Secoda Docs
Get Started
  • Getting Started with Secoda
    • Secoda as an Admin
      • Deployment options
      • Sign in options
      • Settings
      • Connect your data
        • Define Service Accounts
        • Choose which schemas to extract
      • Customize the workspace
      • Populate Questions with FAQs
      • Invite your teammates
        • Joining & Navigating between Multiple Workspaces
      • Onboard new users
        • Onboarding email templates
        • Onboarding Homepage template
        • Training session guide
      • User engagement and adoption
        • Tips & Tricks to share with new users
    • Secoda as an Editor
    • Secoda as a Viewer
      • Introduction guide
      • Requesting changes in Secoda
  • Best practices
    • Setting up your workspace
    • Integrating Secoda into existing workflows
    • Documentation best practices
    • Glossary best practices
    • Data governance
    • Data quality
    • Clean up your data
    • Tool migrations using Secoda
    • Slack <> Questions workflow
    • Defining resources workflow
    • Streamline data access: Private and public teams workflow
    • Exposing Secoda to external clients
  • Resource Management
    • Editing Properties
      • AI Description Editor
      • Bulk Editing
      • Propagation
      • Templates
    • Resource Sidesheet
    • Assigning Owners
    • Custom Properties
    • Tags
      • Custom Tags
      • PII Identifier
      • Verified Identifier
    • Import and Export Resources
    • Related Resources
  • User Management
    • Roles
    • Teams
    • Groups
  • Integrations
    • Integration Settings
    • Data Warehouses
      • BigQuery
        • BigQuery Metadata Extracted
      • Databricks
        • Databricks Metadata Extracted
      • Redshift
        • Redshift Metadata Extracted
      • Snowflake
        • Snowflake Metadata Extracted
        • Snowflake Costs
        • Snowflake Native App
      • Apache Hive
        • Apache Hive Metadata Extracted
      • Azure Synapse
        • Azure Synapse Metadata Extracted
      • MotherDuck
        • MotherDuck Metadata Extracted
      • ClickHouse
        • ClickHouse Metadata Extracted
    • Databases
      • Druid
        • Druid Metadata Extracted
      • MySQL
        • MySQL Metadata Extracted
      • Microsoft SQL Server
        • Page
        • Microsoft SQL Server Metadata Extracted
      • Oracle
        • Oracle Metadata Extracted
      • Salesforce
        • Salesforce Metadata Extracted
      • Postgres
        • Postgres Metadata Extracted
      • MongoDB
        • MongoDB Metadata Extracted
      • Azure Cosmos DB
        • Azure Cosmos DB Metadata Extracted
      • SingleStore
        • SingleStore Metadata Extracted
      • DynamoDB
        • DynamoDB Metadata Extracted
    • Data Visualization Tools
      • Amplitude
        • Amplitude Metadata Extracted
      • Looker
        • Looker Metadata Extracted
      • Looker Studio
        • Looker Studio Metadata Extracted
      • Metabase
        • Metabase Metadata Extracted
      • Mixpanel
        • Mixpanel Metadata Extracted
      • Mode
        • Mode Metadata Extracted
      • Power BI
        • Power BI Metadata Extracted
      • QuickSight
        • QuickSight Metadata Extracted
      • Retool
        • Retool Metadata Extracted
      • Redash
        • Redash Metadata Extracted
      • Sigma
        • Sigma Metadata Extracted
      • Tableau
        • Tableau Metadata Extracted
      • ThoughtSpot
        • ThoughtSpot Metadata Extracted
      • Cluvio
        • Cluvio Metadata Extracted
      • Hashboard
        • Hashboard Metadata Extracted
      • Lightdash
        • Lightdash Metadata Extracted
      • Preset
        • Preset Metadata Extracted
      • Superset
        • Superset Metadata Extracted
      • SQL Server Reporting Services
        • SQL Server Reporting Services Metadata Extracted
      • Hex
        • Hex Metadata Extracted
      • Omni
        • Omni Metadata Extracted
    • Data Pipeline Tools
      • Census
        • Census Metadata Extracted
      • Stitch
        • Stitch Metadata Extracted
      • Airflow
        • Airflow Metadata Extracted
      • Dagster
        • Dagster Metadata Extracted
      • Fivetran
        • Fivetran Metadata Extracted
      • Glue
        • Glue Metadata Extracted
      • Hightouch
        • Hightouch Metadata Extracted
      • Apache Kafka
        • Apache Kafka Metadata Extracted
      • Confluent Cloud
        • Confluent Cloud Metadata Extracted
      • Polytomic
        • Polytomic Metadata Extracted
      • Matillion
        • Matillion Metadata Extracted
      • Airbyte
        • Airbyte Extracted Metadata
      • Informatica
        • Informatica Metadata Extracted
      • Azure Data Factory
        • Azure Data Factory Metadata Extracted
    • Data Transformation Tools
      • dbt
        • dbt Cloud
          • dbt Cloud Metadata Extracted
        • dbt Core
          • dbt Core Metadata Extracted
      • Coalesce
        • Coalesce Metadata Extracted
    • Data Quality Tools
      • Cyera
      • Dataplex
        • Dataplex Metadata Extracted
      • Great Expectations
        • Great Expectations Metadata Extracted
      • Monte Carlo
        • Monte Carlo Metadata Extracted
      • Soda
        • Soda Metadata Extracted
    • Data Lakes
      • Google Cloud Storage
        • GCS Metadata Extracted
      • AWS S3
        • S3 Metadata Extracted
    • Query Engines
      • Trino
        • Trino Metadata Extracted
    • Custom Integrations
      • File Upload
        • CSV File Format
        • JSONL File Format
        • Maintain your Resources
      • Marketplace
        • Secoda SDK
        • Upload and Connect your Marketplace Integration
        • Publish the Integration
        • Example Integrations
      • Secoda Fields Explained
    • Security
      • Connecting via Reverse SSH Tunnel
      • Connecting via SSH Tunnel
      • Connecting via VPC Peering
      • Connecting via AWS Cross Account Role
      • Connecting via AWS PrivateLink
        • Snowflake via AWS PrivateLink
        • AWS Service via AWS PrivateLink
      • Recommendations to Improve SSH Tunnel Concurrency on SSH Bastion
    • Push Metadata to Source
  • Extensions
    • Chrome
    • Confluence
      • Confluence Metadata Extracted
      • Confluence best practices
    • Git
    • GitHub
    • Jira
      • Jira Metadata Extracted
    • Linear
    • Microsoft Teams
    • PagerDuty
    • Slack
      • Slack user guide
  • Features
    • Access Requests
    • Activity Log
    • Analytics
    • Announcements
    • Audit Log
    • Automations
      • Automations Use Cases
    • Archive
    • Bookmarks
    • Catalog
    • Collections
    • Column Profiling
    • Data Previews
    • Data Quality Score
    • Documents
      • Comments
      • Embeddings
    • Filters
    • Glossary
    • Homepage
    • Inbox
    • Lineage
      • Manual Lineage
    • Metrics
    • Monitors
      • Monitoring Use Cases
    • Notifications
    • Policies
    • Popularity
    • Publishing
    • Queries
      • Query Blocks
        • Chart Blocks
      • Extracted Queries
    • Questions
    • Search
    • Secoda AI
      • Secoda AI User Guide
      • Secoda AI Use Cases
      • Secoda AI Security FAQs
      • Secoda MCP Server
    • Sharing
    • Views
  • Enterprise
    • SAML
      • Okta SAML
      • OneLogin SAML
      • Microsoft Azure AD SAML
      • Google SAML
      • SCIM
      • SAML Attributes
    • Self-Hosted
      • Additional Resources
        • Additional Environment Variables
          • PowerBI OAuth Application (on-premise)
          • Google OAuth Application (on-premise)
          • Github Application (on-premise)
          • OpenAI API Key Creation (on-premise)
          • AWS Bucket with Access Keys (on-premise)
        • TLS/SSL (Docker compose)
        • Automatic Updates (Docker compose)
        • Backups (Docker compose)
        • Outbound Connections
      • Self-Hosted Changelog
    • SIEM
      • Google Chronicle
  • API
    • Get Started
    • Authentication
    • Example Workflows
    • API Reference
      • Getting Started
      • Helpful Information
      • Audit Logs
      • Charts
      • Collections
      • Columns
      • Custom Properties
      • Dashboards
      • Databases
      • Documents
      • Events
      • Groups
      • Integrations
      • Lineage
      • Monitors
      • Resources
      • Schemas
      • Tables
      • Tags
      • Teams
      • Users
      • Questions
      • Queries
      • Getting Started
      • Helpful Information
      • Audit Logs
      • Charts
      • Collections
      • Columns
      • Custom Properties
      • Dashboards
      • Databases
      • Documents
      • Events
      • Groups
      • Integrations
      • Lineage
      • Monitors
      • Resources
      • Schemas
      • Tables
      • Tags
      • Teams
      • Users
      • Questions
      • Queries
  • FAQ
  • Policies
    • Terms of Use
    • Secoda AI Terms
    • Master Subscription Agreement
    • Privacy Policy
    • Security Policy
    • Accessibility Statement
    • Data Processing Agreement
    • Subprocessors
    • Service Level Agreement
    • Bug Bounty Program
  • System Status
  • Changelog
Powered by GitBook
On this page
  • Overview
  • Enabling Secoda AI
  • Charting
  • AI Settings
  • Governance
  • Tools
  • Custom Instructions
  • Personas
  • Memory
  • Additional documentation

Was this helpful?

  1. Features

Secoda AI

This page will go over the Secoda AI functionality.

Last updated 28 days ago

Was this helpful?

"LLM provider" refers to OpenAI or Anthropic. Workspace admins can choose which provider they use in their AI settings.

Overview

The Secoda Secoda AI enhances your data stack by providing a powerful chat interface that allows anyone in your organization to retrieve data insights.

Secoda AI is powered by OpenAI and Anthropic's API. Workspace admins currently have the choice of using OpenAI's GPT-4o model or Anthropic's Claude Sonnet 3.5 model. Read more about Secoda AI's security posture in our Secoda AI Security FAQs.

Secoda's AI can help you with documentation, query building, institutional knowledge discovery.

Enabling Secoda AI

By default, Secoda AI is disabled. To activate it:

  1. Navigate to > AI.

  2. Toggle on the Secoda AI.

  3. Once enabled, the Secoda AI will appear in the left-hand menu of your workspace.

Charting

Secoda AI Charting enables users to create data visualizations through natural language prompts, making data insights accessible without requiring SQL or charting expertise.

Secoda AI Charting allows users to describe the charts they want in plain English (e.g., "Show monthly revenue trends"). The system analyzes your data to suggest appropriate visualization types and provides contextual explanations of insights.Users can refine visualizations through conversational follow-ups to adjust chart types, add trendlines, or change grouping parameters.

Simply navigate to the Secoda AI interface, ask a question involving data visualization, and request a chart based on SQL results. The feature integrates seamlessly with the SQL query functionality, allowing you to save both queries and their visualizations.For best results, be specific about metrics, dimensions, and time periods in your requests. The AI will guide you through creating the most effective visualization for your data story.

AI Settings

Admins can customize AI settings to align with workspace preferences and security protocols:

Governance

AI Governance in Secoda empowers organizations to control the data accessed by AI, enhancing security and data relevance.

Key Features:

  • Customizable Filters: Admins can specify which resources are accessible to the AI by setting inclusive or exclusive filter rules. This ensures that AI interactions are confined to appropriate datasets.

Benefits:

  • Enhanced Data Security: Restricts AI access to sensitive or non-production data, minimizing potential exposure.

  • Improved Data Relevance: Focuses AI interactions on current and verified data, increasing the accuracy and reliability of the insights provided.

By implementing these rules, Admins can tailor AI capabilities to fit organizational needs and compliance requirements, ensuring that only relevant and secure data is queried.

Tools

  • Run SQL: Executes SQL queries within Secoda to support doing analysis.

  • Add memory: Saves personal preferences for an individual user, for example, language preference.

  • Get Secoda docs: Searches https://docs.secoda.co for any product related questions.

To ensure security and relevance:

Team-Based Replies: Our AI strictly adheres to Team-based data access permissions. If a user asks about resources from a Team that they are not a part of, the AI will not return any results.

Query Execution Requirements: The AI will only execute a query if both of the following conditions are met:

  1. run_sql is toggled on in the AI settings.

  2. The user asking the question has Query access for the specific integration, which can be managed by admins in the Integration Permissions settings.

This ensures that only authorized users can run queries on sensitive or critical data, maintaining control over data access.

Custom Instructions

Chat

Admins can set specific instructions for the AI to follow, enhancing control and relevance.

Some examples that we've seen work well:

  • Do not index on resources tagged with "archived" or "deprecated" or "stale".

  • Only provide results on "Verified" resources.

  • Only provide results on Published resources - do not include resources that are still in Draft.

  • Only reference tables and views from the production analytics schema in Snowflake, never use data from the RAW database.

By default, both Published and Draft resources are included in Secoda AI responses. This can be controlled using the custom instructions to restrict this to only Published resources, for example.

Descriptions

Admins are able to define custom instructions to the AI Description Editor so that you can define documentation standards and a format for it to follow.

Some examples that we've seen work well:

  • Add "AI-Generated" to the end of each description added, to indicate to users that a human didn't come up with this definition.

  • Do not reference the database, schema, table information in the description (this information is obvious in Secoda)

  • Do not use full, wordy sentences. Be brief and include only the necessary facts.

  • Descriptions should be concise and not editorialized. Do not describe the data as 'essential' or 'critical'; only describe the contents.

  • All tables and columns are related to insurance. Keep this in mind when generating descriptions.

Personas

Secoda AI Personas are customizable assistants tailored to specific roles, aligning with team workflows. They access relevant data, support unique instructions, and integrate with tools like Slack. Personas can be personalized with names, icons, and permissions, ensuring the right people use the right tools for enhanced productivity.

Configuration

Each Persona can be configured with the following details:

  • Name: Give your Persona a unique name.

  • Icon: Select an icon that represents the Persona.

  • Description: Add a brief description of the Persona's purpose.

  • Custom Instructions: Set specific instructions for the Persona's role and tasks.

  • Resource Filters: Limit the Persona’s access to certain datasets or resources.

  • Team Access: Control which teams or users can access this Persona.

Once your Persona has been created, you can switch between Personas on the Secoda AI page. After that you can chat with your Secoda AI Persona similar to how you chat with Secoda AI.

Memory

Secoda AI Memory allows Secoda AI to remember important details about your preferences and working style across conversations. This personalization feature helps make interactions more efficient and contextual over time.

Enabling AI Memory

AI Memory can be enabled by workspace administrators through the AI settings page:

  • Navigate to Settings > AI

  • Ensure "Use Secoda AI" is enabled

  • Look for the Personalization section

  • Click "Manage Memories" to view and manage stored memories

Managing Memories

You can view and manage all memories that Secoda AI has stored:

  • Click "Manage Memories" in the AI settings

  • View a list of all stored memories

  • Delete any memories you no longer want the AI to remember

How It Works

When you interact with Secoda AI, it automatically identifies and stores important details about your preferences and working patterns. These memories are then used to:

  • Provide more personalized responses

  • Reduce repetitive questions

  • Maintain context across different conversations

  • Tailor recommendations to your specific needs

For example, if you frequently work with specific databases or dashboards, the AI will remember these preferences and prioritize them in future interactions.

Additional documentation

This guide ensures that Admins are equipped to optimize the AI Assistant within their Secoda environment, driving efficient and secure data operations across the organization.

Secoda AI Assistant is only available for Version 7.0.0 and up.

Consistent Configuration: The filter rules for AI are aligned with , ensuring a unified approach to data governance across the platform.

AI Governance Filters

To create an AI Persona, open the and expand the "Personas" section and click the "Create Persona" button.

those used on the Search and Catalog pages
AI settings
Secoda AI User Guide
Secoda AI Use Cases
Secoda AI Security FAQs
Settings