Topics
late
AI
Amazon
Image Credits:TechCrunch
Apps
Biotech & Health
Climate
Image Credits:TechCrunch
Cloud Computing
Commerce
Crypto
Image Credits:TechCrunch
enterprisingness
EVs
Fintech
Image Credits:TechCrunch
Fundraising
Gadgets
Gaming
Government & Policy
Hardware
Layoffs
Media & Entertainment
Meta
Microsoft
Privacy
Robotics
Security
societal
blank
Startups
TikTok
Transportation
speculation
More from TechCrunch
case
Startup Battlefield
StrictlyVC
Podcasts
Videos
Partner Content
TechCrunch Brand Studio
Crunchboard
Contact Us
At its re : Invent conference , AWS declare on Tuesday a serial publication of updates toQ Developer , its coding assistant political program that competes with the likes of GitHub Copilot . The focus here is on going beyond code closing and helping developers with a wider orbit of routine tasks involve in the end - to - terminal software life hertz .
The service , which you may remember under its previous name of “ CodeWhisperer , ” is part of AWS ’s overall Amazon Q generative AI weapons platform , which also include Q Business ( and which is also gettinga good deal of updates today ) .
“ What developers require is they want to really have Q be the buddy to work out some of the uniform heavy lifting so that they can in reality have more exemption to innovate , ” Swaminathan ‘ Swami ’ Sivasubramanian , AWS ’ VP of AI and Data , secern me . “ So that ’s why have an assistant — or buddy — that helps them do things faster , more streamlined , is such an important thing , and that ’s why we ’re focussed on it in a big manner . ”
Managing the end-to-end software life cycle
Sivasubramanian told me that he consider what differentiates Q Developer from competing platforms is its stress on the full software development life cycle . So far that meant helping developers troubleshoot emergence and do multistep tasks to fix them ( or build entirely new apps ) , as well as scan the codification for security vulnerabilities .
At re : Invent , the company is taking this a step further . Q can now , for example , automatically bring forth unit test . But what ’s maybe even more important is that it can now do the one thing that many developer detest the most : compose and sustain the documentation for that code . To fill in this cycle , Q can now generate a first code review when developer check in their code .
“ In Amazon , we have this principle that no codification ever gets checked in without a codification recapitulation , ” Sivasubramanian said . “ So if you do n’t do a code review , then you’re able to not check in codification . But not many enterprises really have either enough senior engine driver to go over or the senior engineer says : ‘ I ca n’t deal with so many reviews . Can somebody first survey it before we do so ? ’ Q will streamline the code review procedure by being the first line of reviewer and takes aid of automatically crack code timbre , surety vulnerability , and so forth . ”
Then , once the codification is in production , a novel operations federal agent for Q can now automatically pull in data from AWS CloudWatch , the company ’s monitoring serving , and immediately start investigating when an alert goes off . “ It utilizes the [ knowledge it has about an ] organization ’s AWS resources and then it sifts through 100 of data points across various resources sitting in CloudWatch . Then , after analyzing it , Q comes up with possible possibility for the root cause and then it guides the user through how to fix it , ” Sivasubramanian explained .
Join us at TechCrunch Sessions: AI
Exhibit at TechCrunch Sessions: AI
All you wanted for Christmas was help with your Cobol and .NET migrations, right?
For those enterprise with older codebases , transition to the cloud often involves rewriting a lot of their existing computer code . One of the earliest differentiating features of Amazon Q Developer was its agentive role for code transmutation . At the time , the focus of this agent was onmodernizing older Java apps . Today , the team is expanding this by also help developers update their older .NET - based applications from Windows to Linux .
And while this may at first seem like a curiosity , AWS is also launch an agent for develop COBOL mainframe applications . A lot of gravid enterprises still rely on this old code , after all , which few developer recognize to work with today . These are very complex migration , Sivasubramanian strain , and so the end here is not to simply translate the survive codification 1:1 .
“ Our finish is not to actually just like fully COBOL project in , computer code out , ” he said . “ The reality is , these projects are inherently passing complex . You need to have a human in the loop to leverage it , but I ’ve heard client say , ‘ Hey , this hold multiple yr and customer have explicitly severalize us this is a game changer and would importantly unload that timeline . ”
Sivasubramanian note that while there is less COBOL code to cultivate models to automate the code migration , the team was capable to leverage AWS ’ overall experience in modernizing mainframe applications , as well as more traditional methods for codification rendering .
“ Taking codification from one language to another one arguably is the easy part , ” he read . “ But the harder part is : how do you recognize you got it right ? And how do you even sleep together what the codification does ? And then the challenge in these [ codebases ] is they are usually badly documented and dependencies are not well sympathize . So what we have built is really extremely groundbreaking , and [ the organization ] also understands , at a task degree , what are the objectives of each of the module , and then be after out and creates a migration provision timeline to actually generate the code , and then bring forth the test — and institute humans in the eyelet to see how you validate it . ”
From the Storyline:AWS re:Invent 2024: Live updates from Amazon’s biggest event
Amazon ’s re : invent 2024 conference returns to Las Vegas for a serial of reveals and tonic through December 6 . AI is …
