Overview
Product Information on GitHub Copilot
Updated 13th October 2025
What is GitHub Copilot?
GitHub Copilot Pricing
Overall experience with GitHub Copilot
Software Engineer
250M - 500M USD, SoftwareFAVORABLE
“Recent Updates Streamline Automated Testing and Framework Development With GitHub Copilot”
Using GitHub Copilot has become a daily habit for my Selenium/java work. It's not just a fancy autocomplete anymore, the recent updates in have turned it into a proper coding partner. Having our automated test framework on GitHub makes the integration seamless. I use it mostly for boilerplate code, like generating those repetitive page object methods or writing snippets for our api tests. It's incredibly fast at picking up the patterns in the codebase, so it knows exactly how to name the variables and structure the tests without me having to explain it every time.
The Copilot agent integration is the real game changer here. Unlike the standard suggestions, the agent can now look at my entire workspace and handle more complex tasks like refactoring an entire test suite or fixing a tricky race condition in our selenium scripts. I can just @workspace in the chat and ask it to find all tests that don't have proper teardown logic and it highlights them and offers a fix in seconds. It's also great for generating documentation for our test cases, which is something I used to spend way too much time on.
I use copilot when I want to stay in the flow and write the code myself but with a lot of help. I use it for quick fixes and real-time suggestions, whereas I send the bigger, more time-consuming tasks over to other AI tools that I also use along with Copilot. Together, they make a powerful team. Copilot helps me with the logic and small details, and the other one handles the heavy lifting of building entire scenarios from scratch.
It still has those moments where it suggests code that looks right but is actually slightly outdated it doesn't perfectly match our custom framework wrappers. Also, if I am working on a very large file, it can sometimes lose the context of what I was doing three hundred lines up. And just like with other tools, there's always that slight concern about it being a bit hallucinatory with library versions if it has not seen the latest updates yet. But honestly, for the speed and accuracy it provides in my daily Java development, it's hard to imagine going back to coding without it.
Engineer
1B - 3B USD, RetailCRITICAL
“Github Integration Enhances Code Review While Data Analysis Accuracy Remains Inconsistent”
It is one of the best AI code assistants out there that helps you select between the agents (Ask, edit, plan) along with the model selection of your choice.
About Company
Company Description
GitHub is a platform where developers, businesses, and organizations collaborate to create and innovate. Offering tools for version control, CI/CD, security, and code review, GitHub helps teams build software efficiently and securely. With GitHub Copilot, developers can leverage AI to receive real-time coding assistance, streamlining their workflows and enabling them to focus on solving complex challenges. The platform supports a wide range of projects, from open source to enterprise, while integrating seamlessly into development processes to foster collaboration and security. As part of Microsoft, GitHub is committed to empowering developers and organizations to bring their ideas to life, working toward the goal of supporting 1 billion developers worldwide.
Company Details
Company type
Public
Year Founded
2008
Head office location
San Francisco, United States
Number of employees
2500 - 4999
Annual Revenue
1B-3B USD
Website
Do You Manage Peer Insights at GitHub?
Access Vendor Portal to update and manage your profile.
Key Insights
A Snapshot of What Matters - Based on Validated User Reviews
Top GitHub Copilot Alternatives
Peer Discussions
What Your Peers Are Saying About GitHub Copilot
VP of IT
What is the level of accuracy of GitHub copilot as code quality tool according to the following parameters? a. Syntax and Correctness b. Code Quality and Best Practices c. Security d. Context Awareness e. Refactoring and Optimization f. Language-Specific AccuracyCEO
See Full DiscussionI recognize I may not be addressing the question directly, but even if large language models (LLMs) like GitHub Copilot are not yet at the level required for complete autonomy, isn't it reasonable to anticipate that, over time, their ability to learn patterns from our codebase will evolve to a point where human intervention becomes significantly less frequent? With this in mind, I believe the focus should be on preparing for that future—gradually adopting copilots and leveraging empirical data to guide their implementation and integration into workflows.
Group Solutions Leader
How are large global companies implementing gen AI solutions as part of their larger AI strategy? As an example, there are three primary approaches, as per McKinsey:
In “Taker” use cases, companies use off-the-shelf, gen AI–powered software from third-party vendors such as GitHub Copilot or Salesforce Einstein to achieve the goals of the use case.
In “Shaper” use cases, companies integrate bespoke gen AI capabilities by engineering prompts, data sets, and connections to internal systems to achieve the goals of the use case.
In “Maker” use cases, companies create their own LLMs by building large data sets to pre-train models from scratch. Examples include OpenAI, Anthropic, Cohere, and Mistral AI.COO
See Full DiscussionFrom discussion with peers in banking and financial services, the 'taker' model is popular to 'dip their toes' into the Gen AI solutions. Often run as pilots or from existing partnerships with say Microsoft, this provides a low risk entry point into Gen AI.
GitHub Copilot Reviews and Ratings
Filter Reviews
Sort By:
Most helpful
Last 12 Months
Star Rating
Reviewer Type
Reviewer's Company Size
Reviewer's Industry
Reviewer's Region
Reviewer's Job Function
- Software Engineer50M-1B USDSoftwareReview Source
Recent Updates Streamline Automated Testing and Framework Development With GitHub Copilot
Using GitHub Copilot has become a daily habit for my Selenium/java work. It's not just a fancy autocomplete anymore, the recent updates in have turned it into a proper coding partner. Having our automated test framework on GitHub makes the integration seamless. I use it mostly for boilerplate code, like generating those repetitive page object methods or writing snippets for our api tests. It's incredibly fast at picking up the patterns in the codebase, so it knows exactly how to name the variables and structure the tests without me having to explain it every time. The Copilot agent integration is the real game changer here. Unlike the standard suggestions, the agent can now look at my entire workspace and handle more complex tasks like refactoring an entire test suite or fixing a tricky race condition in our selenium scripts. I can just @workspace in the chat and ask it to find all tests that don't have proper teardown logic and it highlights them and offers a fix in seconds. It's also great for generating documentation for our test cases, which is something I used to spend way too much time on. I use copilot when I want to stay in the flow and write the code myself but with a lot of help. I use it for quick fixes and real-time suggestions, whereas I send the bigger, more time-consuming tasks over to other AI tools that I also use along with Copilot. Together, they make a powerful team. Copilot helps me with the logic and small details, and the other one handles the heavy lifting of building entire scenarios from scratch. It still has those moments where it suggests code that looks right but is actually slightly outdated it doesn't perfectly match our custom framework wrappers. Also, if I am working on a very large file, it can sometimes lose the context of what I was doing three hundred lines up. And just like with other tools, there's always that slight concern about it being a bit hallucinatory with library versions if it has not seen the latest updates yet. But honestly, for the speed and accuracy it provides in my daily Java development, it's hard to imagine going back to coding without it. - Sdet10B+ USDBankingReview Source
AI-Assisted Coding Offers Speed Gains with Limitations in Context and Compliance
Overall, our experience with GitHub Copilot has been positive , particularly in improving developer productivity and reducing time spent on repetitive coding tasks. The tool has evolved beyond simple code completion into a more contextual AI assistant that can help with code generation, documentation, and basic troubleshooting, As it transitions toward more agent -like capabilities, Copilot shows potential to support more complex workflows such as multi-step code generation and assisted problem solving. However , it still requires careful human oversight , especially in enterprise environments where code quality, security , and compliance are critical. When used thoughtfully, it acts as a strong productivity enhancer rather than a replacement for developer expertise. - Manager, Project Management10B+ USDConsumer GoodsReview Source
Positive Copilot Adoption, but needs more enterprise flexibility and clearer metrics
OVerall, our experience with GitHub has been 4 out of 5. They are making a real effort to work with us, collaborate, and create good review channels. We appreciate their engagement and willingness to move things forward. However, at times it feels like our feedback is heard but not fully acted on. There is also a lack of clear commitment to timelines, which creates uncertainty for our team. Clearer follow through and more defined deadlines would strengthen the partnership. - Module Lead1B-10B USDSoftwareReview Source
AI-Assisted GitHub Copilot Improves Productivity and Coding Efficiency along with seamless IDE integration.
After using GitHub Copilot for a long time, I can say that it is a fantastic tool that helps enhance code quality by making use of AI assistance. The primary objective of deployment was to help the team reduce manual coding time, enable the team to focus on more time-consuming tasks and help them resolve repetitive tasks. This has helped the team greatly with syntax correction. This speeds up the development of simple and common function libraries. Code checks are also automated. Overall, it has helped to commit to a better coding standard that aligns with the organizational requirements. The development process has been made more stable and robust. Deployment was fairly easy and the IDE integration was straight forward. - Engineer1B-10B USDBankingReview Source
GitHub Copilot Boosts Productivity but Struggles With Large Codebase Complexity
GitHub Copilot integrates directly with IDEs like VS Code, making it relatively straightforward for developers to incorporate it into their existing workflows for writing and reviewing code. It works well for standard tasks like scaffolding out boilerplate code, suggesting implementations, and assisting developers with exploring unfamiliar APIs or frameworks. It is also pretty good at generating documentation from code, writing unit tests, and even refactoring small bits and pieces in a large codebase. It has definitely given developers a productivity boost as they use it as a companion as they code, especially when working with repetitive patterns or trying to understand unfamiliar parts of the code base. Overall, it compliments the development workflow really well.
...
Showing Result 1-5 of 467
Recommended Gartner Insights
This service may contain translations provided by Google. Google disclaims all warranties related to the translations, express or implied, including any warranties of accuracy, reliability, and any implied warranties of merchantability, fitness for a particular purpose and noninfringement. Gartner's use of this provider is for operational purposes and does not constitute an endorsement of its products or services.
