising prompts, inspecting outputs, and accounting for hallucinations while guiding participants through Copilot and browser-based Codespaces.

Read the topics behind these talks

1 conference talk

Key ideas

Scroll to read ↓

A hands-on path through Copilot in VS Code, from supplying useful context and reviewing JavaScript suggestions to understanding model latency, extensions, and multistep development.

  • What does Copilot need to help you write code?
    0:30 ↗
  • From editor context to a suggestion
    3:07 ↗
  • Make the request—and its context—explicit
    7:21 ↗
  • Good names and concrete examples reduce ambiguity
    14:22 ↗
  • Prepare the workshop environment
    19:27 ↗
  • Find the right participant and open a JavaScript file
    29:33 ↗
  • Ghost text, inline edits, and conversation
    36:22 ↗
  • Accept only the part you want
    41:22 ↗
  • Generate a URL parser, then inspect the repair
    47:00 ↗
  • Explain code, reset context, and generate tests
    50:36 ↗
  • Model quality has to fit the interaction
    59:30 ↗
  • Extend chat without assuming full model replacement
    1:04:22 ↗
  • Updated knowledge and automatic delegation solve different problems
    1:07:24 ↗
  • From a reviewed suggestion to a reviewed plan
    1:13:33 ↗

References