Mission Brief: REGENT

• Founded: 2020

• Headquarters: North Kingstown, Rhode Island

• Mission: Fast, safe coastal transit aboard electric Seaglider vessels.

• Core Technology: Commercial Seaglider, high-speed hydrofoiling wing-in-ground effect (WIG) craft that operate over the water within a wingspan of the surface.

• Focus: Transform prototype vehicles into safe, routine flight operations on open water.

The challenge: Real-time control & rapid data review

REGENT is building a first-of-its-kind vehicle, and preparing for their first flight. Their team is laser-focused on developing their innovative technology as fast as possible with safety built into every moment.

To achieve these ambitious goals, REGENT needs their data architecture to serve two distinct, critical needs: real-time decision-making and in-depth data review.

1. Live go / no-go Calls: Every phase demands near-zero latency signals from Seaglider to engineering operators. As a crewed vehicle still in development, accurate safety-monitoring is a non-negotiable. REGENT engineers needed a continuous, cohesive view of their craft’s health as they executed their tests.

2. Comprehensive data review: For REGENT, every data point and piece of context is critical. As a new kind of vehicle, REGENT is setting new criteria for ‘nominal’ system performance with every test. They needed a solution that gave a clear picture of what happened, why, and how it compares to historical data.

For most companies, executing against these challenges means building a real-time telemetry stack in-house and performing disjointed, local analysis separately. This requires months of high-risk development, delayed timelines, and ongoing management that diverts critical engineering focus.

Instead, REGENT chose Nominal.

“Our test infrastructure was absolutely critical for us. We needed data we could trust, every time, in real-time to test, review, and iterate at the pace we needed.”
— Ted Lester, VP of Certification

Nominal in Action

Nominal Core served both of REGENT’s needs with data architecture tailor-made for mission-critical hardware testing. Core provided low-latency streaming, cloud-native data review, and automatic comparisons with historical data.

1. Live telemetry for live go / no-go calls

Nominal streamed sub-300 ms latency telemetry directly to REGENT support boats and the control room. REGENT engineers had a continuous view of craft performance with customized dashboards and data charts.

To work within network bandwidth constraints and minimize latency, Core selectively streamed in safety-critical channels. Nominal’s computation engine used the REGENT team’s pre-built thresholds to automatically identify anomalies and monitor system health. If any critical channel hit an unsafe range, every REGENT engineer would know in under a second.

2. Comprehensive data review

After the test, REGENT’s team batch-uploads full-rate data from their thousands of onboard sensors and data channels. The data is also synchronized in Nominal with video and audio from the tests to provide additional information and context.

Getting answers requires more than just plotting. Nominal Core’s cloud-based architecture enables easy comparisons to historical data so REGENT’s engineers have every prior test right at their fingertips. Component acceptance tests, float tests, system checks: all indexed, retrievable, and queryable.

Nominal then identifies readings as in-family or out-of-family to inform decisions. No manually rummaging through CSVs, no eye-balling old Jupyter plots. Just clear, relevant context – so the team can proceed with confidence.

Results

• Zero internal tooling distraction: By skipping internal tooling, REGENT saved months of delays and full-time software engineers, but still had access to tool support and feature development from Nominal to support needed testing

• Safe, successful foil testing: Delayed, eye-balled monitoring transformed into real-time, automated safety checks. REGENT achieved “safe by design” at every phase.

• Accelerated test cadence: Multi-day test review compressed into just minutes. Engineers were ready to brief test findings the same day as testing.

Looking ahead

REGENT’s upcoming flight tests will seamlessly integrate altitude, airspeed, and wing load data into Nominal’s existing infrastructure, requiring no new tooling. As REGENT begins producing additional vehicles, the plan would be for Nominal to support end-of-line tests and vehicle certification, using historical test data as benchmarks.

REGENT leverages Nominal’s data backbone to help keep Seaglider vessels on a safe, repeatable trajectory – turning every test into a stepping stone for the next.

Mission Brief

• Founded: 2017

• Headquarters: Costa Mesa, CA

• Mission: Build and deploy autonomous systems that give U.S. and allied forces a decisive advantage.

• Operational Focus: High-tempo test & evaluation, rapid autonomy iteration, and safe scale-up from prototypes to production fleets.

The Challenge: When Testing Outpaces Analysis Infrastructure

Anduril operates on a clear premise: test volume drives capability. More tests means more learning. More learning means faster iteration. This philosophy extends across all domains: air, land, sea, and space.

But test volume creates a constraint: analysis infrastructure. The ability to manage and process test data is a limiting factor at-scale.

High-tempo testing across Anduril’s vehicle programs produces massive data volumes: high-frequency telemetry at 1-10 kHz across thousands of channels, onboard video from multiple cameras, logs capturing autonomy decisions, and operator annotations tracking failures and configurations.

Before Nominal, this data landed in dozens of different storage systems and analysis tools spanning test sites and customer operations worldwide. Each program and team had evolved their own stack for operationalizing test data. Sharing insight required manual exports, screenshots over Slack, or learning another team’s bespoke analysis workflow. Test tempo accelerated but the ability to run analysis did not.

The Solution: One Platform for All Programs

Anduril adopted Nominal as the analysis platform underpinning its test and evaluation workflows across a number of Anduril programs, a unified solution where every signal from multiple products could be captured, synchronized, and understood.

One Data Catalog

Nominal Core ingests multimodal data from every source, automatically collates and aligns it, and makes it rapidly queryable by engineers and operators of all stripes.

A test engineer at headquarters, mission operator at a remote range, and software lead at a development facility all work from the same organized catalog of Runs and Assets.

Specialists Build Templates, Teams Run Analysis

Flight test engineers build Workbook templates for post-flight analysis: motor performance, battery discharge, control loop stability, perception accuracy. Specialists define the logic once (which derivatives, which comparisons, which metrics) and save it as a template that any engineer or operator can utilize.

Analysis that required custom Python scripting for each flight (multiple hours, specialist-only) now takes any user minutes. Specialists shifted from repetitive work to investigating anomalies and developing new methodologies.

The transformation: A bottleneck once limited to a few specialists became a capability shared across entire engineering teams.

Real-Time Intelligence in Disconnected Environments

Anduril must perform operations in austere test ranges with limited connectivity and within classified environments that have no egress to the cloud. Nominal Core deploys to servers at the edge, processing high-rate data locally with sub-250ms latency. Real-time monitoring, automated anomaly detection, and electronic procedures execute live during tests. When connectivity returns, data flows back into centralized storage without manual handling, enabling mission operators at austere ranges to have the same capabilities as engineers at headquarters.

Scaling Across Vehicle Classes

As Anduril has scaled their product lines, Nominal has scaled with them. What started as a fast way to review flight logs for small UAVs became the shared workspace for engineers analyzing mission data across all domains.

• Test data flows from the field into Anduril’s data lake and is immediately available in Nominal for analysis. Anduril and Nominal engineers jointly partnered on data ETL pathways that were 40x faster than existing vendor systems.

• Discipline engineers generate charts in seconds with Workbooks and share data with a simple browser link. Version control is handled inside Nominal, preventing fragmentation of analysis scripts as users share artifacts and iterate.

• Web-based analysis largely eliminates the need to pull data locally. What once required hours of exporting and processing across multiple storage systems is now available instantly.

The same infrastructure supports different sensors and different operational contexts. A control systems insight from an aerial vehicle informs maritime autonomy development. A perception algorithm tested on ground platforms transfers to flight. Cross-domain learning becomes standard practice.

Results

• Faster test loops: From 5-6 hours to near real-time analysis

• 40× faster telemetry ingest than vendor provided ETL solutions

• Adoption at scale: 300+ active users across multiple programs

• Operational continuity: Full-function air-gapped deployments with automated backhaul for headquarters analysis, preserving full visibility throughout the mission cycle

• Mindset shift: Non-developers can self-service their test data workflows; analysts can collaborate across programs in one shared environment

The Work Continues

The mission is urgent. Threats don’t wait for perfect tools. Anduril tests aggressively, learns quickly, and ships capability at a pace that the moment demands.

Instrument everything. Understand quickly. Iterate relentlessly.

Those are the operating principles Anduril and Nominal share. High velocity testing delivers decisive advantage.

• Founded: 2024

• Headquarters: Sunnyvale, California

• Mission: Enable the largest robot army in the world through intelligent physical AI for the US military.

• Core Technology: Fury, the foundation model for defense robotics

• Operational Focus: Developing and training an embodied AI brain that allows machines to perceive the world, understand natural language, and coordinate action autonomously across any domain.

“In autonomy, iteration speed is everything. Nominal lets us compress the development cycle of data collection, training, and testing without compromising safety. It gives us the confidence to scale from tens of unmanned systems to the world’s largest multidomain autonomous defense fleet.”

— Collin Otis, CTO & Co-founder, Scout AI

The Challenge: Reviewing and Indexing Copious Amounts of Test Data

Scout AI, a fast-moving autonomy startup, operates at the cutting edge of autonomous vehicle development. Their core strength lies in continuous real-world testing and rapid iteration of software development cycles. Traditional data annotation methods often become a bottleneck, slowing down the development cycle and hindering the ability to quickly retrain autonomy software. An efficient and scalable solution to process and annotate the vast amounts of data generated during these tests directly results in faster improvements to the autonomous system.

Within Scout AI, diverse roles and responsibilities necessitate access to the same test data for distinct use cases:

• Engineers: Review drive logs and quickly triage critical issues.

• Annotators: Critique the autonomous system’s behavior based on Reinforcement Learning from Human Feedback (RLHF) workflows to be used in training.

• Operators: Update what they were thinking after the fact so the autonomous system can learn to think like them.

By rapidly moving through cycles of live testing, event annotation, and model retraining, Scout AI developed Fury, a defense-specific Vision-Language-Action (VLA) foundation model engineered to transform every defense robot into an intelligent, autonomous agent.

Scout AI’s Autonomy Edge: Vision-Language-Action Models

Unlike traditional robotics software, Fury is an embodied AI system capable of perceiving the physical world, interpreting natural language, and issuing real-time motor commands to act decisively even in comms-denied and GPS-denied environments.

Fury’s impressive capabilities and performance rely on an innovative new approach to autonomy development. VLA models are a class of multimodal foundation models that integrate computer vision and natural language to generate autonomous actions. Given an input video of the robot's surroundings and a text instruction, the VLA directly outputs instructions for the robot to execute autonomously.

VLAs are constructed by fine-tuning a vision-language model (VLM, a large language model with vision capabilities) on a large-scale dataset of labels that capture natural language instructions, time aligned with vision inputs and robot telemetry. Google DeepMind pioneered the approach in 2023 with a VLM adapted for end-to-end manipulation tasks, capable of unifying perception, reasoning and control.

A generalized architecture for vision-language-action models; Scout AI uses Nominal to rapidly capture, optimize, and manage Text Instruction annotations, time aligned with video inputs and system telemetry, within Nominal’s Events data catalog.

The Solution: Event Annotation with Nominal

Scout AI partnered with Nominal to address these challenges, leveraging Nominal's cloud platform for storing, reviewing, and adjusting their saved live audio-transcribed annotations from the field. Nominal is now the source of truth for tagging and tracking training data across all the robots, missions, and tasks. Engineers take advantage of Nominal’s performance and ease of use for rapid search and curation of training sets.

Live Event Annotation during Field Tests

Nominal's Event catalog in Workbooks proved to be a game-changer for Scout AI's team. Engineers can now easily review events recorded from a field test, automatically time-synchronized with the video and telemetry data collected from the vehicle.

Instead of manual tagging or complex UIs, operators would simply speak into a microphone using speech-to-text to transcribe the scene live around the vehicle during a test and save events that would populate in Nominal. Engineers can then go to Nominal to review each recorded audio command provided to the autonomous system to analyze performance around that instance of time.

Nominal makes it very easy for a user to search for the following example commands and indicate exactly where it occurred around the telemetry data in the chart:

• "Reverse into a K-turn”

• "Steep Terrain ahead"

• “Negative Obstacles detected to the left"

In the past few months, Nominal has allowed Scout AI to:

• Increase annotation speed: Engineers could focus on monitoring the test and simply narrate observations, eliminating the need to look away or manipulate devices.

• Capture rich context: Audio annotations provided a deeper understanding of the operator’s intent and the surrounding circumstances, which might be missed by traditional annotation methods.

• Reduce post-test workload: Majority of initial annotations were already captured in real-time during the test, reducing need to retroactively tag data manually which streamlines the review process.

• Collaborate on results: Instantly send links to team members for immediate review of interesting test events without having to re-run post-processing scripts.

Post-Test Refinement and Retraining

After the field tests, Scout AI utilized Nominal's platform to meticulously review and refine the collected data.

• Adjusting Events: Nominal’s intuitive interface allowed engineers to easily go back to specific points in the test data, more precisely adjust the alignment of start and end times of events, and add more granular details to the initial audio annotations. For example, a spoken annotation "Obstacle detected" could be refined to precisely mark the moment the obstacle appeared and disappeared, and categorize it such as "pedestrian - unexpected crossing."

• Re-training Autonomy Software: The refined and high-quality annotated data was then directly fed back into Scout AI's machine learning pipeline. This rapid feedback loop allowed Scout AI to quickly retrain their autonomy software, addressing edge cases and improving the robustness of their algorithms.

The Impact: Faster Iteration, Smarter Autonomy

By integrating Nominal into their organization’s workflows, Scout AI achieved significant improvements in their development cycle:

Everyone in the company is able to use Nominal to self-service data for a wide variety of their own use cases and quickly share workbook links around the entire organization - from vehicle utilization, to operations efficiency, to fleet management, to sensor evaluation.

Looking Ahead

Scout AI continues to leverage Nominal's data platform to push the boundaries of autonomous technology. As early adopters of Nominal in the Autonomy space, their team provides valuable insights and feedback to our product to ensure we can support crucial workflows for robotics and autonomy development.

Through this partnership, Nominal's robust software platform has proven invaluable for large-scale data management, analysis, and annotation. We are proud to support Scout AI's mission by allowing their team to dedicate more time to the demanding process of developing reliable autonomous defense systems, rather than managing infrastructure or tooling.

For more information on how Nominal can accelerate your autonomy development, please visit our site or contact us.

Mission Brief

• Founded: 2018

• Headquarters: Atlanta, Georgia

• Mission: Operationalize hypersonic flight for defense and commercial aviation.

• Core Technology: High-Mach and hypersonic aircraft. Most recent prototype: Quarterhorse Mk 1.

• Operational Focus: Rapid prototyping and iterative testing to dramatically accelerate aerospace development cycles.

“We did our first high-speed taxi and first flight within minutes of each other. That requires the ability to distribute, access, and review test data immediately. Nominal made that possible.” — AJ Piplica, CEO, Hermeus

The Challenge

Hermeus sets development timelines that haven’t been achieved since ‘the golden age of aerospace’ in the 60s, compressing typical aerospace timelines from a decade to less than a year. Their team is committed to rapid iteration & innovation to push the boundaries of what’s possible.

At the same time, achieving hypersonic flight involves extreme operational complexity – intense thermal environments, rapid system dynamics, and precise real-time data handling from multiple sources.

Hermeus engineers faced:

• High-stakes safety & performance checks in extreme conditions.

• Complex data integration and organization, involving simultaneous streaming from software-in-the-loop (SIL), hardware-in-the-loop (HIL), and static file sources – with multiple file formats and changing configurations.

• Complicated system and component testing across disparate test sites with disaggregated engineering teams, including government sites with limited connectivity

Hermeus needed well-organized, easy access to data, regardless of the engineering team, test site, or subsystem. Without it, their ambitious timelines would be impossible.

Unfortunately, legacy aerospace tools choke at scale. They’re local-only, manual, and blind to historical context. For Hermeus, the choice was stark: limp forward with tools built for the Cold War, or spend millions on custom software – delaying missions by years.

That’s where Nominal stepped in.

The Solution: Continuous test, powered by Nominal

Nominal embedded itself in every testing workflow across Hermeus’ development progress. From avionics and flight software simulations to materials testing to engine tests to the first flight, Nominal provides the confidence & performance that engineers need to achieve record-breaking timelines.

Nominal Connect for ingest and control

Testing across engineering disciplines required ingest of multiple data formats – PCAPs from full-scale engine test stands, ch10 streams with variable TMATs from flight software simulations and onboard flight computers, live video.

Nominal enabled 80% reduction in time from ‘upload-start’ to ‘eyes-on-data.’ GUI and headless Connect pipelines abstracted away the difficulties of different data formats – automatically encoding and time-stamping data so that engineers could focus on analysis.

Robust, direct hardware control interfaces in Connect allowed engineers to set their test conditions, see live data on the edge, and stream to Nominal Core for engineers offsite.

Nominal helped engineers minimize time from test to build, accelerating cycles and timelines.

Nominal Core for validation and alerting

At the High Enthalpy Air-breathing Test (HEAT) facility outside Jacksonville, FL, the propulsion team configured automatic validation checklists to apply to each new test event. Engineers were immediately alerted of any anomalous trends or out-of-specification conditions. Using Nominal Core, Propulsion engineers in Atlanta could collaborate with test engineers at HEAT in real time to dive deeper into issues and resolve them faster.

Meanwhile, the flight software team used Nominal’s validation checks nearly every day. They were able to stream simulation data to Nominal to test the performance of their new builds, leading to near-instant feedback and quick turn modifications to the flight software.

Integrated test operations from Edwards AFB

First flight is a massively complex event. The whole company rallied to watch results come in through Nominal.

The flight test team ran operations at Edwards AFB, streaming data from both the aircraft and ground control station to Nominal Core. Nominal enabled engineers from Hermeus’ Los Angeles, Atlanta, and Jacksonville sites to watch their relevant telemetry channels during the flight.

Engineers of every discipline had access to real-time data. Each streamed data into their customized views in Nominal Core – monitoring and commenting on their subsystems throughout the duration of the test.

As their first flight progressed, every engineer at Hermeus understood what was happening and why. As if the entire team had custom dashboards right on the flight deck.

The Results

With Nominal, Hermeus:

• Designed & built the Quarterhorse Mk 1 in 7 months

• Closed the loop between test and validation for rapid iteration of hardware and software builds

• Democratized access to real-time telemetry and automated alerting – across teams, locations, and systems.

Powered by continuous test and iteration, Hermeus set a new standard for the pace of aerospace innovation.

Looking Ahead

Hermeus is already developing the Mk 2 – targeting flight within a year. They are re-configuring their manufacturing to be wholly controlled by Nominal Connect, and streaming all of their test data into Nominal Core – from the component manufacturing line to flight test. Together, Hermeus and Nominal are making the impossible routine.

“We at Hermeus feel GREAT about the data partner we picked. Nominal’s team worked like ‘Hermeus’ people, made telemetry integral to how we operate, and opened our eyes to the ‘art of the possible’” — Ken Venner, COO, Hermeus

Each milestone compounds: faster cycles, tighter feedback loops, greater ambition. As Hermeus pushes the boundaries of what’s possible, Nominal will be there every step of the way.

Engine test. Taxi. Flight. Again. And again. And again

Mission Brief

Founded: 2023

Headquarters: Torrance, California, USA

Mission: Abundant Energy throughout the Solar System.

Core Technology: Transportable nuclear micro reactors powered by HALEU TRISO fuel – designed for autonomous operation over three years in harsh conditions.

Key Customer: Antares is providing resilient energy to the DoD, DoE, and NASA ahead of pursuing critical commercial markets in mining, manufacturing, data centers, and remote grids.

Operational Focus: Antares targets sites where no other power solutions can provide the necessary capabilities and energy density, including military installations and space missions.

“Reliable, resilient energy is the backbone of national security. Without it, there is no mission assurance.”

— Jordan Bramble, CEO

The Challenge: Moderator Thermal Performance

“Our materials have to operate in some of the most extreme environments imaginable. The ability to swiftly and accurately test our lab-scale demonstration builds has been critical to evaluating new hardware and iterating designs at our rapid pace. We needed a continuous approach that captured every reading – no matter how fast or remote.”

— Kelsy Green, Senior Engineer

Antares’ micro-reactors rely on complex thermal management systems to transfer heat to the power conversion system – conducting through the core to the graphite moderator under neutron impingement and irradiation. Thermal energy is then transported into a phase-changing fluid in the heat pipe to the primary heat exchanger, where a working fluid absorbs the heat ahead of later expansion in the cycle’s turbomachinery. The test setup is instrumented with flow meters, thermocouples, and pressure transducers to capture multiple signals in real time, characterizing the system’s performance. Antares needed a continuous testing and data acquisition approach that could:

• Stream multiple types of data at extremely high resolution

• Calculate performance metrics based on live data

• Aggregate and analyze run data across R&D and eventual full-scale manufacturing.

• Operate both in lab settings and remote, sealed environments where local control is key.

Their answer: Nominal Connect

Nominal in Action

Real-Time Monitoring & Edge Automation

Thermocouples feed controllers to make sure temperatures and power rates are within safe margins. If signals drift, Nominal Connect flags the deviation and can trigger an automatic abort, cooldown, or reconfiguration. Operators can watch every wave, but the system executes with or without on-site staff.

Unified Storage & Compute

All timestamps and measurements flow into Nominal’s data warehouse. In-house software can tap this data in real time – no more rummaging through scattered logs. R&D and production lines share the same source of truth, with consistent tags and versioning on every test.

Analytics & Operations at Scale

Antares teams across multiple states collaborate while overlaying current waveforms on historical runs, spotting microtrends or repeat anomalies. As designs move from R&D to manufacturing certification, the same test approach follows. Predictive checks and automated defect detection unify the entire workflow – synchronizing data from test cells, final acceptance, and operational monitoring.

Wins

Immediate Feedback. Constant checks catch thermal anomalies before they threaten safety or performance.

Shared Data, No Bottlenecks. Engineers see the same data at the same time, creating a live feedback loop from design to production.

Faster Iteration & Certification. Moderators move through tests more often with fewer manual steps—scaling capacity in lockstep with reactor manufacturing.

“Nominal has been a game changer for sharing data in our testing. It allows for live streaming and almost instantaneous sharing between us and our partners across the country. The ability to share real time transformations of sensor data enables us to keep our design team connected and moving rapidly.”

— Tyler Dennis, Test Engineer

Propelling Toward Sustainable Power

Antares is preparing for a future of resilient power in any setting – on Earth or beyond. With Nominal’s edge automation, storage, and analytics layers, they unify real-time testing, long-term data retention, and remote autonomy in a single loop. From the first sensor readout to final operational oversight, Antares now tests continuously on every reactor they build.

All Reactors Nominal.

Rapid field testing accelerates Vatn’s transition to mass manufacturing

Vatn develops autonomous underwater vehicles (AUVs) designed for intensive maritime operations. With unmatched access to testing waters, Vatn rapidly transitioned from prototype to ready for large-scale manufacturing, powered by Nominal’s automated testing pipeline.

Mission Brief: Vatn

Founded: 2023
Headquarters: Portsmouth, RI
Mission: Deliver affordable, mass-produced autonomous underwater vehicles (AUVs) to expand naval capability, scale maritime operations, and counter adversary threats in contested environments.
Core Technology [Defense]:
The Skelmir S6 – an expendable, modular autonomous underwater effector designed specifically for high-volume naval and special operations missions. The platform is rapidly manufacturable and supports diverse payloads (kinetic, electromagnetic, cyber, sensor) without requiring complex vessel integrations.
Operational Focus:
Vatn enables mass deployment of autonomous underwater systems to overwhelm adversary defenses, mitigate operational risk, and significantly expand mission capabilities. Deployed en masse from air, surface, subsurface, or shore, Vatn’s systems offer covert insertion and precision placement through GPS-denied navigation, advanced current and tide modeling, and tactical integration (ATAK compatible).

“We’re testing and iterating faster than anyone today – ready to deliver capability, not promises. Nominal lets us out-test the competition, validate assets, and confidently ramp production.”

– Nelson Mills, CEO

The Challenge: Scaling from Prototype to Fleet Operations

• Rapid Daily Testing: Vatn submersibles test nearly every day, in all weather, generating vast quantities of critical data.

• Manual Bottlenecks: Legacy spreadsheet analysis and manual merges slowed iteration, limiting test volume and scaling readiness.

• Readiness for Production: Vatn required streamlined, automated acceptance testing to quickly transition from daily field tests to full-scale production, demonstrating clear capability to prospective customers.

Vatn’s success hinged on automating data collection and eliminating internal tooling hurdles to confidently deliver production-level capabilities at a high cadence.

Nominal in Action

1. From Surfacing to Validation in Under 5 Minutes

When each AUV exits the water, Vatn’s automated pipeline is triggered, immediately uploading mission data into Nominal’s central warehouse. Engineers get test results compared to pass/fail criteria within 5 minutes – enabling multiple rapid test cycles each day.

“We’re no longer wasting test time with manual spreadsheet reconciliation. Automated reports are the way. Now we stay focused on hardware, not screens.”

– Josh Allder, Maritime Test Engineer

2. Checklists Replace Manual Reviews

Vatn uses Nominal’s automated checklist system to validate acceptance tests without manual intervention:

• Depth Mode Checks: Automated verification of subsurface navigation systems.

• Speed Runs: Instant propulsion data analysis across surface, depth, and altitude conditions.

• INS Navigation Validation: No manual wrangling – immediate analysis of navigation test data.

Automated checklists mean engineers spend less time parsing data, more time advancing hardware and scaling operations.

3. Fleet-Wide Test Visibility, Repeatable Results

Nominal indexes every test by mission parameters, weather, and fleet units – providing instant visibility into test trends across multiple vehicles. Deviations or anomalies trigger structured, collaborative investigations within Nominal Workbooks, eliminating scattered data across spreadsheets.

4. Preparing for Scale: Edge Analytics at Sea

Vatn currently uploads data after surfacing, but soon they’ll deploy Nominal Connect directly aboard chase vessels and test platforms. Edge analytics and real-time, automated acceptance tests will further increase daily test volume – squeezing additional outcomes every day on the water.

Concrete Results: Ready for Mass Manufacturing

Before Nominal

• Hours to actionable test results

• Manual data merges across spreadsheets

• Single daily test

After Nominal

• Under 5 minutes to validation

• Fully automated pass/fail checklists

• Dozens of test cycles daily

Why It Matters: Vatn is sprinting towards being a maritime market maker

Nominal identifies and partners early with startups like Vatn, betting on teams poised to become industry leaders within five years. Vatn’s accelerated testing and readiness for scaled production is proof:

• Daily iterative advantage: Testing frequency is second-to-none, creating a clear market edge.

• QA for mass production: Every AUV meets stringent field readiness criteria, validated automatically by Nominal’s pipeline.

Vatn punches way above their weight, running more tests per engineer than nearly any team we've seen. Their rapid daily iteration shows how fast you can move when you commit fully to continuous test across the stack – from system architecture through operational tools.

– Cameron McCord, CEO, Nominal

Vatn is ready to deliver capability today – at scale.

Mission Brief

Founded: 2015
Headquarters: San Diego, California
Offices: Dallas, Washington DC, and International Hubs
Mission: Shield AI’s mission is to protect service members and civilians with intelligent systems.
Core Technology: Shield AI’s flagship product, Hivemind, is an artificial intelligence pilot that has flown multiple platforms, including the F-16 fighter jet, the V-BAT vertical takeoff and landing drone, MQ-20 aircraft, and the MQM-178 Firejet.
Key Customers: U.S. Department of Defense and Allied Forces
Operational Focus: Shield AI’s systems are designed for contested environments; enabling autonomous systems to perform ISR (Intelligence, Surveillance, Reconnaissance), tracking, and targeting in dynamic, high-stakes missions.

“Delivering V-BATs at scale requires eliminating any bottlenecks from test, validation, and delivery. Nominal helps us move from raw vehicle data to high confidence decisions, without losing time.”
— Brandon Tseng, Co-Founder, President

The Challenge

“Speed of iteration is what matters in fielding new capability. The pace of testing - reviewing data and making decisions - defines everything else we can do. We had to solve this. Nominal has helped us deliver on both speed and validation.”
— Armor Harris, SVP Aircraft

Shield AI operates in a world where test cycle times determine the speed at which they can deliver intelligent, affordable mass to the warfighter. V-BATs, powered by Hivemind, must be able to operate autonomously in communications- and GPS-denied and degraded environments such as Ukraine and the Indopacific. Such missions often rely on a fast feedback loop to test and perfect flight data in order to get back into the fight. The faster Shield AI is able to iterate on this loop, the faster V-BAT can contribute to the mission.

To meet these mission goals, Shield engineers have to:

• Capture and manage the increasing volume of test data without losing track of critical details.

• Eliminate delays between testing and analysis by removing unnecessary steps.

• Develop data infrastructure and tools that work in low-connectivity environments where traditional tools fail.

Without these capabilities, engineering teams face wasted time, missed opportunities, and stalled progress – which can, sometimes, mean the difference between enabling a mission, sitting this one out, or even crashing.

The Solution: Real-Time V-BAT Flight Testing

Analysis Velocity

Nominal enables Shield AI to review V-BAT test data before engines cool. Data flows directly from the drone into Nominal’s platform, removing the need for engineers to stitch together files manually. Engineers can optimize their minutes-on-mission by generating live plots comparing multiple flights, annotating findings, and diagnosing root causes of issues in minutes – not hours.

Low-Connectivity Field Support

Nominal + Shield AI’s elite engineering teams co-built field tools for limited connectivity, ensuring Shield AI’s teams can capture, store, and analyze data wherever V-BAT’s missions take place – whether in the Gulf of Mexico interdicting drugrunners or in Ukraine searching for missile silos. This capability has proven essential for V-BAT testing both at home in the Dallas, TX manufacturing facility or in remote or contested areas.

Data Catalog for Future Missions

V-BAT testing generates massive amounts of telemetry, video, and environmental data across simulations, HITL tests, and field operations. Nominal’s data infrastructure indexes and synchronizes every frame, providing Shield AI with a durable system for current and future platforms.

The Results

Shield AI’s engineers use Nominal to:

• Reduce delays between tests and decisions.

• Manage and process large volumes of data without adding complexity.

• Test and analyze systems in field conditions that demand reliability.

“Within 5-10 minutes of data being uploaded to Nominal, we were able to eliminate and hone in on potential reasons for a flight issue because multiple teams reviewed their specific data. Typically, it would have taken days for a team to do a deep dive review with their own MATLAB scripts to determine what went wrong. Nominal is already 1 to 2 orders of magnitude better than previous processes.” — Austin Howard, Engineering Fellow

This allows Shield AI to deliver resilient, mission critical systems at full throttle.

Looking Ahead

Testing isn’t just part of the process—it’s the engine that drives progress. Shield AI and Nominal continue to deepen their partnership, ensuring the tools evolve as quickly as the mission requires.