Skip to main content

AI Requirements Generation (ReqGen)

What it does​

Given a hierarchy node and a short natural-language prompt, ReqGen produces a structured set of requirements aligned to V-model level (system, work-package, subsystem, assembly, subassembly), grouped into ~30 categories (functional, safety, EMC, thermal, security, etc.).

Why it matters​

A typical engineer spends 8–12 hours producing the first-pass requirements set for a new subsystem. ReqGen does it in 90 seconds, with category coverage that exceeds what most engineers produce manually.

How it works​

  1. Pick a hierarchy node (e.g., Battery Management Subsystem under EV Powertrain).
  2. Type a short prompt: "Lithium-ion BMS for 400V automotive pack, ASIL-D."
  3. Choose categories (defaults are level-aware) and generation depth.
  4. ReqGen calls the LLM with a level- and category-composed template, returns a structured JSON document.
  5. Engineers review, comment, and iterate — every change tracked.

Key capabilities​

  • Per-category granularity: 30+ category modules including ASIL-driven safety, EMC, biocompatibility, sterilization (medical), automotive EMC.
  • Hierarchy-aware: Inherited context from parent nodes flows in automatically.
  • Re-generation with diff: Edit prompt → regenerate → see colored diff vs. previous draft.
  • Review-first workflow: Submit for review, route to assigned reviewers, accept/reject per comment.

Limits​

  • Free tier: 5 generations/month.
  • Pro tier: 100 generations/month.
  • Enterprise tier: unlimited + private model deployment.