For Agents
Retrieve DevOps Guru insights, anomalies, and recommendations, configure resource collections, and route notifications to downstream incident workflows.
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Amazon DevOps Guru, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Amazon DevOps Guru API.
Configure which AWS resources are analysed via UpdateResourceCollection scoped by CloudFormation stacks or tags
List and inspect operational insights with ListInsights, DescribeInsight, and SearchInsights
Pull related anomalies for an insight using ListAnomaliesForInsight to get supporting metrics and time ranges
Subscribe SNS topics for new insight notifications via AddNotificationChannel and RemoveNotificationChannel
GET STARTED
Use for: List proactive and reactive insights for the last 7 days, Get anomalies that contributed to a specific insight, Update the resource collection to track a new CloudFormation stack, Add an SNS topic as a DevOps Guru notification channel
Not supported: Does not handle remediation, log ingestion, or metric publishing — use for retrieving operational insights and configuring DevOps Guru analysis only.
Jentic publishes the only available OpenAPI document for Amazon DevOps Guru, keeping it validated and agent-ready.
Jentic publishes the only available OpenAPI specification for Amazon DevOps Guru, keeping it validated and agent-ready. Amazon DevOps Guru is a managed service that uses machine learning over CloudWatch metrics and CloudTrail events to detect anomalous behaviour in operational AWS workloads. The API lets you scope which resources DevOps Guru analyses, retrieve insights, anomalies, and recommendations, configure SNS notification channels, and set up Systems Manager OpsItem integration. Use it when an agent needs to automate insight triage or wire DevOps Guru output into existing incident workflows.
Enable Systems Manager OpsItem creation per insight through UpdateServiceIntegration
Provide feedback on insight usefulness with PutFeedback to tune future detection
Patterns agents use Amazon DevOps Guru API for, with concrete tasks.
★ Triage Operational Insights into Tickets
Wire DevOps Guru into the existing incident process by scoping resource collections to production CloudFormation stacks and routing every new insight to an SNS topic that fans out to PagerDuty or Slack. ListInsights and DescribeInsight let an agent enrich each alert with the underlying anomalies and recommended actions before paging a human.
Call AddNotificationChannel with an SNS topic ARN, then ListInsights filtered to the last 24 hours and DescribeInsight on each to enrich the ticket payload.
Scope Detection to a Production Workload
Use UpdateResourceCollection to point DevOps Guru at the CloudFormation stacks or tag set that defines the production workload, ensuring insights focus on business-critical resources rather than every account resource. ListInsights then returns only the relevant anomalies, keeping signal-to-noise high.
Call UpdateResourceCollection with ResourceCollection.CloudFormation.StackNames set to the prod stacks and verify with GetResourceCollection.
Auto-Create OpsItems for Each Insight
Enable Systems Manager OpsItem creation via UpdateServiceIntegration so every reactive insight automatically appears in the Systems Manager OpsCenter queue alongside the rest of the operations backlog. Engineers see the insight, recommendations, and related events in one place without polling DevOps Guru directly.
Call UpdateServiceIntegration with OpsCenter.OptInStatus set to ENABLED and confirm via DescribeServiceIntegration.
Agent-Driven Insight Triage
An AI agent connected via Jentic can poll DevOps Guru, pull the anomalies and recommendations that back each new insight, and decide whether to file a ticket, page on-call, or close as known. Jentic returns the matching DevOps Guru operation and schema so the agent can compose a multi-step triage flow without bespoke AWS SDK code.
Search Jentic for 'list DevOps Guru insights', load ListInsights, execute it with a 24-hour StartTimeRange, then DescribeInsight on each result and ListAnomaliesForInsight to assemble the triage context.
31 endpoints — jentic publishes the only available openapi specification for amazon devops guru, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/insights/{Id}
Describe a specific insight
/anomalies/{Id}
Describe a specific anomaly
/anomalies/insight/{InsightId}
List anomalies for an insight
/channels
Add a notification channel
/service-integrations
Enable Systems Manager OpsItem integration
/event-sources
Update event source configuration
/feedback
Submit feedback on an insight
/insights/{Id}
Describe a specific insight
/anomalies/{Id}
Describe a specific anomaly
/anomalies/insight/{InsightId}
List anomalies for an insight
/channels
Add a notification channel
/service-integrations
Enable Systems Manager OpsItem integration
Three things that make agents converge on Jentic-routed access.
Credential isolation
AWS access keys for DevOps Guru are stored encrypted in the Jentic vault. Jentic signs each DevOps Guru request with SigV4 at execution time and the agent only sees scoped, short-lived access — raw access keys never enter the agent's context.
Intent-based discovery
Agents search by intent (e.g., 'list DevOps Guru insights' or 'add an SNS notification channel') and Jentic returns the matching operation with its input schema, so the agent can call the right endpoint without browsing AWS documentation.
Time to first call
Direct DevOps Guru integration: 1-3 days for SigV4 signing, IAM scoping, and pagination handling. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
AWS CloudTrail
API event logs that DevOps Guru analyses for anomalous activity.
Choose CloudTrail when the agent needs the raw API event history rather than the ML-derived insights.
Amazon GuardDuty
Threat-focused anomaly detection rather than operational health.
Choose GuardDuty when the concern is security threats; choose DevOps Guru when the concern is operational performance.
Amazon EventBridge
Routes events including DevOps Guru notifications to downstream targets.
Choose EventBridge when the agent needs to fan DevOps Guru events out to multiple targets beyond a single SNS topic.
Specific to using Amazon DevOps Guru API through Jentic.
Why is there no official OpenAPI spec for Amazon DevOps Guru?
AWS does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Amazon DevOps Guru via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Amazon DevOps Guru API use?
DevOps Guru uses AWS Signature Version 4 (HMAC) signing with an AWS access key ID and secret access key. Through Jentic, those credentials live encrypted in the Jentic vault and are injected into signed requests at execution time, so the agent never sees the raw secret access key.
Can I limit DevOps Guru to a specific CloudFormation stack?
Yes. Call UpdateResourceCollection with ResourceCollection.CloudFormation.StackNames set to the stacks you want analysed. DevOps Guru will then constrain insights and anomalies to resources defined in those stacks.
What are the rate limits for the Amazon DevOps Guru API?
DevOps Guru shares standard AWS service quotas, which are managed per account and region rather than published as fixed per-second limits in the spec. Bulk insight retrieval should use pagination via NextToken and back off on ThrottlingException responses.
How do I get DevOps Guru insights into Slack via Jentic?
Search Jentic for 'list DevOps Guru insights', load ListInsights, execute it on a schedule, and forward the response to a Slack-posting operation also discovered via Jentic. Run pip install jentic and use the async search and execute pattern.
Does this API trigger remediation, or only surface findings?
The API surfaces insights, anomalies, and recommendations. Acting on a recommendation requires calling the underlying AWS service API (such as Auto Scaling or Lambda) directly — DevOps Guru itself does not execute remediation.
/event-sources
Update event source configuration
/feedback
Submit feedback on an insight