Deploy a Slack gateway for Amazon Q, your enterprise skilled

Amazon Q is a brand new generative AI-powered software that helps customers get work finished. Amazon Q can turn out to be your tailor-made enterprise skilled and allow you to uncover content material, brainstorm concepts, or create summaries utilizing your organization’s information safely and securely. You should utilize Amazon Q to have conversations, resolve issues, generate content material, achieve insights, and take motion by connecting to your organization’s data repositories, code, information, and enterprise programs. For extra data, see Introducing Amazon Q, a new generative AI-powered assistant (preview).

On this publish, we present you find out how to convey Amazon Q, your business expert, to customers in Slack.

You’ll give you the option converse with Amazon Q utilizing Slack direct messages (DMs) to ask questions and get solutions based mostly on firm information, get assist creating new content material reminiscent of e mail drafts, summarize hooked up recordsdata, and carry out duties.

You too can invite Amazon Q to take part in your workforce channels. In a channel, customers can ask it questions in a brand new message, or tag it in an current thread at any level, to offer further information factors, resolve a debate, or summarize the dialog and seize the subsequent steps.

Resolution overview

Amazon Q is amazingly highly effective. Try the next demo—seeing is believing!

Within the demo, our Amazon Q software is populated with a set of AWS whitepapers. You possibly can populate your personal Amazon Q enterprise skilled software with your personal firm’s paperwork and data base articles, so will probably be capable of reply your questions!

The whole lot you want is supplied as open supply in our GitHub repo.

On this publish, we stroll you thru the method to deploy Amazon Q in your AWS account and add it to your Slack workspace. While you’re finished, you’ll marvel the way you ever managed with out it!

The next are among the issues it could possibly do:

Reply to messages – In DMs, it responds to all messages. In channels, it responds solely to @mentions and responds in a dialog thread.
Render solutions containing markdown – This contains headings, lists, daring, italics, tables, and extra.
Observe sentiment – It offers thumbs up and thumbs down buttons to trace person sentiment.
Present supply attribution – It offers references and hyperlinks to sources utilized by Amazon Q.
Perceive dialog context – It tracks the dialog and responds based mostly on the context.
Keep conscious of a number of customers – When it’s tagged in a thread, it is aware of who mentioned what, and when, so it could possibly contribute in context and precisely summarize the thread when requested.
Course of hooked up recordsdata – It may possibly course of as much as 5 hooked up recordsdata for doc query answering, summaries, and extra.
Begin new conversations – You possibly can reset and begin new conversations in DM channels through the use of /new_conversation.

Slack example

Within the following sections, we present find out how to deploy the challenge to your personal AWS account and Slack workspace, and begin experimenting!

Conditions

It’s worthwhile to have an AWS account and an AWS Identity and Access Management (IAM) position and person with permissions to create and handle the mandatory assets and parts for this software. For those who don’t have an AWS account, see How do I create and activate a new Amazon Web Services account?

You additionally must have an current, working Amazon Q enterprise skilled software. For those who haven’t set one up but, see Creating an Amazon Q application.

Lastly, you want a Slack account and entry to create and publish apps to your Slack group. For those who don’t have one, see if your organization can create a Slack sandbox group so that you can experiment, or go to slack.com to create a free Slack account and workspace.

Deploy the answer assets

We’ve supplied pre-built AWS CloudFormation templates that deploy every part you want in your AWS account.

For those who’re a developer and also you need to construct, deploy, or publish the answer from code, seek advice from the Developer README.

Full the next steps to launch the CloudFormation stack:

Log in to the AWS Management Console.
Select one of many following Launch Stack buttons to your desired AWS Area to open the AWS CloudFormation console and create a brand new stack.

Area	Launch Stack
N. Virginia (`us-east-1`)
Oregon (`us-west-2`)

For Stack title, enter a reputation to your app (for instance, AMAZON-Q-SLACK-GATEWAY).
For AmazonQAppId, enter your current Amazon Q software ID (for instance, 80xxxxx9-7xx3-4xx0-bxx4-5baxxxxx2af5). You possibly can copy it from the Amazon Q console.
For AmazonQRegion, select the Area the place you created your Amazon Q software (us-east-1 or us-west-2).
For AmazonQUserId, enter an Amazon Q person ID e mail tackle (go away clean to make use of a Slack person e mail because the person ID).
For ContextDaysToLive, enter the size of time to maintain dialog metadata cached in Amazon DynamoDB (you may go away this because the default).

When your CloudFormation stack standing is CREATE_COMPLETE, select the Outputs tab, and preserve it open—you’ll want it in later steps.

Create your app

Now you may create your app in Slack. Full the next steps:

Create a Slack app in https://api.slack.com/apps from the generated manifest—copy and paste from the stack output: SlackAppManifest.
Select App Dwelling within the navigation pane and scroll all the way down to the part Present Tabs.
Allow Messages Tab.
Choose Permit customers to ship Slash instructions and messages from the messages tab.

This can be a required step to allow your person to ship messages to your app.

Slack enable messages

Add your app in your workspace

Now you may add your app in your workspace. That is required to generate the bot person OAuth token worth that’s wanted within the subsequent step.

Go to OAuth & Permissions (in https://api.slack.com) and select Set up to Workspace to generate the OAuth token.
In Slack, go to your workspace.
Select your workspace title, Settings & administration, and Handle apps.
Select your newly created app.
In the precise pane, select Open in App Listing.
Select Open in Slack.

Configure Slack secrets and techniques in AWS Secrets and techniques Supervisor

Let’s configure your Slack secrets and techniques to be able to confirm the signature of every request and publish on behalf of your Amazon Q bot.

On this instance, we aren’t enabling Slack token rotation. You possibly can allow it for a manufacturing app by implementing rotation through AWS Secrets Manager. Create a problem (or, higher but, a pull request) within the GitHub repo if you’d like this characteristic added to a future model.

Full the next steps to configure a secret in Secrets and techniques Supervisor:

On the AWS CloudFormation console, navigate to your stack Outputs tab and select the hyperlink for SlackSecretConsoleUrl to be redirected to the Secrets and techniques Supervisor console.
Select Retrieve secret worth.
Select Edit.
Exchange the values of SlackSigningSecret and SlackBotUserOAuthToken utilizing the values within the Slack software configuration below Primary Data and OAuth & Permissions.

Watch out you don’t by chance copy Consumer Secret as an alternative of Signing Secret.

Edit secrets

Begin utilizing Amazon Q

Full the next steps to begin utilizing Amazon Q in Slack:

Open your Slack workspace.
Below Apps, Handle, add your new Amazon Q app.
Optionally, add your Amazon Q app to workforce channels.
Within the app DM channel, enter Howdy.

Say hello

You could have now deployed a strong new AI assistant into your sandbox Slack atmosphere.

Play with it, strive all of the options mentioned on this publish, and duplicate the belongings you noticed within the demo video. Most significantly, you may ask about matters associated to the paperwork that you’ve ingested into your personal Amazon Q enterprise skilled software. However don’t cease there. You could find further methods to make it helpful, and whenever you do, tell us by posting a remark.

As soon as you might be satisfied how helpful it’s, speak to your Slack admins (and present them this publish) and work with them to deploy it in your organization’s Slack workspaces. Your fellow workers will thanks!

Clear up

While you’re completed experimenting with this resolution, delete your app in Slack (https://api.slack.com/apps) and clear up your AWS assets by opening the AWS CloudFormation console and deleting the AMAZON-Q-SLACK-GATEWAY stack that you simply deployed. This deletes the assets that you simply created by deploying the answer.

Conclusions

This pattern Amazon Q slack software mentioned on this publish is supplied as open supply—you should utilize it as a place to begin to your personal resolution, and assist us make it higher by contributing again fixes and options through GitHub pull requests. Discover the code, select Watch within the GitHub repo to be notified of latest releases, and test again for the newest updates. We’d additionally love to listen to your ideas for enhancements and options.

For extra data on Amazon Q, seek advice from What is Amazon Q (For Business Use)?

In regards to the Authors

Gary Benattar is a Senior Software program Growth Supervisor in AWS HR. Gary began at Amazon in 2012 as an intern, specializing in constructing scalable, real-time outlier detection programs. He labored in Seattle and Luxembourg and is now based mostly in Tel Aviv, Israel, the place he dedicates his time to constructing software program to revolutionize the way forward for Human Sources. He co-founded a startup, Zengo, with a deal with making digital wallets safe via multi-party computation. He acquired his MSc in Software program Engineering from Sorbonne College in Paris.