GitHub Copilot: The World's Most Widely Adopted AI Developer Tool

Key Takeaways

[Music] so good morning everybody morning there we go my name is Dave bernes I'm a senior devops Advocate with GitHub and I want to talk today about GitHub co-pilot and demo a little bit of everything that co-pilot is today because it has the capabilities have grown a lot now over the last uh 2 three years so how many how many of you are using GitHub co-pilot today okay looks like half to 2third kind of a thing kind of a ratio or so here so yeah as we get started we can see GitHub copilot started out just as generating code in the IDE with co-pilot individual then we launched co-pilot business into ga uh shortly after that year and a half ago I guess that would be we launched co-pilot chat so now not only could you ask co-pilot to generate code for you but you could pick somebody's existing code maybe they didn't write very good comments in their code shocker right say hey co-pilot explain that code to me or help me simplify that code so many many more ways to use GitHub co-pilot and then just this February we launched GitHub co-pilot Enterprise being able to not only use co-pilot in your IDE of choice but also right on github.com itself have co-pilot help you generate poll request summaries or tap into information that may be stored in your knowledge bases and ask co-pilot questions uh and things like that and use a lot of the same chat features right there and I'll also talk about some of the things that um we're launching uh right now we've got in beta and and Technical preview and and such so as most of you know uh Gib co-pilot is there to be your AIP pair programmer help you uh generate code based on comments and things now the thing about co-pilot individual and co-pilot business it lives and runs extensions in Visual Studio code GitHub code spaces which is Visual Studio code running inside the browser the jet brains idees like py charm and intellig and visual studio and a key thing about this is it doesn't actually matter where your code lives right the code hopefully lives on GitHub GitHub Enterprise Cloud but the code could live in bitbucket or Azure devops even in team Foundation Version Control doesn't even have to be git-based Version Control and you can still take advantage of everything that co-pilot business and co-pilot individual have to offer so I am going to play through a little little video of the basics here because there's a couple of things I want to point out this is just a two-minute video let's see how co-pilot can make me a more productive developer I'm using Django python which like most programming languages and Frameworks is supported by co-pilot Jango is a framework for cre creating lined business applications and the first step is to create my model classes which is typically tedious what I'm going to do instead is describe using natural language what I need my model to look like that gray italicized text is copilot generating the appropriate code it creates the class definition and the full class across multiple lines of code copilot is also context aware it saw the fact that I created a speaker class and once again goes well speakers need to do something and it generates a talk class for me that entire class all of those lines of code was generated for me automatically by co-pilot there was one thing I didn't necessarily want here which is it's allowing for speakers and talks all to be delet it I want to modify that so I go back to co-pilot ask it for a new suggestion and it generates one finally I want to add on a code for the talk which matches a particular pattern normally at this point I would go running off to stack Overflow to look up how to write this regular expression instead I describe in natural language what that pattern is supposed to look like and copilot generates all of the appropriate code for me this allows me to stay in the zone and focus in on the more important aspects of writing code all right now I know that's a very basic demo and most of you who are using co-pilot have seen it and used it in this way but still there's some key things to point out here it's called GitHub co-pilot it's not called GitHub autopilot you know this is not going to replace developers we still need that person in the middle and there was a great example here of that you know when it generated uh the in the talk class initially it was allowing speakers to be deleted even when talks existed so he wiped out that line he continued the conversation with co-pilot added that additional comment to say hey no don't allow speakers to be deleted when talks exist and then he was able to get you know exactly what he needed in this case now another thing there's there's actually an opport opportunity here in this in even in this little demo to talk about prompt crafting or prompt engineering you know when when he was adding this talk code he didn't just say add a talk code he was more specific right he said with a format of three letters a dash and three numbers and that would allowed him to get back the regular expression that he needed so that you know part of prompt crafting is is that specificity in your comments in your requests and things but another key element here is he was able to stay in the flow he didn't have to leave the IDE and go to find some regular expression documentation or do a a Google search or anything like that to figure out that syntax he got that in a matter of seconds so you can see in a second actually you know so you can see just how much this can improve productivity and keep you in the flow and things like that now next we oh so here's some at the end I'll have a link where you can find a lot of these resources uh and things and at some point after this session I'll put a PDF up there so you've also got all of these uh links and things but we've got several resources now to learn about prompt crafting you know this is not something where you need a weekl long Boot Camp or anything like that just an hour or two of you know it'll take less than an hour to understand prompt crafting but then just kind of playing around with it yourself to get a better feel how do you get more accurate suggestions for the context that you're in and everything and then next we launched GitHub copilot chat so we went from just typing in comments in code to having a chat panel right inside the IDE so now I can do things like hey give me an overview of the entire solution uh help me write automated test explain this code to me help me find and fix the bugs in my code and stuff so let's see a little demo of that co-pilot is great for giving you code suggestions in line as you type but there was no way to easily ask questions or provide additional context until now co-pilot chat lets you have a much richer pair programming experience right in visual studio and visual studio code it can suggest tasks based on your code for example here I have some code I've inherited with a bunch of regular expressions in it but it's pretty poorly documented let's ask co-pilot what they do oh looks like we have validation for email addresses phone numbers and strong passwords Mak sense but let's ask for help to make this code a bit more readable for the next person I'll type make this code more readable not bad but I'd like some more so let's ask copilot to separate out the validation functions and add more comments okay great that's much better the code is now in separate functions with the comments and the variables have much more meaningful names this is going to be a lot easier to maintain going forward so let's bring it over now let's take a look at some code that isn't working and see if co-pilot can help me figure out why I'll ask co-pilot to propose a fix for the bugs in my code now co-pilot's determined by looking at my comment and comparing it to the code that I was treating the data as comma separated in my code but in my comment I was saying it was space separated it's also noticed from the comment that I was returning the values in a different order and is adding some error checking for me that it typically sees with this type of code okay so let's bring this code over and run it and yep that works brilliant while we're here let's ask co-pilot to create us some unit test so we don't accidentally break this code again perfect co-pilots analyzing the co- paaths we take in our code and using the context from the comment to generate a set of unit tests for the branches of logic it sees it's a great start for us so we could take this copy it over into a test function and then build that out over time but let me show you one last thing with chat functionality right in your editor it's so much easier to stay focused and on task you can ask for help about coding right where you are you can even have a conversation with Copilot to learn more let's ask for an example here however we're deliberately constraining the prompt to ensure we only have questions that we detect has an intent around programming if we stray outside of this it will politely decline so yeah while Coop pilot can help you're you're on your own as far as figuring out what's for dinner so so yeah you can see there he was able to have the code explained to him generate comments for the code refactor it uh debug code write unit test for it all from working right inside of GitHub co-pilot chat so we added a lot more capabilities there now we made a pretty big splash at Microsoft build last month talking about GitHub co-pilot extensions so this brings the world's knowledge into the most widely adopted AI developer tool and through a growing partner ecosystem co-pilot extensions are going to enable developers to build and deploy to the cloud where with natural language with their preferred tools and services you know a lot of third parties out there mongodb and and um octopus deploy and data stacks and and and lots of others understand that GitHub is the place that developers want to be so that developers can stay in the flow now with GitHub extensions you can access information and things uh from a lot of these other thirdparty systems directly from GitHub co-pilot chat and so you can see we had an initial set of Partners here and actually I'm going to play through one of the little demos here that so that that link there and again all this will all be provided uh at the end uh takes you to this blog post where we made the announcement and I'm going to play the uh octopus deploy Dem the octopus extension for GitHub co-pilot allows developers to maintain a state of Flow by querying the state of their deployments from the same tools they use to write their code in this example we have a node.js web application we will commit and push changes to our git repository and track those changes through the GitHub co-pilot chat interface we'll make a small change to the index page save those changes and then push those to our repository once pushed the GitHub actions workflow will trigger a build and initiate a deployment to octopus deploy we can then track the deployment through the octopus extension for giab co-pilot we can view the high level status of deployments to all environments with a text Bas dashboard so you can see he asked there hey octopus deploy show me the dashboard and again without breaking the flow right inside of GIB copilot chat he's getting this information to see okay have the changes been deployed all the way to production yet let's look at the versions and see no the latest version is not yet in production so getting all of this valuable information without leaving uh your flow useful items in the deployment logs like URLs can be extracted we can use the comprehension cap actually in the interest of time we'll we'll just stop there because there's definitely other things that I want to uh cover but yeah you you can see that full demo if you go to github.io extensions blog post and we'll have links to that uh available uh later so in February we launched GitHub co-pilot Enterprise so now not only are you able to do all of this inside of your IDE but bringing it to GitHub Enterprise cloud and adding new capabilities like building uh Bing search right into uh the chat and everything be being able to tap into knowledge bases of information that you have uh and everything so for this I'm actually going to do a live demo if I can find here we go so here I am on GitHub uh let me reload this get logged in here there we go so I'm on github.com GitHub you know where where we have our repositories and everything and you can see here now we actually have the chat available to us right inside side of github.com so I can come in here and I can ask general questions like let's say I'm starting a new project and I know we want to put feature Flags into our solution so I could say how do I whoops if I type my little shortcut right here how do I get started with feature flages here at GitHub now if I don't specify that I want to search our knowledge bases I'm going to get a very generic answer choose a feature flag Library integrate that Library uh and and and such but now we have the capability to add in your own knowledge bases so knowledge bases are collections of markdown files that are stored right inside of your repos themselves so if I say hey I I want as context to look at the GitHub engineering documentation and then I ask that same ask that same well yeah I should have pulled out my other keyboard this keyboard's a little sticky come on now there we go how do I get started using feature Flags here at GitHub now I'm going to see a different answer with more specifics based on GitHub engineering's uh documentation and everything so and actually this is still somewhat generic it's it's just it but it is referencing documentation from our uh from our knowledge base so I'm going to do this again because I typically get a little different answer there there we go now my shortcuts working there we go this is more what I was hoping to see so now it's giving me specifics you know it's saying hey we use the flipper FR framework here internally so it's showing me specifics about here's what I need to actually put in my code to get started with feature Flags so that's using knowledge bases all right now I'm going to flip over to another environment this environment uses Enterprise managed users so let me do a refresh here because I'll have to relog in there we go so yeah I have a separate identity under Enterprise managed users because now this is for everything internal you know this is a Walled Garden to ensure that nobody can accidentally take a private repository and make it public uh and things like that so a lot of the security that enterprises are looking for but in this case I have this is this is uh Parts Unlimited uh website so if I open up and if I open up the website it's a site for selling Auto Parts right and how many recognize Parts Unlimited anybody ever the Phoenix project by Jean Kim okay yeah Parts Unlimited was the fictitional company that was in that book but anyway um yeah so Parts Unlimited started out as a brick and mortar store in the Washington area so right now sales tax is kind of hardcoded to sales tax for Washington but that that's not what we want now that we're an e-commerce site we have to be able to calculate sales tax wherever the buyer lives right so I'm going to bring up GitHub co-pilot chat here Enterprise chat and ask where come on my keys will cooperate where in this repo do we have code that calculates sales tax so it'll take a moment but it's looking so something you something to notice here is it's saying this repository has been indexed for improved understanding and accuracy so with GitHub co-pilot Enterprise you go through and pick what repos you want to index for these types of searches so it's telling me yes there's the default shipping tax calculator CS file that includes this calculate tax function and I'm actually going come on there we go going copy calculate tax there but then it's also showing me who the other callers are of calculate tax so I I get a good picture you know of how this is uh working throughout the entire solution uh or repository so we can open that file up and we'll see okay here's calculate tax and yeah in fact it is hardcoded right now to certain tax rates so 7.5% sales tax for state of Washington that might even be out of date um but now I'm going to ask co-pilot this is where kind of like the the Bing built-in Bing search comes into play are there any public apis out there that I can use to calculate sales tax in any postal code so now it's going to come back with uh a list of apis that I could use here free sales tax API tax apis uh Sales Tax USA avalara Etc so now I want to leverage GitHub co-pilot Enterprise to say hey what would that calculate tax function look like if I wanted to use let's say the AL avalara uh API so the but what I want to do is first kind of set the context for co-pilot so I'm going to say now did that paste NOP doesn't look like it uh see if I can spell it right C and see if my keyboard will cooperate there we go calculate tax so now I'm telling copilot that's the context that I'm talking about so now I will say how would this how would I update this code to use of aara API all right you can see this this is live demo responding in real time so now if we look here at the the differences kind of try to zoom in here yeah you can see where we were calculating you know the tax rate here hardcoded now it is showing me how to it's doing the same thing it's still returning taxable times tax rate and all that but here it is using that avalara API and everything instead now another key thing here if I scroll down and look at some of the additional explanation it gave me said hey there's one possible vulnerability here you're when you're working with an API like that you're going to have an API key that you have to store so it's telling me make sure you do not hardcode that API key in your code make sure you store that in hashy corp Vault or Azure key Vault or GitHub Secrets or or something like that so it's helping you with some of those security best practices uh as well along the way all right couple more things and then kind of uh uh about five six minutes left so yeah there's demos out there on YouTube for GitHub co-pilot Enterprise and everything also oh yes so that was the chat in the repository one other thing I want to show you is we we have it now so that when we're looking at poll requests so here's here's an existing poll request and I was kind of lazy when I first created this poll request I've got GitHub integrated with Azure board so I referred to the Azure boards user stories and uh work uh tasks and stuff that I'm completing as part of this but I didn't provide any other kind of a description well now with GitHub copilot chat I can edit this and you'll see we have the co-pilot icon in here as well so I could come in here and say hey co-pilot generate a summary for me so how many times do developers write nice summaries that anybody could read you know getting ready to review the code uh and everything yeah not very not very often but with copilot it's going to look at all the changes that you've made provide a nice summary paragraph and then file by file list out all of the changes there we go just took a few seconds so now I have a nice summary here and then you can see yeah file by file it's listing out each change in each file kind of a thing so and it makes it easy for developers then to provide a lot of information and uh you know not have to spend a lot of time doing that now the other thing that you can do here when you're looking at a poll request and we we we even have more coming with this okay okayy come on internet you can do it there we go so I can go in and look at one of my changes I'm going to skip over this one for the moment yeah let me just look at this change and I can come in whoops that's not the what I want here we go you'll see the co-pilot icon here too now this is obviously a very simple change we're just doing some rebranding of the website here but if this were more complex you know I could say explain and have uh co-pilot explain the change to me so yeah in this case it's just that simple changing from fabric cam to Koso but if this were more complex you know the the reviewer can look at this look back at that user story and say okay by looking at the user story I know what the intent was now does co-pilot agree that the what's actually implemented matches that intent so that's another way to use co-pilot enterpr PR so we talked about the chat we talked about searching the knowledge bases poll request summaries and such this this works with co-pilot works with any language the large language models have been built off of the vast majority of the open source code that's out there there's even Cobalt code out there so I found a Cobalt uh a repository out there that has cobal examples in it so I said hey what what does this code do and GitHub co-pilot was able to provide an explanation for me you know simple Fibonacci Sequence so you could then next prompt and say hey how would what would that code look like in Java what would that code look like in C or something so use this as a way to modernize your your uh cobal and other code the next one is co-pilot workspace ah I ran out of time I actually don't let's see let's go all right let me do this I'm not sure if there's anybody coming in the room right away here at 11:15 let me do this first just in case there is somebody coming in next so if you want to take a screenshot of this uh URL we have a page out there that has I don't know 15 20 links to additional training some of our key blog posts and things like that that we've recently had and yeah this will be dynamic as more and more things come in we'll um we'll add to that and everything uh also yes we'll be at the GitHub Booth uh where we can a answer additional questions and and things like that so yep I see people moving on thank you very much for your time so yeah stop by the Microsoft booth and we'll show you co-pilot workspace [Music]