# Analyst, the AI agent for hardware engineering > Ask questions about your hardware data, build editable analyses, and turn test plans into pass/fail checks with Nominal Analyst. Source: https://nominal.io/platform/analyst Introducing Nominal Analyst # The AI agent for people building hardware Nominal Analyst is an AI agent for engineers building hardware in Nominal. It helps teams ask questions about their data, build editable analyses, and turn test plans into pass/fail checks, with sources and calculations engineers can review. [Try Nominal](https://nominal.io/demo.md?from=%2Fplatform%2Fanalyst&cta=analyst-hero)[Read the blog](https://nominal.io/blog/analyst.md) Asked why the primary battery died during hover run H-18, Analyst reads the pack voltage, the NBP-9640 datasheet, the rig’s CAD assembly, stand camera 2 and the run log. It finds that the run started at 41 % charge against the procedure’s 90 %, and that pump P-2 starting at 41.28 seconds pulled the pack to 264.9 V, under its 268.8 V cut-off, and saves the analysis as a workbook. Analyst in practice ## Follow one investigation A battery pack fails a thermal requirement. Analyst works from the requirement to the sensors and leaves an analysis the team can keep. 1. 01 · Understand ### Start with the question that matters Ask about a result. Analyst brings together the requirement, measurements, and evidence behind it. AnalystBP-17 thermal investigation This battery pack failed its latest test. Which requirement failed, and when? The temperature-spread check failed. Spread exceeded the 8 °C limit for 102 consecutive seconds during sustained load. The requirement allows less than 10 seconds above that limit. Battery pack BP-17Run BP17-054 Requirement THERM-04 Limit 8.0 °C Result Fail 2. 02 · Check ### Check results against the test plan Analyst reads the requirement in your test plan, stored in Nominal. It turns the limit into a pass/fail check, runs it, and links the result to its source. AnalystBP-17 thermal investigation Does this meet the temperature-spread requirement? Temperature spreadBP17-051 to BP17-054 · aligned to load start°C - BP17-054 - BP17-053 - BP17-052 - BP17-051 No. BP17-054 fails THERM-04. During the evaluated sustained-load interval, spread exceeded 8 °C for 102 consecutive seconds. The test plan prohibits 10 consecutive seconds or longer above that limit. Battery pack BP-17Run BP17-054 Above limit 102 s Allowed < 10 s THERM-04 Fail 3. 03 · Locate ### Follow the result to the measurements Move from an overall result to the signals and physical locations worth examining. AnalystBP-17 thermal investigation Which measurements account for the larger spread? At 150 seconds after load start, T04 measured 56.4 °C and T01 measured 44.0 °C. These were the hottest and coolest measured locations, giving a spread of 12.4 °C. Battery pack BP-17Run BP17-054 Hottest · T04 56.4 °C Coolest · T01 44.0 °C Peak spread 12.4 °C 4. 04 · Investigate ### Bring context into the investigation Compare the recorded conditions and identify what additional evidence would help explain the result. AnalystBP-17 thermal investigation Could different cooling conditions explain this? The recorded coolant-flow and inlet-temperature settings match the previous tests. That doesn’t establish whether cooling behaved the same during the run. This dataset has no coolant-flow trace to evaluate that explanation. Battery pack BP-17Run BP17-054 Coolant flow setting Matches Inlet temperature Matches Coolant flow trace Missing 5. 05 · Act ### Leave with a clearer next step Keep the findings, supporting analysis, and open questions together so your team can continue the investigation. AnalystBP-17 thermal investigation Summarize what we know and what we should investigate next. The spread exceeded the requirement and was larger than in the three comparison tests. T04 and T01 define the peak difference; the cause remains unresolved. BP-17 thermal investigationWorkbook · 4 panels Battery pack BP-17Run BP17-054 Runs compared 4 Sensors 6 Cause Open In the hands of engineers ## More time for the work that moves hardware forward - > “I've saved hours and hours by using Analyst. It's been a huge improvement to our iteration speed.” ![Wisk Aero](https://nominal.io/images/analyst/wisk-logo.svg?dpl=dpl_7hfEP3mnKVq6qPcxhUxneDwnxz6G)Cooper DiamondStaff Systems Engineer - > “As a new employee it made it very easy to navigate the large dataset and understand which variables were most useful for analyzing certain situations and root causing issues.” ![Mach Industries](https://nominal.io/images/analyst/mach-logo.svg?dpl=dpl_7hfEP3mnKVq6qPcxhUxneDwnxz6G)Spencer SharpeFlight Test Engineering Intern Saved analysis ## Keep the evidence and continue the investigation Analyst saves its work as a workbook you can open and edit. Add the next run, and the evidence stays together for your team. Capabilities ## What can Analyst do? Find the right data, read the documents, CAD, and video behind it, build an analysis, and check results against your requirements. - ### Build and edit analyses Create and update Nominal workbooks with plots, derived signals, tables, and layouts. - ### Turn test plans into automations Read specs and test plans in Nominal, define pass/fail checks with thresholds, run them against your data, and review violations. - ### Compare runs and calculate signals Overlay runs, apply filters and derivatives, and run frequency analysis such as FFT, PSD, and Bode plots. - ### Write custom analysis code Calculate statistics across runs, explore trends across months of hardware data, and create visualizations for questions that need more context. - ### Read more than telemetry Read the specs, datasheets, test plans, CAD models, and test video your team keeps in Nominal, and cite the page, part, or frame behind each finding. - ### Find the right data Locate runs, hardware, signals, and existing analyses in your Nominal workspace. ## Frequently asked questions What is Nominal Analyst? Nominal Analyst is an AI agent for engineers building hardware in Nominal. It helps teams ask questions about their data, build editable analyses, and turn test plans into pass/fail checks, with sources and calculations engineers can review. Is Analyst ready for my team? Analyst is available today in preview for engineers building on Nominal, and engineers are already using it. What data can Analyst use? Your hardware, runs, signals, analyses, and checks in Nominal, plus the specs, datasheets, test plans, CAD models, and test video your team keeps there. What can Analyst see and change? Analyst acts with your permissions. It can only see and edit what you allow it to. Can I customize how Analyst works? Yes. Write skills that describe your team's analysis methods, review steps, or reporting conventions, and share them across your workspace so everyone's Analyst works the same way. Can I check its work? Yes. You can inspect the calculations, code, and sources behind every analysis, edit the results in Nominal, or ask Analyst to refine them. Is my data used to train models? Your data is not currently used to train models, but we do keep traces and product analytics to improve the product. How do I get access? [Request a demo](https://nominal.io/demo.md) to see Analyst with the Nominal team. Already on Nominal? Ask your account team about preview access. How is Analyst different from a general-purpose AI assistant? Analyst works directly with your data and analysis tools inside Nominal. It builds analyses your team can edit, turns test plans into pass/fail checks and runs them, and follows the playbook your team teaches it through skills. Every conclusion traces back to the data or document behind it. How is Analyst different from connecting my own AI agent to Nominal? Both work in Nominal with your permissions. Nominal's MCP server gives the agent you already use, like Claude, Codex, or Devin, access to Nominal tools, which might be the right fit when your work spans other systems. Analyst is built for engineering work inside Nominal: it creates workbooks, writes and runs checks, derives signals, and grounds its work in your team's documents and skills. Nominal Analyst ## Put Analyst to work on your data Find relevant data, build comparisons, and check results against your engineering requirements. [Try Nominal](https://nominal.io/demo.md?from=%2Fplatform%2Fanalyst&cta=analyst-cta)[Read the blog](https://nominal.io/blog/analyst.md)