A prototype we built for a trade-intelligence publisher. September to December 2025.
A trade-intelligence publisher wanted to know whether the reporting its desk does by hand could start from an automated pass over company websites. The n8n workflow collects the figures, drafts the article and stops at a review step, on the platform the team already runs.
Screens from this system are being added.
The publisher wanted an agentic AI use case that answered a business need rather than a technology demonstration: could the reporting its desk does by hand start from an automated pass over company websites? The prototype was built and shown live on the platform the team already operates, so the answer was a workflow they could run rather than a proposal.
The publisher's team watched the workflow run live on its own n8n in December 2025. The answer to its question was a workflow it could run rather than a proposal.
A prototype we built for wholesale order desks
An email becomes order lines against a catalogue, stock moves to reserved, and a quotation drafts itself. 3 quantities per stock item: on hand, available and reserved.
A prototype we built for ads-ops teams
The CSV or JSON export an ads-ops person opens every morning, aggregated per campaign, compared against the previous day, with what to look at first pulled to the top. 40 minutes of a person's morning, and a spreadsheet, before the prototype.
A prototype we built for an insurance operation in Thailand
Gemini 2.5 Pro reads a scanned Thai and English insurance form and returns every field as structured JSON, on video, with the SAP entry stage mapped for the operation to decide on. 46 fields out of one scanned insurance form, as JSON.
Elsewhere on the site
Where to next
Say so in a few sentences. The reply comes from the person who built this one.