The First RL Engine for PCB Layout

Quilter uses reinforcement learning to actively explore thousands of generated candidate boards. Quilter is never trained on human-designed boards, ensuring that every design is both secure and original.

Privacy

AI That Understands Physics. Not Your IP.

Quilter trains on physics. Our models are built entirely from synthetic data generated by simulation, not your design files, not scraped boards, and never your IP.

Network of connected nodes

01

Neural networks

Neural networks trained on physics, not imitating human designs

Separated blocks processed in isolation

02

Processed in Isolation

Every job is processed in isolation and deleted on completion.

Separate stacked layers of data

03

Data Integrity

No shared training data, no cross-contamination.

Candidate Selection

Your Best Design Rises to the Top

Quilter generates dozens or hundreds of layout candidates per job. Then it ranks them against physics and fabrication rules, raising the best design to the top. Filter by layer count, trace width, vendor rules, and more to find the candidate that best fits your strategy.

  1. 01

    Routing Completion

    Percentage of pins successfully routed
  2. 02

    Manufacturability

    DRC violations (none allowed), trace/space/drill compliance
  3. 03

    Physics Rule Checks (PRCs)

    Ground plane overlap, overheated trace length, differential length mismatch, trace width accuracy, and thermal/signal performance
  4. 04

    Fabrication Fit

    Compatibility with real fabricator stackups and constraints
  5. 05

    Resource Efficiency

    Layer count, via count, trace length, and component density
Auswahl der Kandidaten

Ihr bestes Design setzt sich an die Spitze

Quilter erzeugt Dutzende oder Hunderte von Layout-Kandidaten pro Auftrag. Anschließend werden sie anhand von Physik- und Fertigungsregeln eingestuft, sodass das beste Design an die Spitze rückt. Filtern Sie nach Lagenzahl, Leiterbahnbreite, Herstellerregeln und mehr, um den Kandidaten zu finden, der am besten zu Ihrer Strategie passt.

  1. 01

    Routing-Abschluss

    Prozentsatz der erfolgreich gerouteten Pins
  2. 02

    Fertigbarkeit

    DRC-Verletzungen (keine erlaubt), Einhaltung von Leiterbahn-/Abstands-/Bohrvorgaben
  3. 03

    Physik-Regelprüfungen (PRCs)

    Überlappung der Masseflache, überhitzte Leiterbahnlänge, differentielle Längenabweichung, Genauigkeit der Leiterbahnbreite sowie thermisches/Signalverhalten
  4. 04

    Fertigungskompatibilität

    Kompatibilität mit realen Fertigungs-Lagenaufbauten und -Randbedingungen
  5. 05

    Ressourceneffizienz

    Lagenzahl, Via-Anzahl, Leiterbahnlänge und Komponentendichte
候補の選定

最適な設計が自動的に浮上

Quilterはジョブごとに数十から数百のレイアウト候補を生成し、物理法則と製造ルールに基づいてランキングし、最適な設計をトップに浮上させます。レイヤー数、配線幅、製造先のルールなどでフィルタリングし、戦略に最も合う候補を見つけてください。

  1. 01

    配線完了率

    正常に配線されたピンの割合
  2. 02

    製造性

    DRC違反(ゼロ必須)、配線/間隔/ドリルのコンプライアンス
  3. 03

    物理ルールチェック(PRC)

    グランドプレーンの重なり、過熱配線長、差動配線長の不一致、配線幅精度、熱・信号性能
  4. 04

    製造適合性

    実際の製造業者のスタックアップと制約条件との互換性
  5. 05

    リソース効率

    レイヤー数、ビア数、配線長、部品密度

Quilter candidate reviewer showing a 100% routed board with no DRC violations

Our Origins

We’re Not Chasing AI Hype

We use AI because it’s the right tool for the job, not because it’s fashionable. PCB layout is a tough, persistent bottleneck in hardware engineering. Reinforcement learning offers a real path to solving it.Our team combines deep expertise in AI, from reinforcement learning and machine learning to neural networks, with years of hands-on experience in electrical engineering. We’ve lived the same problems you have, and we’re here to fix them.

NihonPennUC BerkeleySimons InstitutePrincetonPacific Northwest National LaboratorySynopsysNihonPennUC BerkeleySimons InstitutePrincetonPacific Northwest National LaboratorySynopsysNihonPenn
AutodeskAltiumOracleSamsung75th Ranger RegimentCadenceGeorgia TechLockheed MartinMITJohns HopkinsNASASamsungOracleAltiumAutodesk
Get Started

See Quilter in Action

Schedule a consultation and see how physics-driven automation removes layout from your critical path.