AI Assistant
- Filter. Choose Only Europe to show two orders.
- Explore. Choose Sort largest amount first, then Read visible orders.
- Preview an edit. Open More (…) and choose Set order 101 amount to 1500. Try Cancel changes, then submit again and choose Apply changes. Use Undo data change to reverse the edit.
Reset demo restores the original sample data and clears its conversation. To use your own prompts, follow the API-client setup guide.
Both examples use predefined requests without a backend or model key. To interpret your own wording, connect your API client as shown in the quick start and configure your backend.
Your application chooses which operations are available. Filtering and sorting are the starting point; reading totals, changing data and working with products such as Gantt require additional configuration. Supported data and column edits show a preview for the user to approve.
Start here
Section titled “Start here”How it works
Section titled “How it works”- A user enters a request in the grid’s prompt or chat.
- Your interpreter translates those words into a structured command, action or message. It can run on your backend using a model provider you choose.
- The assistant validates the result and uses the existing grid or product APIs. Data and column edits wait for approval.
AiAssistantPlugin supplies the grid integration. Provider SDKs and credentials stay on your backend. Row values are excluded from interpretation requests by default; see Control what the model receives for optional disclosures.
Build up your integration
Section titled “Build up your integration”Follow the first three guides for an initial integration, then open the topic you need:
| Guide | What you will learn |
|---|---|
| 1. Connect your first assistant | Prerequisites, plugin setup and your first filter/sort request. |
| 2. Choose actions and allow edits | Enable reads, layout changes and approved data or column edits. |
| 3. Control what the model receives | Choose disclosed fields, row samples, memory and result evidence. |
| Answer questions about data | Clarify requests and answer from permitted analytical results. |
| Connect custom actions and products | Integrate business services, Pivot, Pivot Charts, Gantt, Scheduler or Kanban. |
| Work with server-side data | Apply criteria through your remote loader and respect paging. |
| Customize chat, history and language | Configure presentation, suggestions, prompt recall and translations. |
| Set up the AI backend | Run the reference service and prepare an authenticated deployment. |
| Test your integration | Verify behavior without live model calls. |