Integration · Cloud and hosting
AI agents for Amazon Web Services
Every AWS service from one connection: EC2, S3, Lambda, RDS, DynamoDB, IAM, ECS, EKS, CloudWatch, Bedrock and over four hundred more.
- Actions
- 7
- Read
- 4
- Write
- 3
Actions
What your agents can do in Amazon Web Services
Every AWS service from one connection: EC2, S3, Lambda, RDS, DynamoDB, IAM, ECS, EKS, CloudWatch, Bedrock and over four hundred more. Find a service and an operation, read its parameters, and run it, with each call checked, signed and read by the AWS SDK's own service models. Signed with an access key, optionally assuming a role.
Read 4
Look things up. Nothing changes.
List services
Lists the AWS services this connection can call, each with its id (the service every other action takes, like ec2, s3 or lambda), name, category and number of operations.
Search operations
Finds AWS operations by what they do, across every service or inside one: "list virtual machines", "read a secret", "delete a bucket".
Describe an operation
Reads one AWS operation's contract from the vendor's own API model.
Run a read operation
Runs one AWS read operation (Describe, List, Get and the like: nothing changes) and returns its answer as JSON in result.
Write 3
Create, change or send.
Run a write operation
Runs one AWS operation that creates or changes something (Create, Put, Update, Start, Tag, Send and the like) and returns its answer as JSON in result.
Run a destructive operationDeletes data
Runs one destructive AWS operation: deletes, terminations, stops and restarts, key regeneration and permission changes, which cannot be undone by another call.
Run an operation on secretsDeletes data
Runs one AWS operation that returns or sets secrets.
A person can approve first
Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything. Actions that delete data ask first by default.
Connection
How it connects
Connect it once in the console, then give it to the agents and workflows that need it.
Enter the sign-in details Amazon Web Services gives you for its API.
What you enter
- Access key ID
- Secret access key
Settings
- Default region
Kept safe
- Credentials are stored encrypted with your organization's own keys.
- They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
- Calls go only to the tool's own servers.
Ideas
Ideas to start with
Starting points made only from the actions above. Mix them with any other tool your agents can use.
- 01
Ask about your Amazon Web Services data
Ask a question in plain words. The agent can list services, search operations or describe an operation in Amazon Web Services, then answers with what it found.
- 02
Let an agent update Amazon Web Services
Have the agent run a write operation or run a destructive operation in Amazon Web Services as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Share what it finds in Slack
Give one agent Amazon Web Services and Slack: it can list services in Amazon Web Services and post a summary to a Slack channel in the same run.
Works well with
More Cloud and hosting tools
- Microsoft Azure7 actionsEvery Azure service from one connection: Virtual Machines, Storage, App Service, Functions, AKS, SQL, Cosmos DB, Key Vault, Networking, Monitor, OpenAI and every other resource provider of Azure Resource Manager.
- Google Cloud7 actionsEvery Google Cloud API from one connection: Compute Engine, Cloud Storage, BigQuery, Cloud Run, GKE, Cloud SQL, Pub/Sub, IAM, Vertex AI and two hundred more.
- Amazon S38 actionsList buckets and files, read and download files, upload any file, save JSON files and delete files in Amazon S3 (Simple Storage Service), signed with an AWS access key.
- Netlify5 actionsList sites and their deploys, start a build, check a deploy's status, and roll a site back to an earlier deploy, on the Netlify teams a personal access token can reach.
- Heroku16 actionsSee Heroku apps, dynos, releases and builds, restart dynos, scale process types, roll back a release and switch maintenance mode, with a Heroku API token.
- Amazon CloudWatch Logs8 actionsSearch and read application logs in Amazon CloudWatch Logs.
FAQ
Amazon Web Services and MyDeepAgents
Can MyDeepAgents connect to Amazon Web Services?
Yes. The Amazon Web Services connector has 7 actions: 4 read and 3 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Amazon Web Services?
Enter the sign-in details Amazon Web Services gives you for its API. You'll need: Access key ID and Secret access key. The connection also asks for: Default region. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.
Can an agent change data in Amazon Web Services without asking?
Only if you let it. Each of the 3 actions that change data can be set to wait for a person's approval before it runs, and the 2 that delete data ask first by default.
Can I use Amazon Web Services in workflows as well as agents?
Yes. Every Amazon Web Services action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Amazon Web Services to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.