groundrun.io
Platform

Groundrun is the validation layer for developing your connected product with AI agents.

Your devices in a rig designed around your product, your app on real phones, your test cloud wired in, and scenarios that run the whole product end to end while a change is still taking shape.

The Groundrun flow builder. On the left, the unboxing flow with the four scenarios it was broken into. In the middle, the sequence a scenario runs through, with a power cut landing part way down it. On the right, the selected step with the faults that can land on it.
What changes

The agents get to work on the whole product.

On your roadmap What has to hold
Cut the delay between tap and action
That time is spent in the app, in your cloud, and on the device, so it only shows itself when the three of them run together.
Add the next device in the line
Everything the line already does has to work on it from the first day it exists.
Support the new phone OS
The app moves underneath devices that did not, and the two still have to agree about everything they agreed on yesterday.
Improve battery life
What drains it is decided by how often the app and your cloud make the device wake up, so the figure only appears once everything is running together.
Update vendor SDK
What moved underneath rarely shows itself until the product runs.

Work like this keeps arriving for as long as your product ships.

How it sits in your work

The agents develop, your product answers.

An agent writes a change that spans your product. Your flows run on your hardware with your app and your test cloud in the run, so the agent works from how the product behaved.

The coding agents the team runs today, in harnesses like Claude Code, Codex, and OpenCode, drive the whole system from inside their loop, so a change arrives in your repository already validated on your hardware.

See it on your product

The rig

Your customer's experience, reproduced on your hardware.

The rig is designed with you, around your product: your devices powered and connected, your app on real phones, your test cloud wired in. The boards on it are the ones your product ships, on the radios they use.

Rig
Power cycles the rig and flashes the new image onto the boards
They come up cold, running what is under test
App
Pairs the device over Bluetooth from the phone on the rig
The device appears in the app
Cloud
Takes the device's claim against your test cloud
The account owns it, and the app shows it online
Cloud
Sends an update to the claimed device
The device reports the version it is running
App
Hands the device to a second account
The second account sees it online

A device coming out of the box, step by step. Each step checks what your customer would see at that moment, and the run hands back the device log, the serial line, the cloud trace, the app screen, the current each board draws, and the timing, together. The drivers handle microcontrollers like the Silicon Labs EFR32MG24 and EFR32ZG28, and the Nordic nRF52840.

Coverage

Every flow your product runs.

We map your flows with you, in the team's own words. Each one becomes the scenarios that run on your hardware, the path through and the paths back.

Flow What it validates
Out of the box
The device is on, claimed, and working in the app
An update arriving
It lands, and the device runs it
A transaction across the product
It completes, and every record of it agrees
The network changing underneath it
The device is back online, and the app shows it
A week of running, then catching up
Everything it recorded arrives, and reconciles
The system

The platform the agents and the team both work in.

Four parts carry your flows from the team's words to the hardware they run on. The team directs what gets validated while the agents drive it as they work.

Flow builder

Your flows, in the team's own words, become the scenarios that run.

Hands over approved scenarios

Run coordinator

Compiles each scenario for the rig it will run on, picks the rig, and keeps the record of every run.

Hands over a compiled run

Rig runner

Flashes the boards, holds their serial lines, drives the phones, and works your test cloud through the scenario.

Hands back what the run produced

Rig supervisor

Switches the power on the rig, so that every run begins on hardware that has just come up cold.

Hands the runner a clean start
What you get

Confidence that keeps up with the agents.

Every change arrives with the flows it ran on your hardware behind it.

Get started

Put the whole product in the agents' loop.

Your hardware, your cloud, your app, working together on the rig.

Tell us about your product. We'll map your flows with you and show you what validation inside the agents' loop looks like on your hardware.

Book a demo