Using the AI Assistant

Describe what you want in plain language, and the right skill activates and looks up accurate component knowledge through the MCP server.

🚧 Early access. Build with AI is rolling out gradually and improving with every release. Something unclear, missing, or broken? Tell us: your feedback directly shapes what we improve next.

You don't invoke skills or MCP tools yourself. Describe the outcome in plain language, and the assistant activates the right skill and looks up real component knowledge through the MCP server.

The right skill activates for you

You're working on…	Skill that activates
Avonni Flow Screen Components in a screen flow	avonni-flow-components
An Avonni Dynamic Component	avonni-dynamic-components
Avonni components on a Digital Experience site page	avonni-experience-components
Avonni components in LWC code (HTML/JS/CSS)	avonni-lwc-components
Anything spanning multiple artifact types, or a business use case	avonni-architect

Rule of thumb: a single artifact of a known type goes to its specific skill. A request that spans artifact types or describes an end-to-end use case goes to avonni-architect. When in doubt, just describe the goal: the skills' activation rules make this decision for you.

Prompt ideas

Copy any of these, adapt the object names to your org, and send. Refer to components by the names used in this documentation: "Data Table", "Kanban", "Calendar", "Date Picker". The assistant resolves each name to the right component through the MCP server.

🆕 Add a component

Add an Avonni Kanban of Opportunities grouped by stage to my screen flow, with a card action that opens the record.

Create a screen flow with an Avonni Calendar showing Events for the current user.

Add an Avonni Data Table of open Cases with a search bar to my screen.

What happens: the avonni-flow-components skill activates, looks up each component's real properties and interactions through the MCP server, and adds the configured component to your flow file.

✏️ Update a screen

Change the Kanban grouping from stage to owner.

Add pagination to the Data Table on my second screen.

Set the Date Picker's default value to today.

What happens: the skill reads your flow file, checks the component's options through the MCP server, and applies the change.

⚡ Wire interactions

Interactions connect a component event to an action, with no extra flow logic.

Move the user to the next screen when they pick a record.

Open a confirmation modal before deleting the selected records.

Fire confetti when the user submits the final screen.

What happens: the skill wires the right interaction types (Flow Navigation, Open Confirmation Modal, Fire Confetti) with their settings, and it knows the prerequisites, for example that Fire Confetti requires the Interaction Service component on the same screen.

🧩 Complete use case

Create a screen flow for booking appointments, and a Dynamic Component with a button that launches it.

This spans two artifact types, so avonni-architect activates. It plans the architecture, builds the flow first, then builds the Dynamic Component with its button wired to launch that flow.

What happens: one request, several artifacts, all wired together in dependency order.

What to expect

A typical session runs in three steps:

1

Lookup

The assistant queries the MCP server for the components involved, with their properties, interactions, and styling options.

2

Plan

It proposes an approach and may ask clarifying questions. For multi-artifact requests, it lays out the artifacts in dependency order.

3

Generate

It creates or updates your flow file. Review it, deploy it with your usual process, then open the flow in Flow Builder to check the screen and activate it.

Nothing is deployed to your org: deployment and activation stay in your hands. See Limitations & FAQ.