Tree chat & AI suggestions

Every node in the Tree has a Chat tab in its Blade — the side panel that opens when you click a node. This is where the AI Data Advisor surfaces suggestions for that specific node, and where you can ask the advisor questions about its reasoning.

If you skipped the advisor when you created your dataset, this is your second chance — the same suggestions surface here for any node in the Tree.

Opening the Chat

1. Open the Tree for a project.
2. Click any node — the Blade slides in.
3. Click the Chat tab.

What you’ll see

The Chat panel has two parts:

Suggestions list

The advisor’s recommendations for the current node — for example:

• Columns it suggests keeping (high signal).
• Columns it suggests dropping or flagging (low signal, likely noise).

Each suggestion is a card you can act on directly.

Apply suggestions

Click a suggestion card to apply it to the current node. RebelCore™ tracks applied suggestions so you don’t double-apply them — once applied, the card visibly changes state (e.g., greyed out / marked as applied).

Tip

Applying a suggestion changes how the node feeds into the agent — it shapes the labelled vector set that the agent eventually consumes. Think of it as curating a second time, with AI input.

Ask questions

A chat box at the bottom, with placeholder text “Ask about these suggestions…”. Type a natural-language question and the advisor responds.

Examples of useful questions:

• “Why did you suggest dropping internal_id?”
• “What would change if I applied the first three suggestions?”
• “Which columns are most important for inference here?”

The advisor responds in the conversation thread above the input.

What the chat won’t do

The chat is intentionally narrow. Its scope is explaining the suggestions and their filtering effects on this node — nothing else.

If you ask broader questions, you’ll get a response like:

“I can only explain these data suggestions and their filtering effects.”

For open-ended workflows on the data — running inference, building specs, asking analytical questions — use the RebelCore™ Agent instead. The agent works at the project level and can act on the whole vector set the Tree exposes.

A practical workflow

1. Open the Tree, click a spec.
2. Switch to Chat.
3. Read through the suggestions; apply the ones that match your intent.
4. Ask a follow-up question if a suggestion isn’t clear.
5. When the spec looks right, switch to Details and click Open in RebelCore™ Agent to act on it.