Improving token efficiency in GitHub Agentic Workflows
Landon Cox & Mara Kiefer May 7, 2026 | Updated May 13, 2026 | 12 minutes 12 minutes Share: GitHub Agentic Workflows is like a team of street sweepers that clean up little messes in…
Landon Cox & Mara Kiefer May 7, 2026 | Updated May 13, 2026 | 12 minutes 12 minutes Share: GitHub Agentic Workflows is like a team of street sweepers that clean up little messes in…
…Control how deeply reasoning models (e.g., Claude Sonnet 4.6 and GPT-5.4) think before responding, and do this directly from the model picker. Your preference persists across conversations. Expand…
…Improvements to standard findings in public preview application security platform governance Apr.13 Release Data residency (US + EU) and FedRAMP-authorized models now available in Copilot copilot platform governance Apr.09 Improvement…
Featured An update on GitHub availability Here’s what we’ve done—and what we’re still doing—to improve our availability and reliability. GitHub Copilot is moving to usage-based billing…
…The first time you enable voice input, the CLI guides you through downloading the runtime and picking a speech-to-text model. Update GitHub Copilot CLI by running copilot update in your…
…Low poly 3D modeling Explore Explore Source Source GPL 3.0 GPL 3.0 Blockbench is a 3D model editor purpose built for low poly models with pixel art textures. It started…
…now supports sanitizers and validators in models-as-data application security Apr.15 Improvement CodeQL 2.25.2 adds Kotlin 2.3.20 support and other updates application security Back to top
…Improvements to standard findings in public preview application security platform governance Apr.13 Release Data residency (US + EU) and FedRAMP-authorized models now available in Copilot copilot platform governance Apr.09 Improvement…
…generate code from a design, send your UI back to Figma for iteration, and pull updates back into your codebase. This feature is available today in VS Code and coming soon to…
…We chose stored prompts over model fine-tuning so that anyone on the team can update the AI’s behavior through a pull request—no retraining pipeline, no specialized ML knowledge required…