August 11, 2025

Flux + GPT-5 (Beta)

Flux Copilot is your AI hardware engineer — a collaborative partner that can design, review, and improve your hardware right inside your project. We’re constantly upgrading it with the best models available, and this weekend we plugged in GPT-5.

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.

Try It Now

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.”

Try GPT-5 in Flux now

What’s New and Better

The upgrade isn’t just that GPT-5 is a newer model. It brings a different caliber of intelligence to Copilot:

  • Stronger reasoning and planning for complex, multi-step problems.
  • More accurate part and constraint decisions, often with clearer explanations.
  • Sharper design reviews that catch subtle issues and propose fixes.
  • Richer, more verbose answers that lay out assumptions, tradeoffs, and edge cases.

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.

Early Win from the Weekend

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.

Try it Now

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.

Getting the most from “Nex Gen” model in Flux

  • Read the whole answer. The “Next Gen” model is verbose on purpose—the assumptions, edge cases, and self-checks are where the value lives.
  • Front-load context. In your first message, share goals; rails & loads; key interfaces (e.g., USB-C: CC1/CC2, D+/D−, SBU); constraints (cost/size/EMI); and manufacturing rules of thumb. Keep answering follow-ups to deepen the design.
  • Scope tightly. When wiring schematics, tackle one rail, one bus, or one block at a time.
  • Plan before you act. Validate the change plan against requirements before applying edits—changing the plan is cheaper than undoing work.

What’s Next

Right now GPT-5 powers Copilot’s chat, but this is just the beginning. We’re already working on:

  • Tighter loops between chat and in-editor actions.
  • More constraint-aware placement and routing.
  • Datasheet-to-design transformations in minutes.
  • Smarter, in-context automated fixes.

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.

Try GPT-5 in Flux now

Profile avatar of the blog author

Ryan Fitzgerald

Ryan is an electronics and electrical systems engineer with a focus on bridging the gap between deep learning intelligent algorithms and innovative hardware design. Find him on Flux @ryanf

Go 10x faster from idea to PCB
Work with Flux like an AI hardware engineer—handling complex tasks, learning your standards, explaining its decisions, and collaborating with you at every step.
Illustration of sub-layout. Several groups of parts and traces hover above a layout.
Design PCBs with AI
Introducing a new way to work: Give Flux a job and it plans, explains, and executes workflows inside a full browser-based eCAD you can edit anytime.
Screenshot of the Flux app showing a PCB in 3D mode with collaborative cursors, a comment thread pinned on the canvas, and live pricing and availability for a part on the board.
Design PCBs with AI
Introducing a new way to work: Give Flux a job and it plans, explains, and executes workflows inside a full browser-based eCAD you can edit anytime.
Screenshot of the Flux app showing a PCB in 3D mode with collaborative cursors, a comment thread pinned on the canvas, and live pricing and availability for a part on the board.
Design PCBs with AI
Introducing a new way to work: Give Flux a job and it plans, explains, and executes workflows inside a full browser-based eCAD you can edit anytime.
Screenshot of the Flux app showing a PCB in 3D mode with collaborative cursors, a comment thread pinned on the canvas, and live pricing and availability for a part on the board.

Related Content

RC Low-Pass Filter: Formula, Cutoff Frequency & Design

RC Low-Pass Filter: Formula, Cutoff Frequency & Design

Explains how RC low-pass filters attenuate high-frequency signals using a resistor and capacitor, with the cutoff frequency formula, component selection trade-offs, and PCB layout best practices.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 29, 2026
What Is a Reflow Oven? PCB Reflow Soldering Explained

What Is a Reflow Oven? PCB Reflow Soldering Explained

Covers how reflow ovens solder SMT components through preheat, soak, reflow, and cooling stages, with common defects and how PCB layout decisions impact manufacturing yield.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 29, 2026
Gerber Files Explained: PCB Layers, Formats & Export

Gerber Files Explained: PCB Layers, Formats & Export

Gerber files are the universal 2D vector format that bridges PCB design and fabrication. This guide covers what each layer file contains, how to export and verify a complete manufacturing package, and the common mistakes that cause production delays.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 19, 2026
Pi Filters Explained: Design, Components & Applications

Pi Filters Explained: Design, Components & Applications

A pi filter is a three-element passive CLC network that provides stronger ripple and EMI suppression than a single capacitor. This guide covers topology selection, component derating, resonance damping, and PCB layout best practices.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 19, 2026
Tantalum Capacitors Guide: Polarity, Derating & Risks

Tantalum Capacitors Guide: Polarity, Derating & Risks

Tantalum capacitors offer high capacitance density in a tiny footprint but demand strict polarity and voltage derating. This guide explains how they compare to ceramics and aluminum electrolytics, common failure risks, and how to select and place them safely.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 19, 2026
What Is PCBA? PCB vs PCBA and Assembly Explained

What Is PCBA? PCB vs PCBA and Assembly Explained

PCBA turns a bare PCB into a functional circuit by mounting and soldering components. This guide breaks down the assembly workflow, SMT vs through-hole methods, required manufacturing files, and common defects to avoid.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 19, 2026
Electrical Rule Check (ERC) vs DRC in PCB Design

Electrical Rule Check (ERC) vs DRC in PCB Design

ERC checks schematic-level electrical issues while DRC checks PCB layout rules -- engineers run ERC before layout and DRC during or after routing.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 7, 2026
Hardware Design Workflow: From Schematic Capture to Manufacturing

Hardware Design Workflow: From Schematic Capture to Manufacturing

The complete hardware design workflow covers requirements, schematic capture, PCB layout, validation, prototyping, and manufacturing.

Profile avatar of Gabriel Hacohen
Gabriel Hacohen
|July 7, 2026