Normalized claim
MTTD: 80% decrease
Initial estimates show that MTTD, MTTR, and MTTK have been reduced by 80, 50, and 83 percent, respectively.
C Spire built an agentic AI assistant on AWS to reduce network incident response times
Use case typeIT operationsUpdated Jul 15, 2026
C Spire built an agentic AI assistant on AWS to help network technicians solve issues more efficiently and keep its network resilient. The solution gives technicians natural-language access to equipment manuals, technical documentation, and network schematics while combining alarms, logs, and configurations to support diagnosis and resolution.
- Organization
- C Spire
- Industry
- Tech & Comms
- Location
- United States
- Published
- July 2026
Reported outcomes
−80%
MTTDOther quantified impact
−50%MTTR−83%MTTK−50%new technician proficiency time
Strategic outcomes
Customer experience & trustImproved network reliabilityCustomer experience & trustBetter customer experienceEmployee experienceReduced technician ramp-up time
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
MTTR: 50% decrease
Initial estimates show that MTTD, MTTR, and MTTK have been reduced by 80, 50, and 83 percent, respectively.
Normalized claim
MTTK: 83% decrease
Initial estimates show that MTTD, MTTR, and MTTK have been reduced by 80, 50, and 83 percent, respectively.
Normalized claim
New technician proficiency time: 50% decrease
the time it takes for a new technician to become proficient from 6 months to 3 months
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- C Spire
- Provider
- AWS
- Maturity
- Unknown
- Linked source
- AWS Solutions Case Study
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 3
- 1IT operations
- 2Agent orchestration
- 3Knowledge management
- The company needed to proactively prevent service disruptions and reduce mean time to detect, know, and repair network incidents.
- Technicians had to work through repetitive diagnostics and root-cause analysis while bridging knowledge gaps during incidents.
- Built the AWS Autonomous Operations Solution as an agentic AI assistant embedded in network operations center workflows.
- Used Amazon Bedrock with Claude and Amazon Nova for natural-language reasoning over technical documentation.
- Used AWS Glue and Amazon Neptune to integrate and connect alarms, logs, configurations, and other network data for incident analysis.
- Initial estimates show 80% reduction in MTTD, 50% reduction in MTTR, and 83% reduction in MTTK.
- New technician proficiency time fell from 6 months to 3 months.
- Rollout began after 8 weeks of development and is being expanded across network segments.
Architecture
C Spire worked with AWS Professional Services to build the AWS Autonomous Operations Solution on Amazon Bedrock, using Claude and Amazon Nova for natural-language reasoning, AWS Glue for data integration, and Amazon Neptune for connected data and graph-based context across alarms, logs, configurations, manuals, and schematics.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jul 15, 2026Publisher: AWSEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.