Introducing Auto in GitHub Copilot for Visual Studio Code

View profile for Asha Sharma

President, CoreAI Product @Microsoft l Board Member @The Home Depot

Faster responses, fewer rate limits, and 10% off premium requests. We are launching auto, now available in Visual Studio Code! Auto picks the right model for the job in GitHub Copilot, chosen automatically based on capacity and performance. Great products these days are rarely powered by a single model. They rely on a system of models working together, each playing to its strengths. With auto, we are bringing that ensemble approach directly to customers.    Over time, auto will get smarter. It will dynamically scale between small and large models based on task complexity, and fold model selection into the development loop itself. 🔗 https://lnkd.in/gTHA-ZsR

  • graphical user interface, application
Phanindra M

Program Management | Client Solutions Delivery | MS in Engineering Management

1w

Game-changing move with GitHub Copilot’s ‘auto’—smart ensemble of LLMs (e.g., Claude Sonnet 4, GPT-5, mini) auto-selects for speed, capacity, cutting rate limits and offering 10% premium discounts. It evolves from single-model limits, mirroring cloud autoscaling for AI, potentially easing dev fatigue by 20-30% via adaptive orchestration. For bolder strides: Enable real-time intra-session model switching via on-device profiling (code context analysis), with “why this model?” tooltips and user overrides—could slash costs 40% in mixed workloads, enhancing transparency and domain fits like UI vision tasks. Pumped for the future! #AICoding #GitHubCopilot #DevTools

Like
Reply
Girraj Jangid ✨

Senior Data Scientist @ Koantek | Building Gen AI | Agents, LLMOps, and MLOps solutions for Enterprises & Startups.

5d

Amazing to see this new feature Asha Sharma

Like
Reply
Kalpit Jain

Partner - Agentic AI Platform @ AuxoAI | 2x Exited Founder | Ex-Google | Ex-Microsoft

1w

Each time I try Auto in Cursor, it more or less, disappoints... When time is money you want to choose the model you can trust most!

CHIKE EMMANUEL

Manager and Lead - Digital Adoption Hub at Reliance North America | Helping Organizations Maximize ROI on their Technology Investments | Business Innovation | Strategy

1w

This is exciting

Like
Reply
Chris Cade

CEO | Enterprise AI Agent Solutions | X-Microsoft Circle of Excellence | Hockey Enthusiast

6d

Great to see!!

Abbas Ali Aloc

Solution Architect | IT Leader | People-Process-Technology Organizer for Success in Critical Architectures | TOGAF, PMP and AZURE Certified

4d

Sounds like a smart, efficient way to optimize resource usage and improve the developer experience! Excited to see how Auto evolves.

Like
Reply
Eric D. Boyd

Founder/CEO at responsiveX, Microsoft Regional Director, Azure MVP, AI MVP

1w

Hey Asha. I have a question about your post. You used the word "ensemble". Is the auto feature in Visual Studio Code truly an ensemble where it does something like bagging or boosting, ultimately returning what is evaluated as the best result from multiple results across multiple models? Or is it "guessing" what it thinks is the best model to use based on the input prompt, and then ultimately routing?

Like
Reply
Dona Sarkar

Chief Troublemaker-Microsoft #AI and #Copilot Extensibility 🦉#CopilotLearningHub⚡️TED/UN/Keynote Speaker 🍷Chief Wine Officer at #SideHustleTaps 👗Fashion Biz Owner at #PrimaDonaStudios 📚Published Author

6d

Okay this is a cool functionality—so many of our customers have been asking for this. Thank you team!

See more comments

To view or add a comment, sign in

Explore content categories