Announcing: Resolve AI Expands Coverage for AWS

We are excited to announce that Resolve AI has expanded to offer full support for all AWS services, providing AWS customers with AI for prod to autonomously investigate incidents, improve operations across their AWS and Kubernetes environments, and code with production context. The new capabilities will be on full display at re:Invent 2025 - visit booth 712.

Resolve AI transforms application troubleshooting and perforwith mance management for AWS CloudOps into natural, conversational experiences that enable fast resolution with AI agents. With a quick and secure AWS Identity and Access Management (IAM) integration, Resolve AI multi-agent system discovers context about your AWS infrastructure, including Amazon Elastic Container Service (ECS), Amazon Elastic Compute Cloud (EC2), Amazon Relational Database Service (RDS), Amazon Managed Streaming for Apache Kafka (MSK), Application Load Balancer (ALB), Amazon Managed Service for Prometheus, Amazon Managed Kubernetes Service (EKS) and more. No complex setup, scripts, or additional configuration required.

Leveraging Resolve AI represents an opportunity for engineering teams to identify an incident’s root cause in 10 minutes, backed with detailed evidence to support running production systems built using AWS services. Teams can discover cost optimization across observability and infrastructure spend, enhance security, proactively debug production, design improved software, and more. In this blog, we'll explore the benefits of having an AI SRE that works seamlessly with your AWS services, explain how it works, and share how you can get started.

Why an AI for prod matters for AWS environment

AWS provides the foundation for modern cloud infrastructure with powerful capabilities across compute, storage, databases, AI, and more. As teams scale their operations across multiple AWS services, including Amazon ECS, Amazon EC2, Amazon RDS, Amazon MSK, Amazon EKS, alongside third-party observability tools, they need to correlate signals across Amazon CloudWatch metrics, AWS CloudTrail events, RDS Performance Insights data, service configurations, and recent code changes in GitHub to identify patterns and trends. Engineers often work across multiple tools and interfaces during incident investigations, which can be time-consuming, especially during critical moments.

Resolve AI helps teams work more efficiently across your AWS stack and other platforms by autonomously discovering and reasoning over your environment alongside code, third-party observability data, and infrastructure for incident resolution and day-to-day production work. It brings autonomous and conversational intelligence to your existing AWS infrastructure, enabling engineers to automatically get to the root cause, ask natural questions, and receive evidence-backed answers that span multiple AWS services, all without switching between tools or manually piecing together signals.

Key benefits of AI for prod include:

• Comprehensive AWS coverage: Native support across Amazon ECS, Amazon EC2, Amazon RDS, Amazon MSK, ALB, Amazon CloudWatch, AWS CloudTrail, Amazon Managed Service for Prometheus, Amazon EKS, and more, enabling teams to autonomously investigate from day one.
• Conversational operations: Ask questions like "Why is RDS slow?" or "What changed before MSK consumer lag spiked?" and see investigations that correlate Performance Insights, CloudTrail events, telemetry, and code changes.
• Safe, auditable change: Resolve AI generates remediation plans, including code changes, for human review and execution, keeping engineers in control while accelerating resolution.
• Unified telemetry approach: Integrates CloudWatch alongside Datadog, New Relic, Splunk, Amazon Managed Grafana, Amazon Managed Service for Prometheus, and OpenSearch to support complete root cause analysis across observability data and tools.
• Immediate time to value: Quick and secure IAM setup enables teams to run real-world scenarios in their AWS accounts from the very first day.

How it works

Resolve AI integrates with your AWS infrastructure. Once connected via IAM, Resolve AI discovers relevant context across your environment and maintains a comprehensive understanding of your AWS services, configurations, and operational state. This enables Resolve AI to quickly and thoroughly investigate incidents, correlate findings across services, and deliver explanations grounded in actual signals and events within minutes.

The workflow is straightforward:

1. Quick IAM integration: Connect with a secure, least-privilege setup. Select the accounts and services to include based on your team's scope of work.
2. Automatic discovery: Resolve AI automatically discovers relevant context across Amazon ECS, Amazon EC2, Amazon RDS, Amazon MSK, ALB, Amazon Managed Service for Prometheus, and more during incident investigations and day-to-day production work.
3. Converse with your AWS infrastructure: Ask natural questions, and Resolve AI translates them into the appropriate queries across AWS services, analyzes the resulting data, and delivers synthesized answers with citations to underlying signals.
4. Move to safe change: Use outputs generated from Resolve AI for human review, ensuring auditability and control.

With this capability, teams can investigate all their AWS services through a unified conversational interface, making the complexity of multi-service architectures more manageable.

What you can do on day one

We are covering a large set of services with AWS; here's a small sampling of scenarios of how you can use Resolve AI for AWS:

• RDS slow query, identify the source: Use Performance Insights and pg_stat_statements to determine which service or container is issuing the slow query, then find the code change that introduced it.
• RDS is overwhelmed by traffic: Use Performance Insights with your telemetry provider to identify which service is causing RDS to receive an increased number of queries.
• MSK consumer lag: Detect the CloudTrail event that changed the consumer service IAM policy and removed access to MSK.
• Configuration drift: Surface when an S3 bucket policy is switched to public, or trace a drop in requests to a service back to a security group configuration change.
• ALB routing and network paths: Debug routing or path anomalies through natural questions about ALB configuration, target group state, and recent deployments.
• Root cause with unified signals: Use Amazon CloudWatch alongside Datadog, New Relic, Splunk, Amazon Managed Service for Prometheus, and OpenSearch to build complete causal chains.

Getting started

Discover how Resolve AI can amplify your AWS infrastructure, enhancing developer productivity and customer satisfaction. Available to all Resolve AI customers, it's easy to get started in five simple steps:

1. Connect AWS via IAM with an attached SecurityAudit role.
2. Select the accounts and services to include.
3. Choose a scenario, for example, RDS slow queries or MSK consumer lag.
4. Run the drill in Slack, or in the console.
5. Review the findings and recommendations, then put them into action.

What's next

Resolve AI’s robust support for AWS is available today, and it's just the beginning. As we continue to deepen our AWS service coverage and evolve our AI capabilities, the gap between asking a question about your infrastructure and receiving a complete, actionable answer will continue to shrink. We will continue to march towards closed-loop remediations and full agent support for software engineering.

The teams that win will be those that can operate and optimize AWS services with the least friction, the fastest time to resolution, and the most leverage per engineer. They will be the teams who turn production engineering from reactive firefighting into proactive system management. That's what AWS customers can now get with Resolve AI.

Book a demo with Resolve AI to see how AWS and Resolve works better together. Available on AWS Marketplace.