In the right scenarios, it’s already delivering sharper reasoning, smarter reviews, and more accurate design decisions than anything we’ve shipped before. We wanted to get it into your hands immediately so you can explore what’s possible alongside us. It’s early, it’s raw, and we want you to push it. Break it. Tell us where it shines.
You can start using it right away. Open any project in Flux and launch Copilot. Click the model dropdown at the top of the chat panel, select “Next-gen” and then give it a real challenge. Some great starter prompts to see its strengths include:
“Perform a top-to-bottom schematic review for correctness, completeness, and robustness. Assess power, clocks/resets, signal interfaces, analog paths, protection, and passive choices.”
“Replace all low-stock parts with alternatives that meet the same constraints.”
The upgrade isn’t just that GPT-5 is a newer model. It brings a different caliber of intelligence to Copilot:
These improvements land harder in Flux because Copilot already has deep, live context on your design—down to parts, pins, nets, properties, constraints, and stackups—so reinforcement models and LLMs can work side-by-side from the canvas up to system architecture. And because Flux is built for agentic workflows—stepwise actions, constraint-aware edits, and iterative design loops right where you work—GPT-5 isn’t starting from scratch; it applies improved reasoning directly to your schematic or layout. Layered on top is a knowledge base of industry best practices and embedded design/process checks, so your AI partner starts from seasoned experience and turns that context into answers that are immediately relevant and actionable.
In just 48 hours of testing, we saw moments that made us stop and say, “This is new.”
Design a low-noise microphone preamplifier for an electret condenser mic feeding a 24-bit ADC. You must calculate the bias network, gain-setting resistors, coupling capacitors, input high-pass cutoff, output anti-aliasing RC, and decoupling layout. Follow the op-amp and microphone capsule datasheets, ADC input requirements, and industry best practices. It will be integrated into a design. Supply: 3.3V analog rail. Mic bias: 2.0 V through resistor, current ~0.5 mA. Target gain: 20 dB to 40 dB switchable. Bandwidth: 20 Hz to 20 kHz. Input noise target: as low as practical. Include pop-suppression considerations and star-grounding strategy.
In this case Flux took a plain-English prompt and produced a full low-noise mic preamp to a 24-bit ADC—calculating the right bias, gain, and filter values, choosing real parts, then placing and wiring the entire block with decoupling, VCM bias, and star-ground best practices. It even audited itself (fixed missed ties, made gain legs switchable). The result is a ready-to-review schematic 80% away from layout built end-to-end—complex, competent, and fast.
Right now GPT-5 powers Copilot’s chat, but this is just the beginning. We’re already working on:
Open Flux now, switch Copilot to “Next-gen” and see how it handles your next design challenge. The sooner you try it, the more your feedback can shape the next leap in AI-powered hardware design.
A practical guide to when hardware teams should use low-volume PCB prototyping to validate a design versus full-scale fabrication to scale production, and how to transition between the two without costly mistakes.
A practical guide to the four main PCB via types — through-hole, blind, buried, and microvia — covering how each is fabricated, their cost and signal-integrity trade-offs, and when to use them based on layer count, BGA pitch, and routing density.
Learn PCB design for manufacturability (DFM) guidelines, rules, and common issues to ensure your circuit boards can be reliably produced.
Learn the best PCB routing techniques for clean circuit board layouts, including trace routing tips, differential pair routing, and layout best practices.
Whether you're migrating from popular EDA applications or starting fresh, mastering high speed PCB design has never been more intuitive. Flux enables teams to design, simulate, and route with real-time AI assistance, so you can spin your next high-speed board with total confidence.
DRC is an automated process that checks your PCB layout against manufacturing and electrical constraints, catching errors like trace spacing and drill sizes before fabrication. Modern tools run this in real-time during design, while older ones batch-check at the end, often producing overwhelming error lists.
Whether you are exploring “What is a PCB?” for the first time or moving into advanced hardware engineering, modern tools make the process easier than ever. With Flux's AI-assisted platform, you can skip the steep learning curve of popular ECAD applications and design collaboratively directly in your browser. Once your board is routed and ready for fabrication, Flux's built-in supply chain features connect you directly with worldwide distributors to source parts instantly. Sign up for free today and start building!
Flux brings circuit simulation to wherever you are in the design process. Start from a prompt when you have no schematic, or let Flux analyze your existing design automatically.
