BigML StrawberryHand the BigML batch predictions to a companion
A companion works the 3 operations your BigML account exposes. It can create source (remote url) and create a model, and every one of those waits on an approval card showing the batch prediction before it changes.
Open the batch prediction. Check it against something else. Write the change. Move to the next one. That is the BigML afternoon nobody can hand off, and a companion does the whole pass and gives you back the batch, with nothing landing on a batch prediction until you approve it.
What it can do is exactly what BigML exposes to an account you authorise and nothing beyond it: 3 operations, no reads and 3 writes. In practice that means it can create source (remote url), create a model and create a batch prediction, and work across the batch predictions, models and sources.
The BigML API stops at BigML. A companion does not. The same run opens the customer's website, the supplier portal, the internal tool somebody built in 2019, because it is working the browser you are already signed into rather than calling in from outside it.
Which BigML batch predictions does a companion see?
In the tab.
BigML exposes no read operation to a connected account, so a companion opens BigML in the session you are already signed into and reads the screens you would.
The batch predictions are what most of this inventory is about, alongside the models. A companion can hold all 3 of these operations and forty open tabs in the same pass, which is how an afternoon of BigML admin becomes a queue you review.
Can it change a batch prediction without asking?
All 3 write operations wait for you. A companion can create source (remote url), create a model and create a batch prediction, and each one is staged on an approval card first: you see the batch prediction, the field and the new value before it lands in BigML.
Nothing in BigML is sent, changed or deleted on your behalf without that click, and a rejected card leaves the batch prediction exactly as it was. The gate is the same one on every surface, described at security.
- Create Source (Remote URL)
- Create Model
- Create Batch Prediction
Can the batch predictions pass run every Monday?
Yes.
Saved as a routine, the BigML batch predictions pass runs at the hour you pick: the Monday sweep, the overnight refresh, the Friday check. Keep Awake holds the machine awake for the length of a run, so a scheduled pass finishes with the lid closed.
The product and engineering playbook catalogues the other recurring shapes of the engineering admin, the BigML batch predictions sweep among them, and finished runs are published at real runs.
Experience Strawberry for free
DownloadTrusted by fast-growing companies worldwide
Frequently asked questions
Strawberry is free to download and includes AI credits to start. Paid plans begin at $20/month. See pricing. · Reviewed · Canonical facts for AI agents