// Menu
SYSTEM ONLINE·GERBERGPT v4.7·MODELS LOADED: 12·LAT 47.6062° N·LON 122.3321° W·——
[01]//HOMEPAGE · REV 4.7EN-US

Physics-drivenAI for electronics/ design.

Trained on the world's largest electronics corpus — not the world's largest chat corpus.

[ ENTER[ VIEW SPECS// free tier · 100 lookups/day
[01]
1,700,000+
Finetuned Components
[02]
20,000,000+
Vectorized Parameters
[03]
5,000+
Data-Driven Footprints
[04]
99.99%
Lookup Accuracy
[02]//MODEL CAPABILITIES · INFERENCE ENGINEARCH v4.7

Not a chatbot.
An inference engine for hardware.

GerberGPT is a transformer pretrained on real electronics — parts, packages, schematics, and pad stacks — then fine-tuned to reason about circuits the way an engineer does. It doesn't retrieve text; it designs.

[01]reasoning

Schematic Inference

Reads a partial schematic and infers the missing nets, bypass strategy, and connectivity — completing intent in seconds instead of hours.

[02]parametric

Component Replacement

Swaps any part for a pin- and parameter-compatible alternate, reasoning over fine-tuned parameters to keep the circuit electrically valid.

[03]generative

PCB Feature Design

Generates board features — planes, decoupling, length-matched buses — from intent, opening design spaces human iteration rarely reaches.

[04]vectorized

Footprint Generation

Produces accurate landing patterns and courtyards straight from datasheet geometry, vectorized so placement and DRC stay consistent.

[05]inference

Layout Tracing & Routing

Infers trace topology from the netlist while respecting impedance, clearance, and manufacturability — routing as a learned behavior, not a solver hack.

[06]always-on

Continuous Pretraining

Pretrained on a corpus that grows daily, the model learns new parts and packages as the industry ships them — never frozen at a cutoff.

[03]//INDEXED REALITY · MODEL CORPUSREV 4.7 / 2026-Q2

The largest dedicated electronics knowledge base ever assembled.

Chat models know a little about everything. GerberGPT knows everything about one thing — electronics. Parts, packages, parameters, pad stacks. Indexed, vectorized, and continuously updated.

[01]
1,700,000+
Finetuned Components
// vs. ~12k in GPT-5 reasoning context
[02]
20,000,000+
Vectorized Parameters
// 768-dim embeddings · cosine search
[03]
5,000+
Data-Driven Footprints
// AI-traceable pad geometry library
[04]
847/wk
Schematics Indexed
// updated continuously · growing fast
[04]//ACCURACY · GERBERGPT vs CHATGPT-5N=10000 / 2026-04

We measured. Twice.
Then a third time.

// 10,000 part-lookup queries across 47 datasheet families. Verified against authoritative manufacturer specs. ChatGPT-5 answered with confidence on every question; only 37.2% were correct.

GerberGPT
99.99%PASS
ChatGPT-5
37.2%FAIL
Claude 4.6
48.4%PARTIAL
// sample query log · 6 of 10,000view full report →
  • STM32F407VGT6 pinoutPASSFAIL · hallucinated PA9 as USART2
  • TPS62840 EN logic levelPASSFAIL · cites datasheet rev. 0 (obsolete)
  • 0402 0.1µF X7R replacementPASSPARTIAL · ignores derating
  • LMR16030 thermal padPASSFAIL · skips PowerPAD wiring
  • ADP1740 dropout @ 1.8VPASSFAIL · gives generic LDO range
  • BAS70-04 forward voltagePASSFAIL · confuses with 1N4148
[05]//VECTORIZED LOOKUP · 20M PARAMETERSLAT < 47ms

Find by intent,
not by part number.

Every component parameter — voltage, current, package, tolerance, dropout, ripple, ESR — is embedded into a 768-dimension vector space. Search semantically. Replace BOM items in milliseconds. Find alternates your distributor still has in stock.

  • Cosine similarity over 20,000,000+ parameter vectors
  • Natural language — engineering English in, parts out
  • Distributor stock & lifecycle joined at query time
  • Sub-50ms p95 latency, deterministic ranking
gerbergpt://search
● secure
search
── embedding query · 47ms · ranking ────────────────

// demo · live query latency p50 = 31ms · p99 = 78ms

[06]//DATA-DRIVEN FOOTPRINTS · LIBRARY5000+ INDEXED

One revolution at the gate:
every pad knows
its physics.

Pad shape, paste mask, courtyard, thermal relief, current-handling, assembly process — each footprint carries the data the AI needs to place, route, and verify it. This is what makes AI PCB layout tracing actually work.

[01]1.27 mm
SOIC-8
[02]0.50 mm
QFN-32
[03]0.80 mm
BGA-256
[04]imperial
0402
[05]0.50 mm
TQFP-100
[06]0.95 mm
SOT-23-5
[07]0.50 mm
QFN-48
[08]imperial
0603
[09]1.27 mm
DFN-8
[10]1.00 mm
LGA-36
[11]0.50 mm
LQFP-144
[12]0.50 mm
QFN-20
+4,988 more footprint families  ·  updated weekly
[ browse library → ]
[ READY ]//BUILD ON THE ELECTRONICS-NATIVE MODELEOF

Stop prompting.
Start engineering /

The schematic library grows every hour. Your next part, footprint, and replacement is already indexed — waiting in the corpus.

// what you get
  • Schematic inference
  • Instant component replacement
  • Generative footprint & layout
  • A model that learns daily