Decide whether this move earns its cost
A queue receives more browser jobs than the account can run at once. Workers must wait for capacity and recover slots after failed jobs.
AgentCore Browser's AWS integration can matter more than moving a browser endpoint. Retain AWS identity and observability requirements in the evaluation, and separately account for the code runner and website login before comparing Notte's integrated workflow.
Notte is a candidate when its published concurrency tiers fit the queue and the team wants browser and Python execution resources in one platform. Capacity must be checked separately from the hourly rate.
An existing pool or queue integration can outweigh a rate difference when it already handles the burst reliably. A single-session latency result does not establish fleet behavior for any provider.
Keep the result contract stable
A fixed burst of jobs, the account's documented concurrency entitlement and a bounded application queue.
The queue drains without exceeding the entitlement; every allocated browser is associated with one job and eventually released.
Preserve the evidence contract across the move: Queue arrival and start times, allocated sessions, completion counts and recovered capacity.
Map the workflow's resources
| Requirement | AWS AgentCore Browser | Notte |
|---|---|---|
| Browser control | Browser automation endpoint | Documented |
| Saved browser state | Explicit state design | Documented |
| Live view | Documented | Documented |
| Deployment choice | AWS service | Enterprise options |
Sources: docs.aws.amazon.com [1] ↗docs.notte.cc [2] ↗docs.notte.cc [3] ↗docs.notte.cc [4] ↗docs.notte.cc [5] ↗
Capacity and limits
AWS AgentCore Browser: AgentCore Browser supports multiple simultaneous sessions. Review AWS quotas and the chosen tool/session configuration; the browser session's timeout and the controller's execution timeout are separate limits.
Notte: The public plans list 5, 25 and 100 concurrent browser sessions, with custom limits on Enterprise. Session duration and concurrent capacity are separate plan limits; a larger technical API limit does not override the plan.
Browser control
AWS AgentCore Browser: Create or select a Browser Tool, then start an isolated browser session. The documented default session timeout is 15 minutes and the maximum is eight hours. Browser automation uses the session's WebSocket endpoints.
Notte: Create an owned browser session, connect Playwright or Puppeteer over CDP, and stop the session when the work finishes. Browser lifecycle management remains necessary even when the control socket disconnects.
Deployment ownership
AWS AgentCore Browser: Use an AWS-managed Browser Tool or configure a custom browser with recording, networking and an execution role. Keep the controller's deployment separate in the architecture and operational estimate.
Notte: Use a remote browser from your existing process or deploy the browser automation as a Notte Function. These choices put lifecycle, scheduling and monitoring responsibilities in different places.
Pricing model
AWS AgentCore Browser: A complete AWS workflow may include browser use, the controlling compute service, storage and other metered services. Price the selected architecture and region instead of treating a browser benchmark rate as the final invoice.
Notte: The public usage rates are $0.01 per browser-hour, $0.05 per Function-hour and $10 per GB of managed proxy traffic. Paid plans return their price as usage credits. Price the relevant meters and plan eligibility for the workload.
Sources: aws.amazon.com [1] ↗notte.cc [2] ↗
Cut over one responsibility at a time
For this AWS AgentCore Browser-to-Notte migration, keep the business assertion outside provider resource management. Source profile, connection, file and execution IDs are not valid target IDs; use a documented transfer path or establish the corresponding resource in Notte.
Retain source job history and a rollback route until the target pilot passes. A migration checklist is not evidence that saved state or runtime behavior is automatically portable.
- Keep admission control in place while introducing the target provider.
- Move one queue partition and record allocation failures separately from task failures.
- Compare drained jobs, leaked slots and cost per completed job before raising concurrency.
Sources: docs.aws.amazon.com [1] ↗notte.cc [2] ↗docs.notte.cc [3] ↗
A proposed acceptance case
This is an evaluation design, not a claim that this workflow has been executed successfully on every provider.
| Part of the test | Required observation |
|---|---|
| Controlled input | A fixed burst of jobs, the account's documented concurrency entitlement and a bounded application queue. |
| Pass condition | The queue drains without exceeding the entitlement; every allocated browser is associated with one job and eventually released. |
| Negative case | Fail a job after browser allocation. Verify that the next queued job can acquire the recovered slot and that retries do not create untracked sessions. |
| Evidence to retain | Queue arrival and start times, allocated sessions, completion counts and recovered capacity. |
A reason to delay or keep the source
Fail a job after browser allocation. Verify that the next queued job can acquire the recovered slot and that retries do not create untracked sessions.
AWS AgentCore Browser: The browser tool is not the entire AgentCore platform. Do not assign capabilities from unrelated AgentCore execution or identity products to a browser session without specifying the composition.
Delay cutover when the target's selected plan, required artifact path or supported website-account flow is not established. Resolve that gap before moving real jobs, even if the rate comparison favors the target.