Chat

Conversational AI for quick questions and general assistance.

Overview

Chat provides a simple, conversational interface to AI. Use it for quick questions, brainstorming, writing assistance, and general help—no code or data connections required.

What Chat Does

Quick Answers

Ask questions and get immediate responses:

• Technical explanations
• Code snippets and examples
• Writing and editing help
• Research and summaries
• Problem-solving assistance

Conversation Context

Chat remembers your conversation:

• Reference earlier messages
• Build on previous answers
• Refine responses iteratively

Using Chat

Starting a Conversation

1. Launch Chat from the Hub
2. Type your message in the input field
3. Press Enter or click Send
4. AI responds in the chat window

Example Conversations

Get code help:

You: How do I read a CSV file in Python?

Chat: Here's how to read a CSV file using pandas:

import pandas as pd
df = pd.read_csv('your_file.csv')
print(df.head())

Brainstorm ideas:

You: I need to name a new analytics dashboard feature

Chat: Here are some naming ideas for your analytics dashboard:
- InsightHub
- DataPulse
- MetricsView
- AnalyticaLive
...

Get explanations:

You: Explain what a JOIN does in SQL

Chat: A JOIN combines rows from two or more tables based on
a related column between them...

When to Use Chat vs Other Tools

Features

Markdown Support

Chat formats responses with:

• Bold and italic text
• Code blocks with syntax highlighting
• Bullet points and numbered lists
• Tables when appropriate
• Headers for organization

Code Blocks

Code appears in formatted, copyable blocks:

# Example code is easy to copy
def hello():
    print("Hello, World!")

Conversation History

• Scroll up to see previous messages
• Context is maintained throughout the session
• Start a new conversation anytime

Tips for Better Results

Be Specific

Less effective: "Help with Python"
More effective: "How do I sort a list of dictionaries by a specific key in Python?"

Provide Context

"I'm building a Flask API and need to add authentication.
What's the simplest approach for JWT tokens?"

Iterate

Ask follow-up questions to refine answers:

You: How do I connect to PostgreSQL in Python?
Chat: [provides psycopg2 example]
You: Can you show the same thing using SQLAlchemy instead?
Chat: [provides SQLAlchemy example]

Request Formats

Ask for specific output formats:

• “Give me a bullet list of…”
• “Show this as a table…”
• “Provide a step-by-step guide…”
• “Give me just the code, no explanation”

Limitations

Chat is designed for general conversation and doesn’t:

• Access your files or workspace
• Connect to databases
• Execute code
• Browse the web

For those capabilities, use:

• Deep Data Agent for data and SQL
• Lab for running notebooks
• Agentic Browser for web tasks

Privacy

• Conversations are private to your session
• Chat doesn’t access your workspace files
• No conversation data is used for training