AWS · Cloud service
AWS Lambda with OrchestrAI
Catalog exported 2026-09-02
Operate AWS Lambda from chat: create functions, invoke them, tune configuration, and add triggers and layers.
OrchestrAI exposes 6 Lambda operations: 2 are low-risk (read-only or low-impact), and 4 create or modify resources and run only after you confirm the plan. 1 of them also carries a step-level approval gate.
What teams use it for
Backend teams use OrchestrAI to create a function from a package, invoke it with a test payload, raise memory or timeout, set environment variables, publish a layer for shared dependencies, add a resource policy permission for API Gateway or S3, and connect an SQS queue or DynamoDB stream as an event source. Invoking and publishing layers are low risk; configuration updates wait for confirmation. There is no operation to update function code, delete a function, or list functions, so new code versions are deployed through your CI pipeline.
Every Lambda operation, with its risk level
| Operation | What it does | Risk | Step-level approval |
|---|---|---|---|
Invoke Lambda Function |
Invoke a Lambda function synchronously or asynchronously | Low risk | No |
Publish Lambda Layer Version |
Publish a Lambda layer version for shared dependencies across functions | Low risk | No |
Add Lambda Permission |
Add a permission to a Lambda function's resource-based policy | Creates resources | No |
Create Lambda Event Source Mapping |
Create a mapping between an event source and a Lambda function | Creates resources | No |
Create Lambda Function |
Create a new AWS Lambda serverless function | Creates resources | No |
Update Lambda Function Configuration |
Update a Lambda function's configuration (memory, timeout, environment, runtime, handler, layers) | Creates resources | Yes |
Risk tiers come from the catalog: low is read-only or low-impact, medium creates resources and is reversible, high modifies existing resources, destructive may lose data. Every plan that creates or changes resources is shown with its cost estimate and waits for your confirmation. Operations marked with a step-level approval pause again on their own step. Destructive operations require a typed risk phrase.
Prompts that work
- Create a Python 3.12 Lambda called image-resizer in us-east-1 from s3://deploy-artifacts/image-resizer.zip with the lambda-exec role
- Invoke the nightly-report function with {"date": "2026-09-01"} and show me the result
- Raise the timeout on process-orders to 60 seconds and set LOG_LEVEL=debug
Before anything runs
Every mutation shows its plan, cost estimate, and blast radius, then waits for your confirmation. Destructive operations require a typed risk phrase. Credentials are minted per run through OIDC federation and discarded afterward; nothing you create here is invisible later, because every resource lands in the desired-state ledger where drift is detected and can be converged. Details on the security page.
Frequently asked questions
- Can OrchestrAI update the code of an existing Lambda function?
- No, it can create functions and change configuration such as memory, timeout, runtime, handler, and layers, but code updates are not in the operation set.
- Can OrchestrAI connect a queue or stream to a Lambda function?
- Yes, the event source mapping operation links a source such as SQS or DynamoDB Streams to a function, and add_permission grants invoke rights to services like API Gateway.
- Which Lambda operations need an extra approval step?
- One operation carries a step-level approval gate on top of plan confirmation: Update Lambda Function Configuration. None of them is classed destructive.
Other AWS services
Related integrations
Try it on your own account
Connect your cloud read-only and see your resources, drift, and costs before anything runs. $5 minimum to start. Unused credits refunded in your first 14 days.
Unused credits refunded in your first 14 days.