Tellius
  • 🚩Getting Started
    • 👋Say Hello to Tellius
      • Glossary
      • Tellius 101
      • Navigating around Tellius
    • ⚡Quick Start Guides
      • Search
      • Vizpads (Explore)
      • Insights (Discover)
    • ✅Best Practices
      • Search
      • Vizpads (Explore)
      • Insights (Discover)
      • Predict
      • Data
    • ⬇️Initial Setup
      • Tellius architecture
      • System requirements
      • Installation steps for Tellius
      • Customizing Tellius
    • Universal Search
    • 🏠Tellius Home Page
  • Kaiya
    • ♟️Understanding AI Agents & Agentic Flows
      • Glossary
      • Composer
      • 🗝️Triggering an agentic workflow
      • The art of possible
      • Setting up LLM for Kaiya
    • 🤹Kaiya conversational AI
      • ❓FAQs on Kaiya Conversations
      • Triggering Insights with "Why" questions
      • Mastering Kaiya conversational AI
  • 🔍Search
    • 👋Get familiar with our Search interface
    • 🤔Understanding Tellius Search
    • 📍Search Guide
    • 🚀Executing a search query
      • Selecting a Business View
      • Typing a search query
      • Constructing effective search queries
      • Marketshare queries
    • 🔑Analyzing search results
      • Understanding search results
      • Search Inspector
      • Time taken to execute a query
      • Interacting with the resulting chart
    • 📊Know your charts in Tellius
      • Understanding Tellius charts
      • Variations of a chart type
      • Building charts from Configuration pane
      • List of chart-specific fields
      • Adding columns to fields in Configuration pane
      • Absolute and percentage change aggregations
      • Requirements of charts
      • Switching to another chart
      • Formatting charts
      • Advanced Analytics
      • Cumulative line chart
    • 🧑‍🏫Help Tellius learn
    • 🕵️‍♂️Search history
    • 🎙️Voice-driven search
    • 🔴Live Query mode
  • 📈Vizpads (Explore)
    • 🙋Meet Vizpads!
    • 👋Get familiar with our Vizpads
    • #️⃣Measures, dimensions, date columns
    • ✨Creating Vizpads
    • 🌐Applying global filters
      • Filters in multi-BV Vizpads
      • Filters using common columns
    • 📌Applying local filters
    • 📅Date picker in filters
      • Customizing the calendar view
    • ✅Control filters
      • Multi-select list
      • Single-select list
      • Range slider
      • Dropdown list
    • 👁️Actions in View mode
      • Interacting with the charts
    • 📝Actions in Edit mode
      • 🗨️Viz-level actions
    • 🔧Anomaly management for line charts
      • Instance level
      • Vizpad level
      • Chart level
    • ⏳Time taken to load a chart
      • Instance level
      • Vizpad level
      • Chart level
    • ♟️Working with sample datasets
    • 🔁Swapping Business View of charts
      • Swapping only the current Vizpad
      • Swapping multiple objects
      • Configuring the time of swap
    • 🤖Explainable AI charts
  • 💡Insights (Discover)
    • 👋Get familiar with our Insights
    • ❓Understanding the types of Insights
    • 🕵️‍♂️Discovery Insights
    • ➕How to create new Insights
      • 🔛Creating Discovery Insight
      • 🔑Creating Key Driver Insights
      • 〰️Creating Trend Insights
      • 👯Creating Comparison Insights
    • 🧮The art of selecting columns for Insights
      • ➡️How to include/exclude columns?
  • 🔢Data
    • 👋Get familiar with our Data module
    • 🥂Connect
    • 🪹Create new datasource
      • Connecting to Oracle database
      • Connecting to MySQL database
      • Connecting to MS SQL database
      • Connecting to Postgres SQL database
      • Connecting to Teradata
      • Connecting to Redshift
      • Connecting to Hive
      • Connecting to Azure Blob Storage
      • Connecting to Spark SQL
      • Connecting to generic JDBC
      • Connecting to Salesforce
      • Connecting to Google cloud SQL
        • Connecting to a PostgreSQL cloud SQL instance
        • Connecting to an MSSQL cloud SQL instance
        • Connecting to a MySQL Cloud SQL Instance
      • Connecting to Amazon S3
      • Connecting to Google BigQuery
        • Steps to connect to a Google BigQuery database
      • Connecting to Snowflake
        • OAuth support for Snowflake
        • Integrating Snowflake with Azure AD via OAuth
        • Integrating Snowflake with Okta via OAuth
        • Azure PrivateLink
        • AWS PrivateLink
        • Best practices
      • Connecting to Databricks
      • Connecting to Databricks Delta Lake
      • Connecting to an AlloyDB Cluster
      • Connecting to HDFS
      • Connecting to Looker SQL Interface
      • Loading Excel sheets
      • 🚧Understanding partitioning your data
    • ⏳Time-to-Live (TTL) and Caching
    • 🌷Refreshing a datasource
    • 🪺Managing your datasets
      • Swapping datasources
    • 🐣Preparing your datasets
      • 🤾Actions that can be done on a dataset
      • Data Pipeline
      • SQL code snippets
      • ✍️Writeback window
      • 🧩Editing Prepare → Data
      • Handling null or mismatched values
      • Metadata view
      • List of icons and their actions
        • Functions
        • SQL Transform
        • Python Transform
        • Standard Aggregation
        • Creating Hierarchies
      • Dataset Scripting
      • Fusioning your datasets
      • Scheduling refresh for datasets
    • 🐥Preparing your Business Views
      • 🌟Create a new Business View
      • Creating calculated columns
      • Creating dynamic parameters
      • Scheduling refresh for Business Views
      • Setting up custom calendars
    • Tellius Engine: Comparison of In-Memory vs. Live Mode
  • Feed
    • 📩What is a Feed in Tellius?
    • ❗Alerts on the detection of anomalies
    • 📥Viewing and deleting metrics
    • 🖲️Track a new metric
  • Assistant
    • 💁Introducing Tellius Assistant
    • 🎤Voice-based Assistant
    • 💬Interacting with Assistant
    • ↖️Selecting Business View
  • Embedding Tellius
    • What you should know before embedding
    • Embedding URL
      • 📊Embedding Vizpads
        • Apply and delete filters
        • Vizpad-related actionTypes
        • Edit, save, and share a Vizpad
        • Keep, remove, drill sections
        • Adding a Viz to a Vizpad
        • Row-level policy filters
      • 💡Embedding Insights
        • Creating and Viewing Insights
      • 🔎Embedding Search
        • Search query execution
      • Embedding Assistant
      • 🪄Embedding Kaiya
      • Embedding Feed
  • API
    • Insights APIs
    • Search APIs
    • Authentication API (Login API)
  • ✨What's New
    • Release 5.4
      • Patch 5.4.0.x
    • Release 5.3
      • Patch 5.3.1
      • Patch 5.3.2
      • Patch 5.3.3
    • Release 5.2
      • Patch 5.2.1
      • Patch 5.2.2
    • Release 5.1
      • Patch 5.1.1
      • Patch 5.1.2
      • Patch 5.1.3
    • Release 5.0
      • Patch 5.0.1
      • Patch 5.0.2
      • Patch 5.0.3
      • Patch 5.0.4
      • Patch 5.0.5
    • Release 4.3 (Fall 2023)
      • Patch 4.3.1
      • Patch 4.3.2
      • Patch 4.3.3
      • Patch 4.3.4
    • Release 4.2
      • Patch 4.2.1
      • Patch 4.2.2
      • Patch 4.2.3
      • Patch 4.2.4
      • Patch 4.2.5
      • Patch 4.2.6
      • Patch 4.2.7
    • Release 4.1
      • Patch 4.1.1
      • Patch 4.1.2
      • Patch 4.1.3
      • Patch 4.1.4
      • Patch 4.1.5
    • Release 4.0
Powered by GitBook

© 2025 Tellius

On this page
  • AI Agents
  • Agentic Flow (also called: Agentic Workflow)
  • Agent Library
  • Composer

Was this helpful?

Export as PDF
  1. Kaiya
  2. Understanding AI Agents & Agentic Flows

Glossary

Detailed and structured glossary tailored for Kaiya AI Agents

AI Agents

Native, prebuilt analytical agents in Tellius designed to perform targeted tasks across the data-to-insight journey. These smart agents are reusable components that handle tasks like planning, data preparation, visualization, insight generation, and more. They are pre-trained and require no code to use. Each agent is optimized for a specific analytical function, and multiple agents can be combined to build Agentic Flows.

Validation Agent

This agent ensures the quality, safety, and feasibility of every query before it runs. It performs:

  • Structural validation of the input

  • Verification of user intent

  • Data availability checks

  • Permission enforcement

By catching issues early, the Validation Agent prevents invalid or unauthorized actions and ensures the workflow is built on reliable, clean foundations.

Planner Agent

The strategic coordinator of the workflow. When a user inputs a question or request, this agent:

  • Understands the task

  • Breaks it down into subtasks

  • Maps each task to the appropriate AI agent

  • Arranges the order of execution

Data Prep Agent

This agent handles data readiness. It automates tasks like:

  • Selecting relevant datasets

  • Applying filters and joins

  • Loading Business Views

  • Preparing structured inputs for downstream agents

It eliminates manual effort and ensures that each subsequent step in the workflow operates on clean, correct data.

Visualization Agent

This agent transforms data into visuals by:

  • Choosing the most appropriate visual format (charts, graphs, tables)

  • Generating visuals automatically based on context

  • Highlighting key trends and outliers visually

It helps users grasp complex data patterns at a glance without building visuals manually.

Insights Agent

A powerful analytical engine that dives deep into the data to:

  • Detect patterns, trends, and anomalies

  • Surface root causes and "why" explanations

  • Deliver contextual, multi-dimensional insights

This agent adds depth to dashboards by moving beyond surface-level metrics.

Summary Agent

This agent takes complex data and insights and converts them into plain-language summaries. It:

  • Extracts key takeaways

  • Generates concise narratives

  • Communicates the essence of analytical outputs quickly

Perfect for executive reporting or users who want the “story” behind the data without reading through charts or tables.

Knowledge Graph Agent

A relationship-mapping agent that:

  • Connects entities (e.g., products, customers, geographies)

  • Identifies hidden relationships and correlations

  • Powers smarter, context-aware recommendations

It enriches analysis by adding a layer of intelligence that understands the relationships behind data points.

Agentic Flow (also called: Agentic Workflow)

A complete, executable workflow composed of one or more AI Agents working together to perform a multi-step analytical task. Agentic Flows can automate:

  • Data validation

  • Data preparation

  • Visualization

  • Insight extraction

  • Narrative summarization

Agentic workflow steps can be defined using natural language, and the appropriate agents are orchestrated automatically. These flows are created in Composer, and can be saved, reused, and shared via the Agent Library.

Agent Library

A centralized workspace that stores and manages all Agentic Flows across the organization. It contains two sections:

  • Published Agents: These are fully configured, ready-to-use workflows available for execution.

  • Draft Agents: These are in-progress flows being built in Composer, not yet finalized or published.

Agentic flows can be edited, deleted, or duplicated from Agent Library.

Composer

A no-code development studio where you can create Agentic Flows using simple instructions in natural language. It enables business users, analysts, and data teams to build intelligent workflows without programming. Composer includes:

  • Name and Description: Start by naming the workflow and briefly describing its purpose.

  • Data Source: Connect and configure the data to be used in the workflow.

  • Steps: Each step is a natural language instruction that activates a specific agent.

  • Triggers: Define the phrases or questions that will initiate the flow. Triggers are customizable and flexible—you can set multiple variations to capture different ways you might phrase the same request. Example: For "Products to discontinue", you can set the variations "Which products should we stop selling?", "Drop candidates?", "Low-performing SKUs?".

PreviousUnderstanding AI Agents & Agentic FlowsNextComposer

Last updated 1 month ago

Was this helpful?

♟️
Agent Library