Classify new rows with AI
When a new row is added in Grist (API key), send its text to Mistral AI and write the returned category back to the row.
See all Grist (API key) + Mistral AI integrations or talk to a human
Google for Startups AcceleratorHow Knit builds this workflow
The Agent researches both APIs and wires the trigger on one side to the action on the other — no pre-built connector required. Here is the vocabulary it has to work with.
Grist (API key) Explore Grist (API key) →
TriggersFires when a row is added to a sheet in Grist (API key).
Fires when a row or column changes in Grist (API key).
Fires when a new spreadsheet or worksheet is created in Grist (API key).
Adds a new row to a sheet in Grist (API key).
Updates the values in an existing row in Grist (API key).
Finds a row by a column value in Grist (API key).
Mistral AI Explore Mistral AI →
TriggersFires when Mistral AI returns a completion, prediction or other result.
Fires when a request to Mistral AI errors or times out.
Fires when a fine-tuning job in Mistral AI finishes.
Sends a prompt to Mistral AI and returns the model's response.
Sends text, an image or other data to Mistral AI and returns the model's output.
Uses Mistral AI to classify or extract structured data from text or images.
More Grist (API key) + Mistral AI workflows
See all Grist (API key) + Mistral AI integrations → · Browse the full workflow library →
Enterprise-grade security
Common questions
Can Knit build “Classify new rows with AI” between Grist (API key) and Mistral AI?
Yes — describe it in the box above and Knit's Integrations Agent researches Grist (API key) and Mistral AI's public API docs (or your own uploaded docs) and builds a working workflow, whether or not either app already has a pre-built connector.
How long does it take to build?
Minutes to a first working version, not weeks — you test it against real data before it goes anywhere near production.
Can AI fill in a spreadsheet column?
Yes. When a row is added in Grist (API key), Mistral AI can process its contents and the output can be written to another column of the same row.
What can the model do with each row?
Common uses are classifying feedback, summarizing long text, translating, extracting fields and drafting replies, all written back into Grist (API key).