IN Brief:
- Emerson is extending NI Nigel AI into a broader test automation platform.
- Planned enhancements include prompt-based code generation and context-aware support across NI software.
- The update targets aerospace, semiconductor, transportation, and other mission-critical test environments.
Emerson is expanding NI Nigel AI across its test software portfolio, adding prompt-based code generation in the NI LabVIEW+ Suite and extending AI-assisted workflows across the wider NI platform.
The enhancements are expected later in 2026 and will extend NI Nigel AI across NI FlexLogger, NI InstrumentStudio, NI TestStand, and NI SystemLink. The aim is to support test development, validation, deployment, troubleshooting, and reuse across engineering teams.
Nigel AI has been developed for test and measurement environments, where software assistance has to work within measurement workflows rather than sit outside them. The system is intended for sectors including aerospace, semiconductors, transportation, and other high-reliability engineering environments.
Within LabVIEW+, prompt-based code generation will support test application development, while the wider platform integration will connect AI assistance with measurement data, hardware configuration, test sequencing, system deployment, and lifecycle management.
Emerson’s internal use has reduced some test development and troubleshooting tasks from days or hours to minutes. The company is now extending that approach into workflows used by engineering teams building and maintaining complex validation systems.
The NI platform combines modular hardware, open software, and data-management tools across the test lifecycle. Its hardware layer supports precise timing, diverse signal types, high-performance data movement, and compact system design, while the software and data layers support system configuration, automation, analytics, collaboration, and reuse.
Test engineering has become a constraint across a growing number of electronics programmes. Semiconductor devices integrate more functions, embedded systems combine compute, sensing, connectivity, and safety features, and transport and aerospace platforms require deeper validation records before release. The test system is often expected to scale with product complexity while remaining maintainable across product generations.
AI-assisted test development could reduce repetitive engineering work, but measurement environments place hard limits on casual automation. Instrument state, timing, calibration, routing, traceability, data provenance, and pass/fail logic all form part of the engineering record. Suggested code or automated guidance has to preserve those relationships rather than simply accelerate the production of scripts.
The more durable value is likely to come from reuse and troubleshooting as much as initial code generation. Test teams frequently inherit legacy systems, adapt existing sequences, move platforms between laboratories and production sites, and diagnose failures across mixed hardware and software stacks. Context-aware assistance can help engineers navigate those layers faster, provided the resulting workflows remain transparent and auditable.
NI Connect 2026 also highlighted applications including rocket development, ADAS validation, sustainable connectivity, and clean energy systems. Those markets are adding measurement channels, data volumes, and validation scenarios faster than many teams can expand. Bringing AI assistance into established test environments gives engineers a way to reduce routine development load while keeping control of the validation process.
