Substrate
AI agents for the physical world.
Yassin Al-Yassin · Hardware-AI bilingual founder
The engineers who design the physical world — chips, circuits, embedded systems, hardware — still work in tools from the 1990s. The AI revolution skipped them entirely.
Models can see
Frontier multimodal models can finally read schematics end to end.
Budgets are urgent
Defence reshoring and supply-chain mandates created real modernisation budgets.
Engineers are ready
They want a tool that works alongside them — not a black box.
It helps engineers modernise legacy electronic circuits step by step, with the engineer checking every output. Ships inside the EDA tools they already use — Altium, KiCad, Cadence.
Read the circuit
Infers what each component is, what the sub-circuits do, and what the whole design is for. The hard part — and the primitive we built at the AMD contest.
Propose, step by step
A modernisation one verifiable step at a time — never an autonomous black box.
Engineer verifies
Every output inspectable and reversible. Trust compounds with each confirmed step.
Tracer
Verifiable modernisation copilot inside existing EDA tools.
Modernisation EDA
A purpose-built platform — the foundation other agents build on.
Substrate agents
Schematic, Embedded & beyond — for everyone designing the physical world.
Each modernisation adds proprietary design data and engineer trust the next layer inherits. Data the market can't get; trust a black box can't earn.
Second-year Electronic Engineering at Southampton, two years building and shipping AI products. Building AI for hardware needs someone who understands electronics and modern ML. Those populations barely overlap — that's the whole thesis.
Pre-seed, building the Tracer MVP, available for founder conversations.