Why agent-first?
Impulse ushers in agent-first engineering — a fundamental inversion of the product development paradigm. AI stops being a command-by-command modeling helper — the copilot era — and becomes an autonomous agent that manages entire multi-step builds: scoping the product, planning the assembly, authoring every part, running physics checks, and committing verified geometry, with minimal human supervision.
Engineers no longer spend their time driving feature trees, sketching constraints, or debugging mates. They act as engineering directors over the agent — defining problem constraints, functional requirements, and design intent. The system compiles intent into manufacturable geometry.
A product is realized part-by-part in parallel goal loops. Each part lands as a reviewable, verified commit — the human reviews outcomes at the boundaries, not keystrokes in the middle.
Delivery is a working, manufacturable product — DFM-checked, STEP-exportable — not a pile of files. The agent may author and discard dozens of candidate constructions to get there; the capability is the asset, not the clicks.
Multi-week design revisions collapse into goal-oriented tasks executed in minutes, with human checkpoints at verified commits.
Because agent velocity is high, loose requirements become precise, structured contracts: fits, clearances, load expectations, process limits. An agent without rigid constraints accumulates physical debt— parts that don't fit, discovered at tooling, where the fix costs 100× and the launch window doesn't wait. Impulse's constraints are enforced at commit time, so the debt cannot accumulate.
Human design review cannot keep up with agent-speed authoring. Every change is measured against everything it touches — real solvers, invoked mid-reasoning — and everything downstream re-verifies automatically. Testing is continuous and built into the runtime, never a bottleneck the team has to script.
Thirty years of CAD interface exists to accommodate human reading and clicking speeds. In agent-first engineering the agent drives the B-Rep kernel and the solver bench directly through APIs — the reasoning loop talks to geometry, not to menus.
A single design intent triggers dozens of kernel constructions, solver runs, and re-derivations inside a sandboxed realization loop. Only verified geometry ever surfaces. The economics are metered compute, priced against the work.
| Dimension | Traditional product development | Agent-first engineering |
|---|---|---|
| Primary human output | Driving CAD feature trees line-by-line | Structuring intent and reviewing verified builds |
| Development cycle | Serialized stage gates, weeks per revision | Asynchronous goal loops, checkpoints at commits |
| Testing paradigm | Human design review and prototype rounds | Continuous measured verification with refusal |
| Application interface | GUIs built for human hands | A kernel and solver bench driven by reasoning loops |
Agent-first engineering hasn't eliminated human engineering intelligence — it has raised it. System architecture, design judgment, and domain expertise remain human-owned.
What changed is who underwrites correctness: the human used to be the verifier of every move; now verification is mechanical, and the human spends their intelligence where it compounds.
An agent that designs whole products as real manufacturable CAD — and proves every change against physics before it commits.