Intuit's Bedrock failover agent cut disaster recovery from hours to about 20 minutes across thousands of microservices

AWS Machine Learning Blog·medium signalXBlueskyLinkedInCopy link

Intuit has been running EWOK Agent in production for eight months, letting engineers type 'failover payments-gateway in production' in the engineering portal or an IDE over MCP, after which the agent validates readiness, checks policy compliance and orchestrates recovery across compute, database, cache and traffic layers. Recovery time dropped from several hours to roughly 20 minutes for supported workloads across thousands of microservices spanning multiple AWS regions. The architecture separates a skill layer of typed, versioned capabilities compiled into tool specs from a deterministic EWOK execution API, which keeps the foundation model a configuration value rather than an architectural commitment.