View Source AWS.BedrockAgentCore (aws-elixir v1.0.11)

Welcome to the Amazon Bedrock AgentCore Data Plane API reference.

Data Plane actions process and handle data or workloads within Amazon Web Services services.

Link to this section Summary

Functions

Creates multiple memory records in a single batch operation for the specified memory with custom content.

Deletes multiple memory records in a single batch operation from the specified memory.

Updates multiple memory records with custom content in a single batch operation within the specified memory.

Confirms the user authentication session for obtaining OAuth2.0 tokens for a resource.

Creates an A/B test for comparing agent configurations.

Creates an event in an AgentCore Memory resource.

Create a new payment instrument for a connector

Create a new payment manager session

Deletes an A/B test and its associated gateway rules.

Deletes a batch evaluation and its associated results.

Deletes a memory record from an AgentCore Memory resource.

Delete a payment manager session

Deletes a recommendation and its associated results.

Performs on-demand evaluation of agent traces using a specified evaluator.

Retrieves detailed information about an A/B test, including its configuration, status, and statistical results.

Retrieves the A2A agent card associated with an AgentCore Runtime agent.

Retrieves detailed information about a batch evaluation, including its status, configuration, results, and any error details.

Retrieves detailed information about a specific browser session in Amazon Bedrock AgentCore.

Retrieves detailed information about a specific code interpreter session in Amazon Bedrock AgentCore.

Retrieves information about a specific event in an AgentCore Memory resource.

Retrieves a specific memory record from an AgentCore Memory resource.

Get the balance of a payment instrument

Retrieves detailed information about a recommendation, including its configuration, status, and results.

Retrieves the API key associated with an API key credential provider.

Returns the OAuth 2.0 token of the provided resource.

Generates authentication tokens for payment providers that use vendor-specific authentication mechanisms.

Obtains a workload access token for agentic workloads not acting on behalf of a user.

Obtains a workload access token for agentic workloads acting on behalf of a user, using a JWT token.

Obtains a workload access token for agentic workloads acting on behalf of a user, using the user's ID.

Sends a request to an agent or tool hosted in an Amazon Bedrock AgentCore Runtime and receives responses in real-time.

Executes a command in a runtime session container and streams the output back to the caller.

Invokes an operating system-level action on a browser session in Amazon Bedrock AgentCore.

Executes code within an active code interpreter session in Amazon Bedrock AgentCore.

Operation to invoke a Harness.

Lists all actors in an AgentCore Memory resource.

Lists all batch evaluations in the account, providing summary information about each evaluation's status and configuration.

Retrieves a list of browser sessions in Amazon Bedrock AgentCore that match the specified criteria.

Retrieves a list of code interpreter sessions in Amazon Bedrock AgentCore that match the specified criteria.

Lists events in an AgentCore Memory resource based on specified criteria.

Lists all long-term memory extraction jobs that are eligible to be started with optional filtering.

Lists memory records in an AgentCore Memory resource based on specified criteria.

List payment instruments for a manager

Lists all recommendations in the account, with optional filtering by status.

Lists sessions in an AgentCore Memory resource based on specified criteria.

Process a payment transaction

Searches for and retrieves memory records from an AgentCore Memory resource based on specified search criteria.

Saves the current state of a browser session as a reusable profile in Amazon Bedrock AgentCore.

Searches for registry records using semantic, lexical, or hybrid queries.

Starts a batch evaluation job that evaluates agent performance across multiple sessions.

Creates and initializes a browser session in Amazon Bedrock AgentCore.

Creates and initializes a code interpreter session in Amazon Bedrock AgentCore.

Starts a memory extraction job that processes events that failed extraction previously in an AgentCore Memory resource and produces structured memory records.

Starts a recommendation job that analyzes agent traces and generates optimization suggestions for system prompts or tool descriptions to improve agent performance.

Terminates an active browser session in Amazon Bedrock AgentCore.

Terminates an active code interpreter session in Amazon Bedrock AgentCore.

Stops a session that is running in an running AgentCore Runtime agent.

Updates an A/B test's configuration, including variants, traffic allocation, evaluation settings, or execution status.

Link to this section Functions

Link to this function

batch_create_memory_records(client, memory_id, input, options \\ [])

View Source

Creates multiple memory records in a single batch operation for the specified memory with custom content.

Link to this function

batch_delete_memory_records(client, memory_id, input, options \\ [])

View Source

Deletes multiple memory records in a single batch operation from the specified memory.

Link to this function

batch_update_memory_records(client, memory_id, input, options \\ [])

View Source

Updates multiple memory records with custom content in a single batch operation within the specified memory.

Link to this function

complete_resource_token_auth(client, input, options \\ [])

View Source

Confirms the user authentication session for obtaining OAuth2.0 tokens for a resource.

Link to this function

create_a_b_test(client, input, options \\ [])

View Source

Creates an A/B test for comparing agent configurations.

A/B tests split traffic between a control variant and a treatment variant through a gateway, then evaluate performance using online evaluation configurations to determine which variant performs better.

Link to this function

create_event(client, memory_id, input, options \\ [])

View Source

Creates an event in an AgentCore Memory resource.

Events represent interactions or activities that occur within a session and are associated with specific actors.

To use this operation, you must have the bedrock-agentcore:CreateEvent permission.

This operation is subject to request rate limiting.

Link to this function

create_payment_instrument(client, input, options \\ [])

View Source

Create a new payment instrument for a connector

Link to this function

create_payment_session(client, input, options \\ [])

View Source

Create a new payment manager session

Link to this function

delete_a_b_test(client, ab_test_id, input, options \\ [])

View Source

Deletes an A/B test and its associated gateway rules.

Link to this function

delete_batch_evaluation(client, batch_evaluation_id, input, options \\ [])

View Source

Deletes a batch evaluation and its associated results.

Link to this function

delete_event(client, actor_id, event_id, memory_id, session_id, input, options \\ [])

View Source

Deletes an event from an AgentCore Memory resource.

When you delete an event, it is permanently removed.

To use this operation, you must have the bedrock-agentcore:DeleteEvent permission.

Link to this function

delete_memory_record(client, memory_id, memory_record_id, input, options \\ [])

View Source

Deletes a memory record from an AgentCore Memory resource.

When you delete a memory record, it is permanently removed.

To use this operation, you must have the bedrock-agentcore:DeleteMemoryRecord permission.

Link to this function

delete_payment_instrument(client, input, options \\ [])

View Source

Delete a payment instrument

Marks a payment instrument as deleted by updating its status to DELETED.

This is a soft delete operation that preserves the record in the database for audit and compliance purposes. The record remains queryable for audit purposes but is excluded from normal list and get operations.

Deleting an already-deleted or non-existent instrument returns ResourceNotFoundException (404).

Authorization: The caller must own the instrument (accountId, userId, and paymentManagerId must match). If authorization fails, a 403 Forbidden error is returned.

Timestamp Management: The updatedAt timestamp is set to the current time, while createdAt is preserved. The version field is incremented for optimistic locking.

Errors:

  • ResourceNotFoundException: The instrument does not exist or is already deleted
  • AccessDeniedException: The caller is not authorized to delete this instrument
  • ValidationException: Required fields are missing or invalid
  • InternalServerException: An unexpected server error occurred
Link to this function

delete_payment_session(client, input, options \\ [])

View Source

Delete a payment manager session

Permanently removes a payment session record from the database.

This is a hard delete operation that removes the session completely.

Deleting a non-existent or already-deleted session returns ResourceNotFoundException (404).

Authorization: The caller must own the session (accountId, userId, and paymentManagerId must match). If authorization fails, a 403 Forbidden error is returned.

Errors:

  • ResourceNotFoundException: The session does not exist or has already been deleted
  • AccessDeniedException: The caller is not authorized to delete this session
  • ValidationException: Required fields are missing or invalid
  • InternalServerException: An unexpected server error occurred
Link to this function

delete_recommendation(client, recommendation_id, input, options \\ [])

View Source

Deletes a recommendation and its associated results.

Link to this function

evaluate(client, evaluator_id, input, options \\ [])

View Source

Performs on-demand evaluation of agent traces using a specified evaluator.

This synchronous API accepts traces in OpenTelemetry format and returns immediate scoring results with detailed explanations.

Link to this function

get_a_b_test(client, ab_test_id, options \\ [])

View Source

Retrieves detailed information about an A/B test, including its configuration, status, and statistical results.

Link to this function

get_agent_card(client, agent_runtime_arn, qualifier \\ nil, runtime_session_id \\ nil, options \\ [])

View Source

Retrieves the A2A agent card associated with an AgentCore Runtime agent.

Link to this function

get_batch_evaluation(client, batch_evaluation_id, options \\ [])

View Source

Retrieves detailed information about a batch evaluation, including its status, configuration, results, and any error details.

Link to this function

get_browser_session(client, browser_identifier, session_id, options \\ [])

View Source

Retrieves detailed information about a specific browser session in Amazon Bedrock AgentCore.

This operation returns the session's configuration, current status, associated streams, and metadata.

To get a browser session, you must specify both the browser identifier and the session ID. The response includes information about the session's viewport configuration, timeout settings, and stream endpoints.

The following operations are related to GetBrowserSession:

StartBrowserSession ListBrowserSessions

* StopBrowserSession

Link to this function

get_code_interpreter_session(client, code_interpreter_identifier, session_id, options \\ [])

View Source

Retrieves detailed information about a specific code interpreter session in Amazon Bedrock AgentCore.

This operation returns the session's configuration, current status, and metadata.

To get a code interpreter session, you must specify both the code interpreter identifier and the session ID. The response includes information about the session's timeout settings and current status.

The following operations are related to GetCodeInterpreterSession:

StartCodeInterpreterSession ListCodeInterpreterSessions

* StopCodeInterpreterSession

Link to this function

get_event(client, actor_id, event_id, memory_id, session_id, options \\ [])

View Source

Retrieves information about a specific event in an AgentCore Memory resource.

To use this operation, you must have the bedrock-agentcore:GetEvent permission.

Link to this function

get_memory_record(client, memory_id, memory_record_id, options \\ [])

View Source

Retrieves a specific memory record from an AgentCore Memory resource.

To use this operation, you must have the bedrock-agentcore:GetMemoryRecord permission.

Link to this function

get_payment_instrument(client, input, options \\ [])

View Source

Get a payment instrument by ID

Link to this function

get_payment_instrument_balance(client, input, options \\ [])

View Source

Get the balance of a payment instrument

Link to this function

get_payment_session(client, input, options \\ [])

View Source

Get a payment session

Link to this function

get_recommendation(client, recommendation_id, options \\ [])

View Source

Retrieves detailed information about a recommendation, including its configuration, status, and results.

Link to this function

get_resource_api_key(client, input, options \\ [])

View Source

Retrieves the API key associated with an API key credential provider.

Link to this function

get_resource_oauth2_token(client, input, options \\ [])

View Source

Returns the OAuth 2.0 token of the provided resource.

Link to this function

get_resource_payment_token(client, input, options \\ [])

View Source

Generates authentication tokens for payment providers that use vendor-specific authentication mechanisms.

Link to this function

get_workload_access_token(client, input, options \\ [])

View Source

Obtains a workload access token for agentic workloads not acting on behalf of a user.

Link to this function

get_workload_access_token_for_j_w_t(client, input, options \\ [])

View Source

Obtains a workload access token for agentic workloads acting on behalf of a user, using a JWT token.

Link to this function

get_workload_access_token_for_user_id(client, input, options \\ [])

View Source

Obtains a workload access token for agentic workloads acting on behalf of a user, using the user's ID.

Link to this function

invoke_agent_runtime(client, agent_runtime_arn, input, options \\ [])

View Source

Sends a request to an agent or tool hosted in an Amazon Bedrock AgentCore Runtime and receives responses in real-time.

To invoke an agent, you can specify either the AgentCore Runtime ARN or the agent ID with an account ID, and provide a payload containing your request. When you use the agent ID instead of the full ARN, you don't need to URL-encode the identifier. You can optionally specify a qualifier to target a specific endpoint of the agent.

This operation supports streaming responses, allowing you to receive partial responses as they become available. We recommend using pagination to ensure that the operation returns quickly and successfully when processing large responses.

For example code, see Invoke an AgentCore Runtime agent.

If you're integrating your agent with OAuth, you can't use the Amazon Web Services SDK to call InvokeAgentRuntime. Instead, make a HTTPS request to InvokeAgentRuntime. For an example, see Authenticate and authorize with Inbound Auth and Outbound Auth.

To use this operation, you must have the bedrock-agentcore:InvokeAgentRuntime permission. If you are making a call to InvokeAgentRuntime on behalf of a user ID with the X-Amzn-Bedrock-AgentCore-Runtime-User-Id header, You require permissions to both actions (bedrock-agentcore:InvokeAgentRuntime and bedrock-agentcore:InvokeAgentRuntimeForUser).

Link to this function

invoke_agent_runtime_command(client, agent_runtime_arn, input, options \\ [])

View Source

Executes a command in a runtime session container and streams the output back to the caller.

This operation allows you to run shell commands within the agent runtime environment and receive real-time streaming responses including standard output and standard error.

To invoke a command, you must specify the agent runtime ARN and a runtime session ID. The command execution supports streaming responses, allowing you to receive output as it becomes available through contentStart, contentDelta, and contentStop events.

To use this operation, you must have the bedrock-agentcore:InvokeAgentRuntimeCommand permission.

Link to this function

invoke_browser(client, browser_identifier, input, options \\ [])

View Source

Invokes an operating system-level action on a browser session in Amazon Bedrock AgentCore.

This operation provides direct OS-level control over browser sessions, enabling mouse actions, keyboard input, and screenshots that the WebSocket-based Chrome DevTools Protocol (CDP) cannot handle — such as interacting with print dialogs, context menus, and JavaScript alerts.

You send a request with exactly one action in the BrowserAction union, and receive a corresponding result in the BrowserActionResult union.

The following operations are related to InvokeBrowser:

StartBrowserSession GetBrowserSession

* StopBrowserSession

Link to this function

invoke_code_interpreter(client, code_interpreter_identifier, input, options \\ [])

View Source

Executes code within an active code interpreter session in Amazon Bedrock AgentCore.

This operation processes the provided code, runs it in a secure environment, and returns the execution results including output, errors, and generated visualizations.

To execute code, you must specify the code interpreter identifier, session ID, and the code to run in the arguments parameter. The operation returns a stream containing the execution results, which can include text output, error messages, and data visualizations.

This operation is subject to request rate limiting based on your account's service quotas.

The following operations are related to InvokeCodeInterpreter:

StartCodeInterpreterSession GetCodeInterpreterSession

Link to this function

invoke_harness(client, input, options \\ [])

View Source

Operation to invoke a Harness.

Link to this function

list_a_b_tests(client, max_results \\ nil, next_token \\ nil, options \\ [])

View Source

Lists all A/B tests in the account.

Link to this function

list_actors(client, memory_id, input, options \\ [])

View Source

Lists all actors in an AgentCore Memory resource.

We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:ListActors permission.

Link to this function

list_batch_evaluations(client, max_results \\ nil, next_token \\ nil, options \\ [])

View Source

Lists all batch evaluations in the account, providing summary information about each evaluation's status and configuration.

Link to this function

list_browser_sessions(client, browser_identifier, input, options \\ [])

View Source

Retrieves a list of browser sessions in Amazon Bedrock AgentCore that match the specified criteria.

This operation returns summary information about each session, including identifiers, status, and timestamps.

You can filter the results by browser identifier and session status. The operation supports pagination to handle large result sets efficiently.

We recommend using pagination to ensure that the operation returns quickly and successfully when retrieving large numbers of sessions.

The following operations are related to ListBrowserSessions:

StartBrowserSession GetBrowserSession

Link to this function

list_code_interpreter_sessions(client, code_interpreter_identifier, input, options \\ [])

View Source

Retrieves a list of code interpreter sessions in Amazon Bedrock AgentCore that match the specified criteria.

This operation returns summary information about each session, including identifiers, status, and timestamps.

You can filter the results by code interpreter identifier and session status. The operation supports pagination to handle large result sets efficiently.

We recommend using pagination to ensure that the operation returns quickly and successfully when retrieving large numbers of sessions.

The following operations are related to ListCodeInterpreterSessions:

StartCodeInterpreterSession GetCodeInterpreterSession

Link to this function

list_events(client, actor_id, memory_id, session_id, input, options \\ [])

View Source

Lists events in an AgentCore Memory resource based on specified criteria.

We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:ListEvents permission.

Link to this function

list_memory_extraction_jobs(client, memory_id, input, options \\ [])

View Source

Lists all long-term memory extraction jobs that are eligible to be started with optional filtering.

To use this operation, you must have the bedrock-agentcore:ListMemoryExtractionJobs permission.

Link to this function

list_memory_records(client, memory_id, input, options \\ [])

View Source

Lists memory records in an AgentCore Memory resource based on specified criteria.

We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:ListMemoryRecords permission.

Link to this function

list_payment_instruments(client, input, options \\ [])

View Source

List payment instruments for a manager

Link to this function

list_payment_sessions(client, input, options \\ [])

View Source

List payment manager sessions

Link to this function

list_recommendations(client, max_results \\ nil, next_token \\ nil, status_filter \\ nil, options \\ [])

View Source

Lists all recommendations in the account, with optional filtering by status.

Link to this function

list_sessions(client, actor_id, memory_id, input, options \\ [])

View Source

Lists sessions in an AgentCore Memory resource based on specified criteria.

We recommend using pagination to ensure that the operation returns quickly and successfully.

Empty sessions are automatically deleted after one day.

To use this operation, you must have the bedrock-agentcore:ListSessions permission.

Link to this function

process_payment(client, input, options \\ [])

View Source

Process a payment transaction

Link to this function

retrieve_memory_records(client, memory_id, input, options \\ [])

View Source

Searches for and retrieves memory records from an AgentCore Memory resource based on specified search criteria.

We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:RetrieveMemoryRecords permission.

Link to this function

save_browser_session_profile(client, profile_identifier, input, options \\ [])

View Source

Saves the current state of a browser session as a reusable profile in Amazon Bedrock AgentCore.

A browser profile captures persistent browser data such as cookies and local storage from an active session, enabling you to reuse this data in future browser sessions.

To save a browser session profile, you must specify the profile identifier, browser identifier, and session ID. The session must be active when saving the profile. Once saved, the profile can be used with the StartBrowserSession operation to initialize new sessions with the stored browser state.

Browser profiles are useful for scenarios that require persistent authentication, maintaining user preferences across sessions, or continuing tasks that depend on previously stored browser data.

The following operations are related to SaveBrowserSessionProfile:

StartBrowserSession GetBrowserSession

Link to this function

search_registry_records(client, input, options \\ [])

View Source

Searches for registry records using semantic, lexical, or hybrid queries.

Returns metadata for matching records ordered by relevance within the specified registry.

Link to this function

start_batch_evaluation(client, input, options \\ [])

View Source

Starts a batch evaluation job that evaluates agent performance across multiple sessions.

Batch evaluations pull agent traces from CloudWatch Logs or an existing online evaluation configuration and run specified evaluators and insights against them.

Link to this function

start_browser_session(client, browser_identifier, input, options \\ [])

View Source

Creates and initializes a browser session in Amazon Bedrock AgentCore.

The session enables agents to navigate and interact with web content, extract information from websites, and perform web-based tasks as part of their response generation.

To create a session, you must specify a browser identifier and a name. You can also configure the viewport dimensions to control the visible area of web content. The session remains active until it times out or you explicitly stop it using the StopBrowserSession operation.

The following operations are related to StartBrowserSession:

GetBrowserSession UpdateBrowserStream

SaveBrowserSessionProfile StopBrowserSession

* InvokeBrowser

Link to this function

start_code_interpreter_session(client, code_interpreter_identifier, input, options \\ [])

View Source

Creates and initializes a code interpreter session in Amazon Bedrock AgentCore.

The session enables agents to execute code as part of their response generation, supporting programming languages such as Python for data analysis, visualization, and computation tasks.

To create a session, you must specify a code interpreter identifier and a name. The session remains active until it times out or you explicitly stop it using the StopCodeInterpreterSession operation.

The following operations are related to StartCodeInterpreterSession:

InvokeCodeInterpreter GetCodeInterpreterSession

* StopCodeInterpreterSession

Link to this function

start_memory_extraction_job(client, memory_id, input, options \\ [])

View Source

Starts a memory extraction job that processes events that failed extraction previously in an AgentCore Memory resource and produces structured memory records.

When earlier extraction attempts have left events unprocessed, this job will pick up and extract those as well.

To use this operation, you must have the bedrock-agentcore:StartMemoryExtractionJob permission.

Link to this function

start_recommendation(client, input, options \\ [])

View Source

Starts a recommendation job that analyzes agent traces and generates optimization suggestions for system prompts or tool descriptions to improve agent performance.

Link to this function

stop_batch_evaluation(client, batch_evaluation_id, input, options \\ [])

View Source

Stops a running batch evaluation.

Sessions that have already been evaluated retain their results.

Link to this function

stop_browser_session(client, browser_identifier, input, options \\ [])

View Source

Terminates an active browser session in Amazon Bedrock AgentCore.

This operation stops the session, releases associated resources, and makes the session unavailable for further use.

To stop a browser session, you must specify both the browser identifier and the session ID. Once stopped, a session cannot be restarted; you must create a new session using StartBrowserSession.

The following operations are related to StopBrowserSession:

StartBrowserSession GetBrowserSession

Link to this function

stop_code_interpreter_session(client, code_interpreter_identifier, input, options \\ [])

View Source

Terminates an active code interpreter session in Amazon Bedrock AgentCore.

This operation stops the session, releases associated resources, and makes the session unavailable for further use.

To stop a code interpreter session, you must specify both the code interpreter identifier and the session ID. Once stopped, a session cannot be restarted; you must create a new session using StartCodeInterpreterSession.

The following operations are related to StopCodeInterpreterSession:

StartCodeInterpreterSession GetCodeInterpreterSession

Link to this function

stop_runtime_session(client, agent_runtime_arn, input, options \\ [])

View Source

Stops a session that is running in an running AgentCore Runtime agent.

Link to this function

update_a_b_test(client, ab_test_id, input, options \\ [])

View Source

Updates an A/B test's configuration, including variants, traffic allocation, evaluation settings, or execution status.

Link to this function

update_browser_stream(client, browser_identifier, input, options \\ [])

View Source

Updates a browser stream.

To use this operation, you must have permissions to perform the bedrock:UpdateBrowserStream action.