Sold by: UST
UST SmartResolution auto-resolves infrastructure incidents end-to-end using multi-agent AI, cutting MTTR and reducing ops toil for teams managing Kubernetes and cloud workloads on AWS.
Overview
Reduce MTTR and Eliminate Manual Remediation with Agentic AI
UST SmartOps SmartResolution is a professional services engagement that deploys a fully agentic, multi-agent AI remediation engine into your AWS environment. It auto-resolves recurring infrastructure incidents from detection to closed ticket - keeping humans in control only when genuine uncertainty exists.
How It Works: The Six-Stage Loop
- Observe: SmartOps Pulse monitors your Kubernetes clusters and cloud infrastructure for anomalies.
- Parse: A detected anomaly is structured into an AIOps alert.
- Ticket: A ticket is opened and bidirectionally synced to your ITSM platform.
- Analyze: The Prompt Agent extracts intent; the Supervisor Agent orchestrates the Knowledge Base Agent (tree-structured RAG retrieval) to match the issue against known SOPs and score confidence.
- Act or Escalate: When confidence exceeds your configured threshold, the Tool Calling Agent executes remediation via the Action Dispatcher and auto-closes the ticket. When confidence falls short, the Reviewer Agent routes the case to a human approver with full context.
- Log: Every decision - automated or human-approved - is recorded for audit.
Key Features
- Supervisor Agent orchestration across specialist agents (Prompt, Knowledge Base, Reviewer, Tool Calling)
- Tree-structured knowledge base with RAG-based SOP matching
- Configurable confidence threshold gating automation vs. human-in-the-loop (HITL)
- Durable, ordered async queue (Action Dispatcher) for reliable execution
- Native bidirectional sync with ITSM and AIOps ticketing
- Full audit trail of every agent decision and human approval
Key Benefits
- Eliminates manual remediation for recurring issues, freeing SRE and ops teams
- Cuts mean time to resolution (MTTR) by removing human wait-time from the resolution path
- Keeps humans in control of genuinely uncertain or high-risk incidents
- Consistent, repeatable resolution with no tribal-knowledge dependency
- Scales incident response without adding operations headcount
Use Cases
- Kubernetes auto-remediation: Pod OOMKill detected, memory limit patched, deployment rolled, ticket closed - all without human intervention across clusters running hundreds of microservices on Amazon EKS.
- Access-restoration workflows: Password resets and permission grants executed with full audit trail, integrated with your identity provider.
- Recurring service issues: Documented SOPs applied automatically for known failure patterns (disk pressure, certificate expiry, scaling events).
- Intelligent escalation: Only genuinely ambiguous or high-risk cases reach human reviewers, with complete context attached.
Engagement Overview
Phase 1 - Discovery and Scoping (Weeks 1-2): Environment assessment, ITSM integration mapping, identification of high-frequency incident categories suitable for automation.
Phase 2 - Configuration and Pilot (Weeks 3-6): Knowledge base population with your SOPs, confidence-threshold tuning, Action Dispatcher integration, pilot deployment on a subset of workloads.
Phase 3 - Production Rollout (Weeks 7-10): Full deployment, HITL workflow activation, team training, and handoff of configured system.
Deliverables: Configured knowledge base, integrated ITSM sync, tuned confidence thresholds, runbook library, and operational documentation.
Prerequisites
- Kubernetes clusters (Amazon EKS recommended) or AWS cloud infrastructure
- Compatible ITSM platform (ServiceNow, Jira Service Management, or equivalent)
- Existing SOPs or runbooks for target incident categories
- Designated SRE or platform engineering liaison for the engagement
AWS Integration
SmartResolution is built to operate natively within AWS environments, leveraging Amazon EKS, AWS Lambda, Amazon Bedrock for foundation model inference, and Amazon CloudWatch for observability signals.
Next Step
Contact UST through AWS Marketplace Messaging to schedule a 30-minute discovery call and scope a pilot for your environment.
Highlights
- Fully agentic remediation - a Supervisor Agent orchestrates Prompt, Knowledge Base, Reviewer, and Tool Calling agents with no fixed script. Every decision is logged for audit, and the system adapts to your environment's SOPs through RAG-based retrieval against a tree-structured knowledge base. Operates natively on AWS with Amazon EKS, Amazon Bedrock, and CloudWatch integration.
- Zero manual touch on the happy path - from anomaly detection through ITSM ticket creation to automated remediation and ticket closure. The Action Dispatcher uses a durable, ordered async queue to ensure reliable execution. Designed to handle recurring Kubernetes and cloud infrastructure incidents such as pod OOMKills, disk pressure, certificate expiry, and scaling events without human intervention.
- Confidence-gated human-in-the-loop - a configurable threshold determines when the system acts autonomously versus when it routes to a human reviewer. Reviewers see full incident context and can approve or reject with a logged reason. Only genuinely uncertain or high-risk cases reach humans, keeping your team focused on novel problems rather than repetitive remediation tasks.
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Pricing
Custom pricing options
Pricing is based on your specific requirements and eligibility. To get a custom quote for your needs, request a private offer.
Legal
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Support
Vendor support
Engagement Process
UST delivers SmartResolution through a structured professional services engagement:
- Discovery Call: Contact UST via AWS Marketplace Messaging to schedule a 30-minute scoping session. UST will assess your environment, ITSM platform, and incident categories.
- Onboarding: A dedicated communication channel is established for ongoing collaboration. UST works with your designated SRE or platform engineering liaison to configure the knowledge base, integrate ITSM, and tune confidence thresholds.
- Pilot and Production: Phased deployment with defined milestones, culminating in a full handoff of the configured system, runbook library, and operational documentation.
Buyer Responsibilities
- Provide access to target Kubernetes clusters or AWS infrastructure
- Supply ITSM credentials and existing SOPs or runbooks
- Designate a technical liaison for the engagement duration
Support Channels
- AWS Marketplace Messaging: Available for initial inquiries, scoping questions, and engagement requests.
- Dedicated Communication Channel: Established during onboarding for ongoing project collaboration and issue resolution.
- Email Support: For pre-sales and post-engagement inquiries, contact the UST Sales team at salesteam_tes@ust.com .
- General Inquiries: Visit https://www.ust.com to learn more about UST services.
Escalation
If an issue is unresolved through your dedicated channel, escalate via AWS Marketplace Messaging or email for priority routing.