← All speakers

Bio, Work & Ideas

Alex Malebranche

Conference affiliation: GitHub · 2024

Alex Malebranche is the founder of BoyTwigg, where he builds custom AI agents that streamline organizational work while preserving human judgment. His experience spans military intelligence, startup entrepreneurship, developer education, and founder programs at GitHub and Cloudflare.

Before entering technology, Malebranche served as a U.S. Army intelligence analyst and earned an accountancy degree from Miami University in 2015. His subsequent professional experience included Amazon, Amazon Web Services, Deloitte, Nestlé, and Braxton Brewing Company.

He founded PlaneAhead, a travel startup that monitored booked flights for price drops and recovered airline credits when cheaper fares became available. Miami University’s student-run RedHawk Ventures invested $25,000 in the company in 2022.

As global engagement lead for GitHub for Startups, Malebranche connected founders with developer tools, technical support, and investor networks; a Stripe Developers interview explores his approach. In 2024, he helped run a Stanford developer workshop and participated in an AI Engineer World’s Fair Copilot workshop, supporting hands-on experimentation with GitHub Codespaces and AI-assisted programming.

He subsequently joined Cloudflare to develop Cloudflare for Startups, cultivate venture-capital and accelerator partnerships, and support Workers Launchpad.

His work centers on three practical concerns:

  • Workflows over prompts: Build repeatable organizational processes around specific operational problems, keeping people involved where judgment matters.
  • Custom AI agents: Consolidate fragmented tasks such as legal-client intake, communications, scheduling, and document preparation.
  • Founder infrastructure and access: Connect early-stage companies with technical platforms, investors, accelerators, and communities, including events for underrepresented founders.

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