Intuit Automates Disaster Recovery Decisions with Bedrock AI Agent

Intuit built EWOK Agent, an AI-powered disaster recovery assistant using Amazon Bedrock, to automate decision-making in failover scenarios across its microservices infrastructure. The agent encodes failover knowledge as skills and uses foundation models to determine recovery workflows, while EWOK handles deterministic execution. Teams at Intuit have used it for eight months to reduce recovery coordination from hours to about 20 minutes for supported workloads.
TL;DR
- Intuit deployed EWOK Agent, an agentic system built on Amazon Bedrock, to automate disaster recovery decisions across thousands of microservices
- The agent handles decision-making (which recovery workflow to use, policy compliance) while EWOK executes the underlying infrastructure actions
- Recovery times for supported workloads dropped from several hours to approximately 20 minutes
- The system has been in production use across Intuit teams for eight months and is delivered as a plugin for the Engineering portal and IDEs
Why It Matters
Disaster recovery at scale requires both fast execution and correct decision-making under pressure. Intuit's approach separates these concerns, using AI to handle the knowledge-intensive decision layer (which recovery workflow applies, policy exceptions, emergency overrides) while keeping deterministic infrastructure orchestration separate. This pattern shows how agentic AI can augment operational systems without replacing their core logic.
Business Impact
For companies operating mission-critical financial systems across multiple regions, failover speed and accuracy directly impact revenue and customer trust. Automating the decision layer reduces mean time to recovery and removes dependency on tribal knowledge held by senior engineers, improving operational resilience and team scalability.
Key Implications
- Agentic AI is moving beyond chatbots into production operational systems where decisions must be policy-aligned and auditable
- The separation of AI decision-making from deterministic execution is a viable pattern for high-stakes infrastructure operations
- Amazon Bedrock's multi-model access and managed infrastructure enabled Intuit to add reasoning without building custom ML infrastructure
What to Watch
Monitor whether Intuit expands EWOK Agent to additional failure scenarios or whether other enterprises adopt similar patterns for operational decision-making. Watch for how guardrails and audit trails evolve as agentic systems handle more critical business processes, and whether the model-execution separation pattern becomes standard practice in enterprise infrastructure automation.
Subscribe to the newsletter
The latest stories and analysis, delivered to your inbox.
Free. No spam. Unsubscribe any time.
