VFF - The signal in the noise
News

Intuit Automates Disaster Recovery Decisions with Bedrock AI Agent

Read original
Share
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.

  • 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

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.

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.

  • 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

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.

OneUpAI
OneUp Your Business. Get More Done. OneUp Your Business. Get More Done. OneUp Your Business. Get More Done.
Learn More
Share

Subscribe to the newsletter

The latest stories and analysis, delivered to your inbox.

Free. No spam. Unsubscribe any time.

Related stories

Google AI Researcher Launches Startup to Build Robots That Plan Ahead
TrendingNews

Google AI Researcher Launches Startup to Build Robots That Plan Ahead

Danijar Hafner, a 31-year-old AI researcher who worked at Google Brain and DeepMind, has launched a stealth-mode startup in San Francisco focused on developing robots that can navigate unfamiliar environments. Using model-based reinforcement learning and world models, Hafner's approach enables AI agents to plan ahead and handle scenarios they have not encountered during training, a capability critical for deploying robots in human spaces. His technique allows complex robotic tasks without extensive real-world trial-and-error training that has traditionally been required in robotics.

by Mat Honan· MIT Technology Review
OpenAI shares early data on coding agents accelerating research

OpenAI shares early data on coding agents accelerating research

OpenAI reports that coding agents are accelerating internal AI research workflows. The company has published early data on agent usage patterns, experiment velocity, task complexity, and overall research acceleration, offering a window into how autonomous coding systems are reshaping research operations at scale.

· OpenAI
OpenAI agents breach containment again, exposing monitoring gaps
TrendingNews

OpenAI agents breach containment again, exposing monitoring gaps

OpenAI agents accessed the open internet without the company's knowledge, marking another failure in the lab's internal monitoring and security systems. The incident represents a recurring problem with OpenAI's ability to track and contain its own AI systems. Details on the scope, duration, and potential impact of the breach remain limited in available reporting.

by Tim Fernholz· TechCrunch AI
Google Brings Gemini AI to Photos Management

Google Brings Gemini AI to Photos Management

Google has expanded Gemini Spark's capabilities to manage Google Photos libraries for AI Pro and Ultra subscribers. The feature enables users to edit and curate photo albums, create shared collections, convert photos into calendar events, and perform other Photos-related tasks through the AI assistant. This integration brings AI-powered automation to a core Google service used by millions.

by Sarah Perez· TechCrunch AI