Cloud Intelligence™Cloud Intelligence™

This page is also available in Deutsch, Español, Français, Italiano, 日本語, and Português.

Opterrix Cuts Hail Analysis From 10 Hours to 10 Seconds

DoiT helped productionize a generative AI system on Vertex AI that turns storm imagery and sensor data into instant similarity search.

Cloud Intelligence™
Opterrix

Meet Opterrix

Opterrix is a cloud-native geospatial analytics platform built specifically for the insurance industry. The company integrates proprietary weather data, natural hazard peril scores, and predictive machine learning to help insurers optimize underwriting, respond to disasters, and manage risk in real-time. With a vision to modernize and accelerate the insurance value chain, particularly in personal and commercial lines, Opterrix delivers mission-critical tools that empower underwriters and analysts to make smarter, faster decisions.

The Challenge

Severe weather is becoming both more frequent and more intense, placing enormous pressure on insurers to assess and respond quickly. Hailstorms pose a unique challenge – they are localized, destructive, and unpredictable. Engineers were consuming up to 10 engineering hours per case manually digging through data to find matches – a slow, error-prone process that couldn't scale. Opterrix's lean team lacked the internal bandwidth, production architecture expertise, and implementation playbook to move quickly with GenAI.

The Solution

Opterrix engaged DoiT as a strategic partner to bring generative AI into production. DoiT helped develop a solution that utilized GenAI to analyze images of hailstones and storm metadata, identifying similar historical events based on geospatial proximity and storm patterns. Leveraging Vertex AI and multimodal embeddings, the system transforms storm imagery and sensor data into searchable, vectorized intelligence in seconds. DoiT also optimized Opterrix's Google Cloud environment for performance and cost, implementing usage-based guardrails and introducing Cloud Intelligence™.

Results

  • Replaced 10-hour manual process with automated solution delivering results in under 10 seconds
  • Compressed R&D cycles by 50% and increased delivery confidence
  • Improved unit economics while preserving performance and uptime through cloud infrastructure optimization
  • Elevated internal team capabilities with hands-on GenAI experience and governance frameworks

We knew generative AI could be game-changing, but we didn't even have the internal capacity to begin exploring it. Within the first few sessions, DoiT had us zeroed in on a real use case. They didn't just help us build the model – they helped us understand it. Within weeks, we had a working prototype that replaced 10 hours of manual effort with a system that delivered results in seconds. That kind of acceleration is rare, but it's exactly what we needed.

Niels Jorgensen, VP of Engineering, Opterrix

A consultative partnership built for agility

From the outset, DoiT approached the engagement not as a vendor, but as a strategic extension of Opterrix's team. The accelerator program – designed to bring projects to life in a structured but flexible way – provided the perfect framework. Early discovery sessions focused on understanding Opterrix's architecture, constraints, and goals in detail. DoiT didn't try to apply a one-size-fits-all model, they customized everything to Opterrix's business and platform – from the first workshop to the final deliverable.

From manual matching to machine intelligence

Previously, Opterrix engineers had to manually compare data and imagery from past hail events – a slow, inconsistent process and highly dependent on individual expertise. DoiT helped Opterrix develop a solution that utilized GenAI to analyze images of hailstones and storm metadata, identifying similar historical events based on geospatial proximity and storm patterns. Leveraging Vertex AI and multimodal embeddings, the system understands visual and contextual features, transforming storm imagery and sensor data into searchable, vectorized intelligence in seconds.

From 10 hours to 10 seconds

The AI-powered hailstorm matching module replaced a labor-intensive, 10-hour process with an automated solution that delivers results in under 10 seconds, freeing significant engineering hours and accelerating insurer response. This leap in efficiency now allows Opterrix to respond faster to weather events, giving insurers near real-time intelligence to expedite claims processing, mobilize resources and reduce losses. By offloading the architectural design, model implementation, and infrastructure optimization to DoiT, Opterrix compressed R&D cycles by 50% and increased delivery confidence.

Empowered teams and future-ready tech

Beyond technical deliverables, the project elevated Opterrix's internal capabilities. Engineers gained hands-on experience with generative AI, understood how to integrate it into production systems and learned how to maintain governance in a regulated environment. The AI module is now a cornerstone capability for Opterrix and a launchpad for further innovation. But even more importantly, the team is now equipped to extend that innovation independently. This wasn't just about shipping a model, it was about transferring the skills, mindset and infrastructure needed to embed AI across their platform.

See how DoiT helps cloud teams control spend

Explore how Cloud Intelligence™ helps teams improve visibility, governance, and unit economics across cloud environments.

More customer stories

Software Projects

Software Projects accelerates a complex IBM-to-AWS migration with DoiT

3
AWS MAP phases delivered: Assess, Mobilize, Modernize
40
Servers migrated 1:1, preserving the full four-tier topology
2→1
IBM Cloud regions consolidated into a single AWS VPC across multiple AZs
Shasta Cloud

Crystal-clear visibility into cloud spend at the workload and tenant level

Days
Time to first cost insights after install
Days
From install to powerful cost reporting
Workload & tenant
Granularity of cost visibility
Finlex

Finlex cuts cloud costs 50% and ships production AI with DoiT

Over 65%
reduction in cloud infrastructure costs from 2024 - present
40%
cost savings achieved through improved visibility and efficient AI architecture
Hippo

Turning cloud costs into team action at Hippo

Minutes
Time to integrate Attribute™ with AWS
Business unit
Level of cost accountability achieved
Island

Island gains true cost-per-customer visibility, without tagging

$5B
Company valuation
Days
Time to first insights
0
Tags required
Claroty

Claroty unlocks precise customer cost attribution with Attribute™

1,000+
Customers protected worldwide
Days
Time to first granular cost reports
Zero
Disruption to operations during deployment
SaaS Leader

How Customer-Level Cost Attribution Enables Value-Based AI Pricing

$1.3M
in negative-margin revenue surfaced
~360
unprofitable accounts identified
$1.3M
in aggregate losses surfaced

What they say

Software Projects

Connecting IBM and AWS privately was the piece we needed to get right, and we wanted to move faster on it than we could on our own. DoiT worked through the options with us, found the subnet overlap that was breaking the routing, and made it stable. That unblocked everything else.

DevOps Lead, Software Projects

Shasta Cloud

Attribute™'s platform is truly unique. We now have crystal-clear visibility into our cloud spend at the workload and tenant level, and that insight has already led to actionable savings and powerful insights as we further scale our service.

Paul White, VP of Engineering, Shasta Cloud

Flooid

We have worked with DoiT for many years, and there has been an increasing number of capabilities and features in DoiT Cloud Intelligence. We've embedded features such as Cloud Analytics and Reports in our own FinOps processes, it's become core to what we do.

Martin Lee, Director of Operations

Finlex

DoiT gave us the confidence to move from experimentation to production. They helped us understand the right way to build AI for the real world.

Milad Rezazadeh, CTO

Hippo

Attribute™'s cost grouping technology took our cost visibility and allocation to a whole new level. Now, our teams are fully accountable for their budgets, significantly improving our cloud efficiency and helping us minimize unnecessary costs.

Eli Zilbershtein, Head of DevOps, Hippo

Island

You can't tag a customer in a multi-tenant environment. Attribute™ finally shows us what each customer costs and what's driving those costs.

Omri Cohen, Director of Engineering, Platform

Claroty

Attribute™'s data is truly unmatched. No other solution on the market could deliver the precise customer cost and usage profiles we needed in such a complex infrastructure. Within weeks, the data from Attribute™ transformed our understanding of cost structures, influencing key strategic decisions in pricing, renegotiations, and market positioning.

Jonathan Langer, COO, Claroty

Salt Security

Attribute™ simplified tracking customer costs in our multi-tenant environments. Customer cost measurement is now clear and standardized, and finance gets the business context they need. Integration was quick and required no changes.

Kfir Lippmann, CFO, Salt Security

PropertyGuru

Attribute™ translates complex cloud bills into actionable, business-centric insights that empower our engineering teams to take true ownership of their costs.

Balamurugan Mohandossgandhi, Head of IT and Infrastructure, PropertyGuru

Accrete AI

This has let us get a better idea of what our cost of goods sold really is. It's not every day you come across something that delivers value as quickly as yours did for us. I was seeing useful insights inside the POC, and we had only deployed it to a couple of real clusters.

Jason Moore, Principal DevOps Engineer, Accrete AI

Akamai

Eliminating the need to tag thousands of resources has freed up my team and we've invested our efforts in enhancing our platform significantly.

Ziv Sivan, VP of Engineering

OneFootball

PerfectScale by DoiT has become an important part of how we optimize Kubernetes at scale at OneFootball. It gives our platform team the visibility, automation, resiliency insights, and confidence we need to balance cost efficiency with production readiness, especially as we prepare for major global football moments like the 2026 FIFA World Cup.

Andrea Benfatto, Platform/Cloud Runtime Engineering Manager

Raptive

Cloudflow's new RDS End of Life alerts have allowed us to be more proactive on keeping our database instances up-to-date. The new solution gives us internal visibility ahead of time so that we can prepare for upgrades, instead of having to upgrade under pressure while incurring extended support costs.

Jon Fairbanks, Site Reliability Engineering Manager

Your cloud bill shouldn't be a mystery

Let us show you what ships this week.