Takes a requirement to a complete device
Hand Flux a requirement, not a click path. It picks the parts, designs the board, models the enclosure, and writes the firmware, then reports back.
Flux for Teams & Enterprise
The AI hardware engineering platform for teams.
One cloud-native platform for electrical, mechanical, firmware, and manufacturing engineering. Bring your favorite AI models into a fully integrated engineering environment built to turn ideas into working hardware.
Electrical
Mechanical
- Electronics Schematic captured
- PCB Placed and routed
- Mechanical Enclosure designed
- Firmware Code matched to the board
Autonomous engineering
From requirement to fab-ready design, Flux gets hard engineering work done.
Stop operating a stack of specialized CAD tools by hand. Describe the outcome you need, and Flux plans the work, designs it, checks it, and hands back results your engineers can review and edit.
Checks its own work in simulation
Flux runs circuit and electromagnetic simulations as part of the work, so problems show up on screen instead of on the bench.
Validates every change
Design rules, electrical checks, and review comments run continuously. Your engineers approve the result instead of hunting for mistakes.
Keeps every design ready to order
Live part pricing and availability, manufacturer-specific rules, and fab-ready outputs keep every design ready to order.
Its own engineering computer
Every AI engineer works on its own cloud computer, with a desktop and a browser. It runs engineering tools, reads PDFs and spreadsheets, and writes its own scripts to check its work.
Product videos
Makes videos of the product it designed, for design reviews, customer updates, and launch pages.
One platform
Designs the board, the enclosure, and the firmware.
Flux is not a collection of disconnected CAD applications. It is one AI-native engineering platform where every discipline shares the same project, the same data, and the same AI engineer.
-
Electrical engineering
Requirements, part research, schematic capture, and simulation.
-
PCB layout
Placement, routing, stackups, design rule checks, and the wiring harnesses between the boards.
-
Mechanical design
Parametric enclosures, brackets, and mounts, fitted to the real board's mounting holes and connectors. Bring in your own STEP models. One parts library for the whole product: chips and connectors, devices that are not on the board, and mechanical hardware such as screws and standoffs.
-
Firmware
Firmware for the board Flux designed, for example on Arm Cortex-M, RISC-V, AVR, or Pico, then built, analyzed, and unit tested.
-
Manufacturing
Live sourcing, cost, and manufacturer-ready outputs.
Model-agnostic AI
Your favorite AI models. Our engineering superpowers.
Flux pairs frontier AI models with a state-of-the-art agent harness built for CAD and EDA. The models bring reasoning. Flux brings the engineering tools, project context, and workflows that turn that reasoning into working hardware.
- OpenAI
- Anthropic
- Google Gemini
- More as they ship
Frontier performance at 30% lower cost.
Adaptive splits every engineering job into tasks and gives each task to the model that does it best for the price. Hard design decisions go to frontier models. Routine work goes to fast, low-cost models. Independent tasks run in parallel, so complete devices come together faster. Your team works with one AI engineer, and Flux handles the delegation behind the scenes.
Frontier AI models
- Reasoning
- Planning
- Language
Flux engineering harness
- CAD and EDA tools
- Project context
- Simulation
- Design rules
Working hardware
- Schematics
- Boards
- Enclosures
- Firmware
- Fab files
- Product videos
Every frontier model, one platform
Work with the frontier models your team already trusts, inside Flux.
Engineering superpowers built in
Every model gets Flux's specialized engineering tools, project context, and workflows.
Upgrade without migrating
When a better model ships, your team gets it without switching engineering platforms.
No single-vendor lock-in
Avoid depending on any one model provider for your engineering capacity.
The right model for every step
Adaptive matches each engineering step to the model that does it best, from deep design decisions to routine checks.
Kernel-agnostic CAD
Builds every part on the right CAD kernel.
Traditional CAD tools are locked to one geometry kernel, and every part inherits its limits. Flux is kernel agnostic, the same way it is model agnostic. The AI engineer picks the right kernel for each part, switches kernels when one cannot build a feature, and brings every part together in one model.
-
OpenCascade
Exact, standard geometry that CAM and other CAD tools read cleanly. Strong for machined parts and multi-part assemblies.
-
SMLib
Smooth, curvature-continuous surfaces for hand-held and consumer products.
-
Parasolid On request
The kernel inside SolidWorks, NX, Solid Edge, and Onshape, for native-quality exchange with those tools.
Surface quality you can see. Zebra stripes, curvature maps, and curvature combs show that every surface is smooth before the part goes to tooling.
Verification lab
Simulates and checks its own work before you build.
Flux doesn't stop at generating designs. The AI engineer simulates and checks its own work with professional-grade solvers, and it shows you the results.
Circuit simulation
SPICE simulation of analog, power, and mixed-signal circuits, run and read by the AI engineer.
Electromagnetic simulation
Full-wave simulation of the routed board: impedance, S-parameters, crosstalk, and antennas.
Thermal simulation
Heat and airflow simulation of boards and enclosures before you build them.
Fluid simulation
Airflow and cooling through the enclosure, so vents, fans, and heat sinks work before the first prototype.
Mechanical simulation
Finite-element stress analysis of brackets, enclosures, and mounts.
Design rule checks
Electrical and manufacturing rule checks on every schematic and board.
Datasheet checks
Reads the datasheet of every part and checks the design against its pinouts, ratings, and limits.
Orchestration
One request. A whole team of AI engineers.
Hand Flux a complete product. The lead AI engineer splits it into workstreams, starts parallel threads across projects, manages them, and reports back.
Parallel threads
Each workstream runs in its own agent thread. The main board, the daughterboards, and the enclosure come together at the same time.
Across projects
The lead engineer starts work in other projects and tracks it all from one place.
Managed for you
It monitors every thread, steers work that goes off the brief, and collects the results.
You stay in control
Changes that move an interface or resize a board wait for your approval.
A product with three daughterboards
Flux writes a brief for each board with its outline, mounting holes, connectors, and the enclosure openings they line up with. Each board gets its own project and its own AI engineer, and all three are designed in parallel. Flux then places the finished boards in the main assembly and measures clearances and connector alignment in millimeters.
Collaboration
Your team, your partners, and your AI engineers in one live project.
Flux runs in the browser. Everyone opens the same project, sees the same live design, and works on it at the same time. No files to send back and forth.
-
Edit together in real time.
Engineers, reviewers, and AI engineers work in the same project at the same time. You see who is in the project and what they have selected.
-
Every change is saved.
Flux records each change, who made it, and when. Open any earlier version, or restore it as a new project.
-
One shared space for your organization.
Your organization's projects, parts, and design standards live in one place. Give the whole organization view, comment, or edit access.
-
Work with suppliers, clients, and contractors.
Invite anyone to one project by email, with view, comment, or edit access. They get that project, not the rest of your organization.
-
Review where the design is.
Comment in the project and @mention a teammate. The discussion stays with the design.
-
Try ideas without risk.
Fork a project to test an idea. The main design does not change.
Customizable
Learns your team's rules and follows them on every project.
Every team builds hardware its own way. Teach Flux your standards, connect it to your tools, and let it build the small apps each project needs.
Team knowledge
Onboard Flux like a new engineer. Write your design guidelines, preferred parts, and lessons learned once, and every AI engineer in your organization applies them on every project.
Your rules
Define your layout rules and manufacturer capabilities once. Flux checks every design against them, every time.
Your tools, connected
Connect any MCP server, or give Flux a key to any web API. Push firmware to your repository, read crash reports from devices in the field, or use the tools your team built itself.
Keys stay secret
Admins add API keys once for the whole organization. The AI engineer uses them but never sees them. Flux adds each key only to requests sent to the services you allow.
Interactive pages
Ask for a one-off tool, and Flux builds it as a live page in the project: a power budget that recalculates when you change a load, a bring-up checklist that tracks progress, or a 3D assembly you can turn and take apart.
Flux in your AI tools
Use Flux from Cursor or any general AI agent that supports its tools. Your agents can read and edit Flux projects and hand design jobs to the Flux AI engineer.
Connects to the services your team already uses.
-
Onshape -
Autodesk Fusion -
PTC Windchill - Siemens Teamcenter
-
Arena PLM -
OpenBOM -
Duro -
GitHub -
GitLab -
Memfault -
Golioth -
Particle -
Nordic nRF Cloud -
Edge Impulse -
NI SystemLink -
SimScale -
Octopart -
SiliconExpert
Sourcing
Picks parts you can buy today, at today's prices.
Flux connects directly to major electronics and mechanical parts distributors. The AI engineer picks chips, connectors, screws, and standoffs that are in stock, compares prices across distributors, and replaces parts that are at end of life before the product goes to production.
-
Digi-Key -
LCSC -
Mouser -
Arrow -
Verical -
TME -
HQonline -
McMaster-Carr -
MISUMI -
JLCMC
Manufacturing
Gets quotes from your fabricators as the design changes.
Flux gets quotes directly from the fabricators for circuit boards and assembly, 3D printing in plastic and metal, CNC machining, sheet metal, laser cutting, injection molding, and casting. The AI engineer compares price and lead time, checks the design against each fabricator's rules, and keeps the quote current as the design changes.
Circuit boards and assembly
-
JLCPCB -
PCBWay -
OSH Park -
AISLER
Mechanical parts
-
Craftcloud - JLC 3D printing
- PCBWay 3D printing
-
Shapeways -
OSH Cut -
SendCutSend
Interoperability
Works with the EDA and CAD tools your team already uses.
Bring in work from the tools your team uses today. Ask Flux to change it in plain words. Export your files at any time.
-
Altium Designer -
OrCAD and Allegro -
KiCad - PADS, Xpedition, and NX
-
CADSTAR -
Eagle and Fusion -
EasyEDA -
SolidWorks -
CATIA - Creo
- Onshape
Edits the STEP files your team already has.
The request, as typed in Flux
“The holder must cover a much taller power supply. Make the bent side flange 40 mm deeper. Keep the 4.4 mm hole in the flange where it is. Then cut five 5 x 30 mm vertical vent slots in the new part of the flange, 15 mm apart and centered on the flange width.”
Bring your existing work
Import complete projects, part libraries, and 3D models. Schematics, parts, and placement come across, and routing from most formats.
Keep going with your AI engineer
Imported designs are ready to edit right away. Ask "move the USB cutout 3 cm left" or "make the enclosure tighter", and Flux does the work.
Get it manufactured
Flux hands you the files that your manufacturer needs: Gerber, ODB++, IPC-2581, bill of materials, and pick-and-place for the board, and STEP, STL, or 3MF for the mechanical parts.
All supported formats
- Complete projects
- Altium, Cadence OrCAD and Allegro, KiCad, Siemens PADS and Xpedition, Zuken CADSTAR, Eagle, and EasyEDA. Schematics, parts, connections, board outlines, and placement come across. Labcenter Proteus netlist and board exports bring in parts, connections, board outlines, placement, and routing.
- Part libraries
- Altium, OrCAD, PADS, KiCad, Eagle, and EasyEDA libraries, Allegro footprints, and JEP30 part models become Flux parts.
- Mechanical files
- STEP, STL, OBJ, 3MF, and glTF models, plus DXF board outlines.
- Handoff to manufacturing and electronics tools
- Gerber, ODB++, IPC-2581, IPC-D-356 test netlists, bill of materials, pick-and-place, EDIF netlists, GenCAD, and KiCad board files.
- Handoff to mechanical design
- The full board and its parts as STEP, compressed STEP, BREP, VRML, glTF, and STL models, plus DXF layer drawings. Enclosures and brackets that Flux designs export as STEP, STL, and 3MF, ready for your mechanical tools or a 3D printer.
Enterprise adoption
We help your team put AI to work.
Flux works directly with engineering organizations to put AI to work on real programs, with hands-on support from Flux engineers.
Book a Demo-
Identify high-value use cases
We map where AI engineering saves your team the most time, from part research to complete devices.
-
Integrate your workflows
We connect Flux to the libraries, rules, and processes your engineers already use.
-
Make it repeatable
We help you establish AI engineering processes your teams can run on every project.
Security and governance
- SOC 2-aligned cloud infrastructure
- Single sign-on (SSO)
- Project-level permissions
- Inputs and outputs are always your IP
- No training on customer data
Pricing
Plans for every engineering organization.
Feature
Teams
$500/month
or $4,900/year
Enterprise
Custom
Seats 5 included, then $100/month per extra seat Custom
AI usage 600 shared AI usage units a month, plus 60 per extra seat Custom
Collaboration Included Included
Model-agnostic AI Included Included
Enterprise integrations Standard Custom
Dedicated onboarding Self-serve Assisted
Forward-deployed engineers — Available
Questions engineering teams ask.
Flux is your team's autonomous hardware engineer. Give it a requirement. It plans the design, picks the parts, draws the schematic, routes the board, shapes the enclosure, and writes the firmware. It checks its own work in simulation and design rule checks, and hands your engineers files ready to manufacture.
Claude and Codex are general AI agents. They can write code and CAD scripts, but they cannot see your board or enclosure, run engineering simulation, or check live part prices and stock. Flux runs the same frontier models inside a complete hardware engineering environment. It sees the design, builds real CAD geometry, simulates it, checks every part against its datasheet and live distributor data, and gets quotes from fabricators. Your whole team shares the projects, knowledge, and rules.
Electrical engineering, PCB layout, mechanical design, firmware, and manufacturing, in one shared project. Flux also runs circuit, electromagnetic, thermal, and mechanical simulation to check its own work.
Frontier models from OpenAI, Anthropic, and Google, with more as they ship. Adaptive gives each task to the model that does it best for the price, so your team gets frontier results at lower cost.
Yes. Flux imports complete projects from Altium, Cadence OrCAD and Allegro, KiCad, Siemens PADS and Xpedition, Zuken CADSTAR, Eagle, and EasyEDA. Labcenter Proteus netlist and board exports bring in parts, connections, board outlines, placement, and routing. Mechanical parts and complete assemblies come in through STEP, from tools like SolidWorks, CATIA, Creo, Onshape, NX, and Fusion. You can export all your files at any time and get them manufactured.
Yes. Flux writes firmware for the microcontrollers on the board it designed, for example Arm Cortex-M, RISC-V, AVR, and Raspberry Pi Pico. Then it builds, analyzes, and unit tests the code.
Flux runs on SOC 2-aligned cloud infrastructure, with single sign-on and project-level permissions. Your inputs and outputs are always your IP, and Flux does not train on customer data.
Yes. Write your design guidelines, preferred parts, and layout rules once, and every AI engineer in your organization applies them. You can also connect your own tools through MCP.
No. Flux runs in the browser. Engineers, reviewers, and AI agents work in the same live project, with no licenses or workstations to manage.
The Teams plan costs $500 a month, or $4,900 a year. It includes 5 seats and 600 AI usage units a month that the whole team shares. Each extra seat costs $100 a month and adds 60 usage units. Enterprise plans have custom seats and usage, custom integrations, assisted onboarding, and forward-deployed engineers. Every plan includes collaboration and the choice of AI models.
Stop shelving hardware ideas. Build them all with Flux.
Give your team the tools and AI engineering capacity to build what previously required an entire organization.