Services
We test AI tools on your work.
The method behind our public tests, run privately for one business. Your task, your sample inputs, and the tools you are deciding between, paid or run on your own machines. You get what each one did, what it cost and where it failed.
Which tool should you pay for, or run yourself?
For a business choosing a tool. You name the task and send real examples of it. We run your shortlist the way a buyer would and report what you need to decide.
Tested for you
"We have three tools on the table. Which one does this job?"
For the person who has to choose
Every tool gets the same input, on the plan a business would buy, or on a machine like yours if it runs locally. We time each step, cost each output, keep everything it made and judge what is usable against a standard set before we start.
- The results table, with the plan and price on the test date
- A recording of every run, and every output, usable or not
- The settings and prompts, so your team can repeat it
- Our verdict for this task, and how far it reaches
What the results table holds
- Each tool, and the plan and price on the test date
- Outputs made, and how many were usable
- Time for each step
- Cost per usable output
- The same task done by hand, as the baseline
Pre-release test
"Where does our tool fail before buyers find out?"
Your tool against up to three competitors on a real business task, under the same rules as a public test. The report is private and ranks the failures by what they would cost a buyer.
For the maker of a tool
Telemetry audit
"What does our software send?"
The tests behind our telemetry reports, run on your build: the shipped code read, every connection listed, traffic captured where the build allows, each finding graded.
For the company that ships it
Training
"Can our team run these tests themselves?"
Half a day or a full day, remote, up to twelve people, prepared from a short questionnaire. The method: set the rules, run a tool on your own task, measure time and cost, judge a usable output, check what a tool sends.
For a team that keeps choosing tools
Documentation
"Write our setup guides."
Install and setup guides for your product, written from a real install on our test machine, delivered as Markdown or HTML for your docs site.
For a product or docs team
How it works
A fixed price before any work starts.
Write to us
Say which service you want and what you are trying to find out.
Scope and price
Within two working days you get the scope, a fixed price and a one-page agreement.
The work
Your task and sample inputs, or your build, or a questionnaire before a training day.
What you keep
The table, the recordings, every output and the raw measurements. All yours.
How we quote
Every engagement is a fixed price for the scope agreed, in writing, before we start. No hourly billing. If the scope grows, we stop and quote again.
Half on agreement, half on delivery, invoiced by StrideNote Studio. Tool subscriptions for the test are bought on a business plan and billed at cost, with the receipts.
Private work stays private. A client is not covered on StrideNote while the work runs and for twelve months after.
The course is free
A plain-language video course on running AI on your own machine. Free to watch, no sign-up. If your team wants it taught live, around your own work, that is the training above.
Tell us what you want to find out.
We reply within two working days.
Write to us