For IT and support
The user says it is slow. Measure it before you reimage it.
A test that runs from a browser tab needs no agent, no admin rights and no ticket to install anything. Same stages on every machine, a report a non-technical user can read back to you.
What the report tells you
Three figures, each with its reading.
Plain-words verdict
text
Is the cooling good, what the machine is good for, its strengths and weaknesses. The first screen of every report is written for the person who raised the ticket.
Run quality
flags
Hidden tab, on battery, single-core fallback, starved workers. The report says when a run is not comparable and why, so a bad run is not a bad machine.
Before and after
curve over curve
Run before a repaste, a driver, a BIOS update; run after. The report overlays the curves and calls anything inside the spread no change.
The diagnosis
The shape of the curve, read for your case.
01A steady slide
Cooling. On a fleet this is dust and age; the machines that slide are the ones to clean first.
02A single step down
A power limit. Often a power plan or vendor tool set to quiet or battery-saver mode, which is a settings fix.
03Erratic
Contention. Security agents, indexers and update clients on the cores. Compare against a clean machine of the same model.
Every class comes with a stated confidence and the measurement’s own noise floor. How the shape is read
Where a browser stops
What it cannot tell you.
- No inventory: the browser hides the exact processor and graphics model. The user picks the processor from a catalogue of about 1,600 parts.
- No storage test: a slow disk is the one common complaint this test will never find.
- No fleet dashboard yet: results live in the user's browser and can be emailed as a link. Central storage is on the roadmap and will be disclosed when it ships.
Which run
Standard, 3 minutes.
Three and a half minutes fits inside a support call. Ask for a deep run when a laptop's settled level is the question.
Both kinds are free. The choice is on the set-up screen.
Questions
Asked in these words.
- Does it need admin rights or an install?
- No. It runs in the browser tab with Web Workers and WebGL or WebGPU. A strict content security policy can block workers, in which case the report says it fell back to a single-core measurement rather than reporting a wrong number.
- Can users share the result with us?
- The report prints to PDF, and where the deployment has email configured the user can send themselves a link. The link opens the same report, with the measurements and the diagnosis.
- Will a security agent affect the result?
- If it uses the cores during the run, yes: throughput falls and noise rises, and the report flags starved workers when the effect is large. Comparing against a known-clean machine of the same model isolates the agent's cost.