Centralize development context within GitHub
Bring your tools and their context into GitHub to reduce context switching.
Developers should leverage agent apps to bring the context and capabilities of their essential tools directly into GitHub.
By integrating tools like Amplitude, Endor Labs, LaunchDarkly, and PagerDuty via agent apps, developers can access data, perform security checks, manage feature flags, and assess deployment risks without leaving their GitHub workflow. This minimizes context switching and streamlines the entire software delivery process.
Instead of opening Amplitude to check user retention data, ask the Amplitude agent directly in GitHub. Instead of manually updating dependencies, ask the Endor Labs agent to check them within the pull request.
This heuristic suggests centralizing your development workflow within GitHub by using agent apps. This approach minimizes context switching, allowing developers to access and utilize tools like Amplitude, Endor Labs, LaunchDarkly, and PagerDuty directly within their GitHub environment for more efficient software delivery.
Reducing context switching by bringing necessary tools and their data into a single interface like GitHub allows developers to stay focused and act more efficiently on insights and tasks.
When the necessary agent apps are not available or when a specific tool's full interface is required for complex operations.
- How to bring your software delivery workflow into GitHub with agent apps ↗GitHub Blog · GitHub Blog: Copilot · Aug 14, 2026 · paraphrased
First seen on Subvolts Aug 14, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- How to bring your software delivery workflow into GitHub with agent appsMicrosoft · GitHub Blog: Copilot · Aug 14, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- Anti-patternCarrying context across multiple disconnected toolsAvoid manually switching between tools and re-entering context for each step of the SDLC. · 5 min
- ChecklistAX Practitioner Playbook Evaluation Quality ChecklistReview your AI agent evaluation process before running it to ensure its quality and trustworthiness. · 30 min
- WorkflowBuild and test an AI agent using Microsoft Foundry ToolkitCreate, configure, test, and evaluate an AI agent within VS Code. · 60 min
- ChecklistChecklist for production-ready AI agent refactoringSteps to ensure an AI agent is production-ready after refactoring. · 20 min
- Anti-patternLetting Models Write Evaluation CriteriaAvoid having AI models generate your evaluation criteria for AI agent performance. · 10 min
- HeuristicDon't Wait for Models to Improve for Your TechActively improve AI agent performance by controlling their information sources. · 15 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with Copilot in the sources.
- Where did this come from?
- GitHub Blog (GitHub Blog: Copilot). Subvolts collected, normalized and credited it; the link above opens the original.