◈ AWS AGENTCORE BLUEPRINTS
PART V · MULTI-AGENT AND ARCHITECTURE · CHAPTER 35 / 36
TOCCONSULTING.FR
AMAZON BEDROCK / ARCHITECTURE C04 / GOVERNANCE

GOVERNANCE AT ORG SCALEPRACTICAL

CHAPTER 35 / 36
TOPIC see every account's agents from one place
REV 2026.07
IN PLAIN WORDS

You will set up one central account that can see the agent traces and metrics from every other account. AWS calls this cross-account observability: the central account makes a sink, each team account makes a link to it, then one console shows everything. Terms: monitoring account = the central one; source account = a team's account; OAM = Observability Access Manager (the sink/link plumbing); StackSets = deploy one template to many accounts at once.

[ 1 ] IN THE MONITORING ACCOUNT, CREATE A SINK (accepts telemetry org-wide)
# CloudFormation, in the central monitoring account
Resources:
  ObservabilitySink:
    Type: AWS::Oam::Sink
    Properties:
      Name: AgentCoreObservabilitySink
      Policy:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Principal: '*'
            Action: ['oam:CreateLink', 'oam:UpdateLink']
            Resource: '*'
            Condition:
              StringEquals: { aws:PrincipalOrgID: '<your-org-id>' }   # all accounts in your org
              ForAllValues:StringEquals:
                oam:ResourceTypes: ['AWS::Logs::LogGroup', 'AWS::CloudWatch::Metric']
Outputs:
  SinkArn: { Value: !GetAtt ObservabilitySink.Arn }   # share this ARN with source accounts
[ 2 ] IN EACH SOURCE ACCOUNT, CREATE A LINK (roll out with StackSets)
# CloudFormation, in every team (source) account
Resources:
  ObservabilityLink:
    Type: AWS::Oam::Link
    Properties:
      LabelTemplate: '$AccountName'
      ResourceTypes: ['AWS::Logs::LogGroup',
                      'AWS::CloudWatch::Metric']
      SinkIdentifier: '<sink-arn-from-monitoring-account>'
ROLL IT OUT
Deploy this link to all member accounts at once with AWS CloudFormation StackSets. Linking through AWS Organizations also onboards new accounts automatically. Each source account needs its own observability on (Transaction Search + Metrics and Logs).
[ 3 ] VIEW EVERYTHING IN THE MONITORING ACCOUNT
Open the AgentCore Observability console in the monitoring account: it automatically shows agents, sessions, traces, and metrics from every linked account. Filter the sessions and traces tables by Account ID to focus on one team.
Limits: cross-account observability is per Region (monitoring and source accounts must be in the same Region); both must have Metrics and Logs enabled; data is only visible while the OAM link is active. Pair this with an organization CloudTrail and cost-allocation tags for full audit and per-team cost.
SRC: AWS AgentCore Developer Guide (monitor AgentCore resources across accounts) + CloudWatch OAM. Concept: chapter 34.
DRAWN 2026.06, REV 2026.07.26
◄ PREVIOUS · CH 34
Governance at Org Scale, Plain Language
NEXT · CH 36 ►
Multi-Region and Distribution, Plain Language
AWS AGENTCORE BLUEPRINTS · CONTENTS
Back to tocconsulting.fr Cover & Table of Contents
PART I · FOUNDATIONS
01AgentCore Overview, Plain LanguageCONCEPT02AgentCore, Key Terms in Plain LanguageCONCEPT03AgentCore, Common Mistakes ExplainedCONCEPT04Inside an AgentCore Agent, BlueprintCONCEPT05Harness, Practical 1, Strands PathPRACTICAL06Harness, Practical 2, Managed HarnessPRACTICAL
PART II · CORE SERVICES
07AgentCore Runtime, Plain LanguageCONCEPT08AgentCore Runtime, PracticalPRACTICAL09AgentCore Memory, Plain LanguageCONCEPT10AgentCore Memory, PracticalPRACTICAL11AgentCore Gateway, Plain LanguageCONCEPT12AgentCore Gateway, PracticalPRACTICAL13AgentCore Identity, Plain LanguageCONCEPT14AgentCore Identity, PracticalPRACTICAL
PART III · TOOLS AND OPERATIONS
15AgentCore Code Interpreter, Plain LanguageCONCEPT16AgentCore Code Interpreter, PracticalPRACTICAL17AgentCore Browser, Plain LanguageCONCEPT18AgentCore Browser, PracticalPRACTICAL19AgentCore Observability, Plain LanguageCONCEPT20AgentCore Observability, PracticalPRACTICAL21AgentCore Evaluations, Plain LanguageCONCEPT22AgentCore Evaluations, PracticalPRACTICAL
PART IV · GOVERNANCE AND TRANSACTIONS
23AgentCore Policy, Plain LanguageCONCEPT24AgentCore Policy, PracticalPRACTICAL25AgentCore Registry, Plain LanguageCONCEPT26AgentCore Registry, PracticalPRACTICAL27AgentCore Payments, Plain LanguageCONCEPT28AgentCore Payments, PracticalPRACTICAL
PART V · MULTI-AGENT AND ARCHITECTURE
29A2A and Multi-Agent, Plain LanguageCONCEPT30A2A and Multi-Agent, PracticalPRACTICAL31Architecture Patterns, Plain LanguageCONCEPT32Multi-Tenant Agents, Plain LanguageCONCEPT33Agent Security and Threat Model, Plain LanguageCONCEPT34Governance at Org Scale, Plain LanguageCONCEPT35Governance at Org Scale, PracticalPRACTICAL36Multi-Region and Distribution, Plain LanguageCONCEPT