Skip to content
Torotech
← All products

Toro Chat AI

Live

Embedded AI chat for SAP Fiori apps — reads your app's own OData service, no platform to license.

SAPFioriOpenRouterODataVisit product ↗

Toro Chat AI is an embedded, read-only chat layer for SAP Fiori apps. Drop in a script tag, a system prompt, and an OpenRouter key next to an app that already exists — no agent framework, no vector database, no separate copilot platform to license.

It's live today inside a real SAP Build Work Zone site, answering questions against a live OData service — SAP's own SEPMRA_SHOP product catalog — with a category breakdown, per-supplier counts, and a generated chart, all pulled from the service in real time. Nothing is scripted or mocked.

The model never holds a connection to SAP. Every read runs through a narrow client scoped to exactly the entities the workflow needs, under the signed-in user's own session — so there's no technical user to provision and nothing extra for security to review. Read-only today; the same pattern extends cleanly to writes when a workflow calls for it.

Read the full architecture write-up: A Chat Layer, Not a Chatbot.

The screen underneath: a standard Fiori list report over the SEPMRA_SHOP product catalog. This is the same OData entity set Toro Chat AI reads — nothing about the app itself was changed to add the chat layer.
The screen underneath: a standard Fiori list report over the SEPMRA_SHOP product catalog. This is the same OData entity set Toro Chat AI reads — nothing about the app itself was changed to add the chat layer.
One click on "Provide me the product overview" and the orchestrator queries the live service for a category breakdown — 205 products, 8 categories, real average prices and stock counts.
One click on "Provide me the product overview" and the orchestrator queries the live service for a category breakdown — 205 products, 8 categories, real average prices and stock counts.
Scrolling the same reply: per-supplier counts, a generated bar chart, and two observations the model drew out of the numbers — Office Furniture's price outlier and Meeting & Presenting's stock shortfall.
Scrolling the same reply: per-supplier counts, a generated bar chart, and two observations the model drew out of the numbers — Office Furniture's price outlier and Meeting & Presenting's stock shortfall.
The same question, same live data, rendered with the widget's richer formatting — a narrative summary above the breakdown table.
The same question, same live data, rendered with the widget's richer formatting — a narrative summary above the breakdown table.
Scrolling that formatted reply reaches the same supplier table and category chart — same query, same orchestrator, just a different rendering pass.
Scrolling that formatted reply reaches the same supplier table and category chart — same query, same orchestrator, just a different rendering pass.

More products

Tell us about the process that hurts.

A 30-minute call is enough to tell whether an agent, an extension or a plain good Fiori app is the answer. No deck, no discovery fee.

Book a callSee the work