# Triggering an agentic workflow

Here, we break down the entire agentic flow—from when a user types a query to when the workflow is executed and completed using AI agents in Tellius. It applies universally to all Agentic Workflows regardless of use case (e.g., revenue analysis, product discontinuation, churn prediction etc.).

{% hint style="danger" %}
To trigger a user-defined workflow or let Kaiya plan and automate the analysis step by step, click the **Deep Insight** button.
{% endhint %}

### 1. User initiates query

When the user interacts with Kaiya by entering a natural language query in the chat interface, it is evaluated in real time against a list of triggers configured for published agentic flows.

Each agentic flow contains one or more trigger phrases defined during workflow creation in Composer. These triggers allow Kaiya to intelligently map user input to the correct workflow, even if the phrasing is not exact. Trigger variations are supported, meaning you can ask a question in different ways, and Kaiya will still recognize the intent.

### 2. Kaiya maps query to a trigger

If a match is found, Kaiya responds with the name and description of the matching agentic flow, and prompts user confirmation to initiate the workflow execution. This user confirmation ensures control and transparency before any backend processing begins.

Choose “**Yes**” to continue, else select “No” to abort the workflow exection.

<figure><img src="https://content.gitbook.com/content/8GaK1h3pmgbR63x0ftET/blobs/HqkQMejKOZ0Fcq7O99FQ/image.png" alt="" width="563"><figcaption><p>Matching the trigger with the workflow</p></figcaption></figure>

### 3. Workflow initialization

Upon confirmation, Kaiya activates the Planner Agent. The Planner Agent's job is to:

* Interpret the workflow's objective
* Break it into logical, executable steps
* Identify which agents need to be involved
* Sequence these agents correctly

<figure><img src="https://content.gitbook.com/content/8GaK1h3pmgbR63x0ftET/blobs/R0zXlsUZ243eY1AnUqd0/image.png" alt="" width="563"><figcaption><p>Supervision Agent working behind the scenes</p></figcaption></figure>

The Planner Agent acts as the orchestrator or mission control of the entire agentic flow. It ensures the right agents are activated at the right time in the right order.

### 4. Squad of AI Agents

A message appears as follows: “*Squad of AI Agents... Finding the best agent to execute next step.*” This indicates that Kaiya is identifying and activating the most suitable agent for the task at hand. The agents activated depend entirely on the workflow steps defined in **Composer**. Agents begin executing each workflow step , using the logic defined in **Composer**. Commonly involved agents include:

| <mark style="color:blue;">**Agent Name**</mark> | <mark style="color:blue;">**Role**</mark>                            |
| ----------------------------------------------- | -------------------------------------------------------------------- |
| Validation Agent                                | Checks query structure, permissions, and data readiness              |
| Planner Agent                                   | Breaks down requests, assigns agent tasks, sequences execution       |
| Data Prep Agent                                 | Filters, joins, and loads relevant data from selected Business Views |
| Visualization Agent                             | Generates appropriate visuals (charts, tables, graphs)               |
| Insights Agent                                  | Performs root cause analysis, trend detection, and pattern mining    |
| Summary Agent                                   | Converts insights into plain-language narratives and summaries       |
| Knowledge Graph Agent                           | Maps relationships, finds entity connections, powers recommendations |

Each of these agents has a specific, modular purpose, and they are invoked only if required by the defined step logic.

<figure><img src="https://content.gitbook.com/content/8GaK1h3pmgbR63x0ftET/blobs/pE2quuRGzM8MuXiwMS5M/image.png" alt="" width="563"><figcaption><p>Analytic Agent working behind the scenes</p></figcaption></figure>

Conditional logic and dependencies between steps are respected. Prompts for additional user input (e.g., filters, time periods, dimensions) may be triggered dynamically. This modular structure enables Kaiya to adapt workflows based on data state, user interaction, or complexity of analysis.

### 7. Result generation

Once the agentic workflow completes execution, visuals, summaries, and insights are presented back to the user. Responses appear conversational but are powered by structured backend analysis.

* Charts and graphs (auto-generated)
* Tabular data&#x20;
* Root cause explanations
* Text summaries with recommendations
* Drill-down links or options

<figure><img src="https://content.gitbook.com/content/8GaK1h3pmgbR63x0ftET/blobs/d8BC8LwITwQtprRZrKC1/Untitled%20design.gif" alt="" width="563"><figcaption><p>Result generation</p></figcaption></figure>

### 8. Post-execution actions

* Ask follow-up questions to go deeper
* Share results or trigger a different workflow
* Request variations or filtered views of the current output

<figure><img src="https://content.gitbook.com/content/8GaK1h3pmgbR63x0ftET/blobs/eg9zGCROVPfGh5Q8vFzD/image.png" alt="" width="563"><figcaption><p>Post-execution actions</p></figcaption></figure>