Normal User 👤 default

💬 General AI Chat

Ask questions, get coding help, or brainstorm analysis approaches. Supports audio speech input and output. Manage multiple conversations and switch between them. Copy responses with one click.

• Multi-turn conversations with AI models
• Select any configured AI provider and model
• Audio speech input/output for hands-free interaction
• Copy individual messages to clipboard

🗄️ AI Database Design

Connect a database and let the AI inspect its schema — tables, columns, foreign keys, and indexes. The AI will flag structural issues (missing indexes, data type concerns, normalization problems) and suggest improvements. When analysing MySQL databases, only tables from the connected database are shown (not server-wide).

• Inspect schema: tables, columns, FKs, indexes
• AI-generated structural analysis with severity ratings
• Category-tagged recommendations (performance, integrity, etc.)
• Conversational follow-up on each finding

🧹 AI Dataset Cleaning

Select a dataset and the AI will review column schemas — types, null counts, unique counts, and sample values — then suggest cleaning steps (handling missing values, fixing data types, normalizing text).

• Column schema overview with statistics
• AI-generated cleaning suggestions
• Review sample values before taking action
• Apply cleaning rules to your data

📊 AI Analysis Rules

Tell the AI what you want to learn from your dataset and it will propose analysis rules — statistical tests, aggregations, groupings — that you can incorporate into a recipe.

• Generate analysis approaches from natural language
• Rules you can preview before applying
• Save as repeatable recipes for future runs

📤 Upload CSV & Excel

Drag-and-drop CSV or Excel files. Configure delimiter, quote character, and encoding. Preview data before importing. The Workbench stores uploaded data in DuckDB for fast local analysis.

🔗 Connect Databases

Browse tables and views from your configured PostgreSQL or MySQL connections. Select specific columns to pull in. Define them as datasets for analysis. Your database credentials are stored per-user and never shared. MySQL connection testing is fully supported — test your MySQL credentials from the connection form.

📋 Dataset Browser

Search and filter all your datasets by source type (upload, table, view, virtual) and group visibility. View metadata, browse data snapshots, and manage column definitions. Trigger data preparation rules from here. Source types include virtual (AI-generated datasets with federated joins).

📓 Jupyter Notebook Import

Upload .ipynb files. The Workbench extracts DataFrame definitions, shows column info and row counts, and imports the resulting tables into your database. Great for bringing in analysis work from external tools.

🧠 Virtual Datasets

Chatbot-guided dataset creation. Connect to multiple databases, select tables and columns, and let the AI generate SQL with joins. Save the result as a virtual dataset for use in recipes and analysis.

📈 Data Visualizations

Create interactive Plotly charts — bar, scatter, line, pie, histogram, and more. Choose a visualization type, provide data as JSON or CSV, configure parameters, and render. Export charts as images for reports.

📋 Analysis Recipes

Build repeatable analysis workflows. A recipe bundles data preparation rules and analysis steps. Select a dataset, configure input columns, set filter conditions, add custom parameters, then reorder steps via drag-and-drop. Run the recipe now or save it for later — and get the same results every time on updated data. Recipes execute through the backend with full statistics and Plotly chart output. A Kill button appears while a recipe is running, and a Select All / Deselect All checkbox speeds up column selection.

📜 Recipe History

Track every execution of your recipes. See when they ran, on which dataset, and review the results. Compare runs over time as your data changes. View rendered charts and statistics alongside raw output.

👤 Profile

• Update your name and email
• Change your password
• Choose your preferred interface language (9 languages available)
• Toggle dark mode
• Subscribe to BCC registration emails
• View your group memberships and role badges

🗄️ Database Connections

• Add PostgreSQL or MySQL connections
• Test connections to verify they work
• Edit or delete saved connections
• Assign connections to groups for shared access
• Set read/write permissions per connection

🤖 AI Connections

• Add AI providers (Ollama, OpenAI-compatible)
• Configure endpoints, API keys, and models
• Test connections to verify they work
• Assign connections to groups
• All authenticated users can browse available AI providers and select from the list when creating a connection.