“EDA’s premier code-based, AI-driven PCB design tool.”
JITX is a code-based platform for the development and optimization of complex printed circuit boards, particularly high-frequency systems. Requirements are described in Python; AI can generate or revise the code. JITX uses this to generate schematics and layouts, employs routing and optimization methods, and can initiate and evaluate electromagnetic simulations using Ansys HFSS.
JTIX
Software-defined electronics
Location: USA ⓘ JITX Inc., 1207 10th Street, Berkeley, CA 94710, USA
Trial / Demo / Training Customized demonstrations, trial accounts, and training programs.
Consulting Consulting for automated hardware design and implementation of the JITX methodology.
Custom Development Custom development, company-specific design libraries, verification rules, and integrations.
Target audiences
JITX is designed for professional electronics developers, RF and high-speed specialists, aerospace companies, semiconductor and system manufacturers, and technical organizations with recurring hardware platforms. The benefits are particularly significant when design rules, optimization goals, and circuit variants need to be represented programmatically.
Outstanding features
JITX combines AI-generated Python code with deterministic EDA primitives, constraint solvers, and physical simulation. The AI can process requirements and datasheets and suggest changes, while the generated code remains inspectable. For high-frequency designs, the system can generate structures, run HFSS simulations, and feed results back into further optimization steps.
Key Areas of Application
Typical applications include RF boards, antenna and high-frequency structures, high-speed electronics, automated pin assignment, constraint-based schematic generation, platform designs, and design space exploration. Companies can implement recurring engineering rules as Python code and verifiable design logic.
Usage & Notes
The user defines requirements and constraints; the AI suggests Python code or code changes. These changes must be approved and then validated through JITX solvers, DRCs, simulations, and engineering reviews. The free license is not suitable for confidential customer projects. For such projects, Enterprise licensing must be arranged in advance.
| Target audience | Assessment |
|---|---|
| Individuals / Makers | Limited – Free-and-open model available, but significantly more technical than traditional PCB GUI tools. |
| Self-employed / Freelancers | Yes, with knowledge of coding and electronics – suitable for reusable, parametric circuit and PCB designs. |
| Hardware startups | Very well suited – can automate variants, component selection, design rules, and recurring tasks. |
| SMEs | Yes – especially for companies with multiple product variants or recurring PCB architectures. |
| Large enterprises | Very well suited – local installation, air gap, proprietary designs, PLM and CAD integrations, and dedicated support are available. |
| Developers / Electrical Engineers | Very well suited – the core target audience is hardware developers who want to model and automate circuits as code. |
| Education / Research | Yes – free open-source model for openly licensed designs and use at universities. |
| Organizations with data protection concerns | Good with Enterprise – local and air-gapped installations enable high data control; public cloud/website usage remains US-based. |
Fact-based AI assessment:
AI tool: Yes. AI involvement: high. Impact on overall functionality: high.
In the current JITX workflow, AI converts requirements into Python code, suggests changes, processes datasheets, and supports optimization processes. The actual technical validation continues to be performed by verifiable Python code, constraint systems, routing solvers, and HFSS simulations. AI is thus central to operation and iteration, while deterministic EDA and simulation components ensure reliability.
Hosting & Data
1) On-prem / local hosting
Meaning: The company operates the solution on its own hardware or within its own infrastructure. In the strictest sense, not only the application runs locally, but ideally the model as well.
2) Private cloud / data center
Meaning: The solution runs in a dedicated or more clearly separated cloud environment, often with a hosting provider or hyperscaler, but in a German data center or in a particularly controlled environment.
3) EU SaaS / managed
Meaning: The provider operates the solution itself as a service. The company uses the tool as a ready-made cloud service, ideally with EU data residency.
4) Hybrid
Meaning: One part of the processing remains internal / local / in a private cloud, while another part runs in an external cloud or EU SaaS.
5) AVV / DPA
Meaning: This is the data processing agreement or Data Processing Addendum. It governs that the provider processes personal data on behalf of the customer and is bound by the customer's instructions.
6) No training
Meaning: The provider does not use your prompts, uploads, attachments, chat histories, or outputs for training or improving the general model — ideally excluded by contract.
7) Open-source / transparency path
Meaning: There is a path toward greater technical transparency and sovereignty, for example through:
- open models
- documented components
- self-hostable parts
- traceable architecture
- export / switching options
| On-prem / local hosting | ✅ |
| Private cloud / data center | ✅ |
| EU SaaS / Managed | ❓ |
| Hybrid | ✅ |
| DPA / AVV | ❓ |
| No training on customer data | ⚠️ |
| Open source / transparency path | ⚠️ |
Overall Assessment:
Local enterprise EDA with optional cloud access and an open entry-level model. JITX offers two distinct operating models: “Free and Open” for open-source designs and “Enterprise” for proprietary designs. Enterprise is hosted locally and can be operated in an air-gapped environment. This makes JITX suitable for confidential hardware, industrial, aerospace, or research projects.
Data processing: The system processes circuit descriptions, component information, design requirements, PCB layouts, test results, and integration data. Enterprise can be connected to PLM systems as well as KiCad, Altium, and Siemens Expedition. The software automates routine tasks and performs detailed electrical design checks.
Generative AI: JITX describes generative AI as a complement to code-based development. According to its own tests, LLMs are particularly well-suited for data extraction from datasheets and writing more abstract code; JITX still sees significant reliability limitations for autonomous original circuit development.
Conclusion:
JITX is attractive to companies that require reproducible and automated PCB engineering. Data protection and intellectual property protection are significantly easier to control with local or air-gapped installations than with pure cloud EDA offerings.
| On-prem / local hosting | ✅ |
| Private cloud / data center | ✅ |
| EU SaaS / Managed | ❓ |
| Hybrid | ✅ |
| DPA / AVV | ❓ |
| No training on customer data | ⚠️ |
| Open source / transparency path | ⚠️ |
Overall Assessment:
Local enterprise EDA with optional cloud access and an open entry-level model. JITX offers two distinct operating models: “Free and Open” for open-source designs and “Enterprise” for proprietary designs. Enterprise is hosted locally and can be operated in an air-gapped environment. This makes JITX suitable for confidential hardware, industrial, aerospace, or research projects.
Data processing: The system processes circuit descriptions, component information, design requirements, PCB layouts, test results, and integration data. Enterprise can be connected to PLM systems as well as KiCad, Altium, and Siemens Expedition. The software automates routine tasks and performs detailed electrical design checks.
Generative AI: JITX describes generative AI as a complement to code-based development. According to its own tests, LLMs are particularly well-suited for data extraction from datasheets and writing more abstract code; JITX still sees significant reliability limitations for autonomous original circuit development.
Conclusion:
JITX is attractive to companies that require reproducible and automated PCB engineering. Data protection and intellectual property protection are significantly easier to control with local or air-gapped installations than with pure cloud EDA offerings.
Strengths & weaknesses at a glance
| Strengths | Weaknesses |
|---|---|
| • A very high degree of automation for complex electronic designs | • High technical barrier to entry |
| • Testable and version-controlled Python code | • Knowledge of Python and EDA remains required. |
| • A combination of AI, deterministic solvers, and physical simulation | • Strongly geared toward professional and complex engineering workflows. |
| • Local or isolated enterprise operation | • Costs and contract terms for the Enterprise offering are available only upon request. |
| • Interfaces to KiCad, Altium, Siemens Expedition, and PLM systems | • According to the provider, the free tier may only be used for designs under specific open-hardware license terms. |
| • Suitable for repeatable platform and product family development | • AI-generated code and simulation results require qualified technical approval. |
Reviews
0 reviews in total
There are no confirmed reviews for this tool yet.
Submit review
Your review will only become visible after email confirmation. This protects the portal against abuse.
Report review
Please select the reason why this review should be checked.
GDPR-compliant usage possible?
Overall assessment:
Conditional; well-controlled in locally hosted enterprise environments.
A positive aspect is that JITX offers enterprise customers a locally hosted and air-gapped installation. This allows proprietary designs to be processed within the customer’s own IT infrastructure without requiring design data to be transferred to a public US cloud. JITX treats customer data as confidential information in its Terms of Service.
A negative aspect is that the general JITX services are hosted in the U.S. The privacy policy mentions Google Analytics, FullStory, and HubSpot; the website may collect device and interaction data, including form interactions. Personal data may be stored in the U.S. and transferred from there to other countries.
Server location: U.S. for general hosted services; local customer infrastructure for the Enterprise model. No publicly available GDPR DPA, EU hosting, SCC document, or complete list of subprocessors was found: No verified information available.
Training on customer data: JITX has published research on the use of external LLMs such as Claude, Gemini, and GPT for PCB code. No general public commitment stating that customer designs are never used for AI training was found. In local or air-gapped operations, this risk can be significantly reduced from a technical standpoint.
Conclusion: For GDPR- and IP-critical hardware projects, enterprise operation on proprietary infrastructure is the most sensible option. The browser-based website and marketing services should be evaluated separately from the actual local design environment.