My Workspace

My Workspace in askEdgi provides a centralized environment for ingesting data, connecting catalog assets, organizing workspace content, and performing AI-assisted discovery and analysis. It unifies data ingestion, intelligent exploration, live data access, and automated insights, enabling users to interact with structured and file-based data, discover patterns, and build reusable analytical workflows within a scalable workspace.

The workspace interface supports clear separation between ingested data and live external sources, improved search and navigation, and enterprise-ready data management across uploaded files and catalog assets.

Interface Overview

The My Workspace interface consists of:

• Data ingestion controls for uploading files and adding catalog assets

• Structured Data Objects sections for Imported Objects and Live Sources

• Unified search across workspace content

• AI-driven exploration and chat workflows

• Right-side dynamic panel for previews, outputs, and conversations.

Data Ingestion Controls

File Upload

• Initiate File Selection

  • Navigate to the My Workspace interface.

  • Select the Files option to open the upload modal window.

    
• Execute File Transfer

  • Utilize either of the following methods:

    • Drag and drop supported files directly into the designated area.

    • Select the 'Browse to Upload' button to open the system file browser, then choose and confirm the file for upload.

      
• Complete Upload Process

  • The system validates file format and size automatically.

  • Once validation is complete, the file appears in the workspace data list, ready for analysis.

Supported File

Parameter	Requirement
Accepted Formats	CSV, PQT, XLSX, JSON
Maximum Capacity	1 GB per file

The modal window remains active during file processing to provide real-time upload status.

Catalog Integration in askEdgi

askEdgi enables users to add catalog data objects and supported file-based datasets directly into the workspace, ensuring consistent ingestion behavior across catalog and upload workflows.

• Initiate Catalog Selection

  • Navigate to the My Workspace interface

  • Select the + Catalog option to enable the Add Objects to Workspace modal.

    
  • This interface allows users to discover, filter, and select cataloged data assets as well as supported file uploads available through the Data Catalog.

• Browse and Select Catalog Assets The Add Objects to Workspace window displays all crawled, indexed, and permissioned catalog assets, including supported file-based datasets.

  
• Users can locate assets using either of the following methods:

  • Use the search bar or filtering options to quickly find specific catalog objects or file-based datasets. File types such as CSV, PQT, XLSX, and JSON.

  • Select Explore Resources to navigate to the Data Catalog interface, where users can browse catalog folders and datasets.

• Select one or more desired assets using the checkbox selection control.

• Click the + Add button to confirm and ingest the selected objects into the workspace.

• Selected items become available for analysis, discovery, AI conversations, and downstream workflows without requiring duplicate uploads.

Supported File Types from Data Catalog

• Users can add all file formats supported by askEdgi uploads directly from the Data Catalog widget, including:

  • CSV

  • PQT

  • XLSX

  • JSON

Data Objects Organization in My Workspace

Imported Objects

Imported Objects represent workspace-ingested data, including:

• Files uploaded through Upload

• Objects added from Catalog

• Outputs generated through recipes

These objects:

• Are stored inside the workspace engine

• Support organization into folders

• Can be moved within the Imported Objects section

• Are fully available for search, discovery, transformation, and AI analysis

Objects cannot be moved to Live Sources, ensuring ingestion integrity.

Live Sources

Live Sources represent external connections that are not ingested into the workspace.

These sources:

• Are queried live at runtime

• Remain read-only external references

• Do not support folder creation or object movement

• Cannot be moved into Imported Objects

This maintains a clear separation between stored workspace data and real-time external systems.

Unified Search Across Workspace Content

A single search bar under Data Objects enables scalable search across:

• Imported Objects

• Live Sources

• Workspace tables

• Files

• Folders

• Chats

• Live connections

Access to catalog assets depends on the organization’s metadata governance and access control settings. Non-permissioned datasets remain hidden from view.

Catalog-linked datasets maintain metadata lineage and can be referenced directly in AI analysis or recipes without duplicating data.

Copy Functionality for Workspace Objects and Data

askEdgi provides copy capabilities for both workspace objects and data values to enable quick reuse during analysis and prompt construction. The behavior is aligned with Data Catalog to ensure consistency in interaction patterns.

Object-Level Copy

Workspace objects support direct copying of object names from the object list.

• A copy icon is displayed adjacent to the object name

• The interaction mirrors Data Catalog behavior in placement and tooltip

• The copied value represents the exact object identifier used in prompts

This functionality is available across all workspace object types, including:

• Catalog tables

• Non-catalog tables

• AI-generated datasets

• Uploaded files

Data-Level Copy

Tabular data within askEdgi supports copy actions for cell-level values, particularly for complex or extended content.

Copy functionality is available for:

• JSON values

• Long text content

Depending on the data representation, the copy can be accessed through:

• Inline hover action within the row, or

• A copy option within the expanded (Read More) view

The copied output preserves the complete value and formatting without truncation.

Interaction Behavior

• Copy actions follow the existing Data Catalog interaction model

• No additional menus or custom behaviors are introduced

• Copy actions are available only where relevant, based on data type and content length

• Copy interaction does not conflict with other object-level or row-level actions

Confirmation

• On successful copy, a confirmation is shown using a tooltip or toast (e.g., “Copied to clipboard”)

Data Type Considerations

• Copy support is enabled for structured and long-form textual data

• Support is extended to applicable data types where full value visibility is required

• Certain simple data types may not expose explicit copy actions if direct selection is sufficient.

Tooltip for Object Source Identification

To improve clarity in My Workspace, tooltips for uploaded or added objects now display the fully qualified object name in the format:

connection.schema.object.

This helps users quickly identify the original data source when multiple connections contain similar table names.

Functionality

• Tooltip displays the connection name, schema name, and object name.

• Applies only to tooltip display - no impact on recipe ingredients or underlying object mapping.

• Enhances usability when working across multiple data connections.

Retry Upload for Failed Objects in My Workspace

askEdgi My Workspace supports uploading data objects from files and the Data Catalog. To improve resilience against temporary failures such as network interruptions or system timeouts, askEdgi now provides a Retry Upload option for failed ingestion attempts.

This enhancement eliminates the need to delete and re-add failed uploads, saving time and reducing repeated effort - especially for large datasets.

Upload Failure Handling Behavior

When an object upload fails in My Workspace, the system marks the object with a Failed status and exposes a Retry Upload action.

Common Failure Scenarios

• Network interruptions

• Temporary connectivity issues

• Large dataset upload timeouts

• System or service disruptions

Retry Upload Action

When an Upload Fails

• The object status displays Failed

• A Retry Upload button or icon appears next to the failed object

• Users can retry without deleting or re-adding the object

Executing a Retry Upload

Steps to Retry a Failed Upload

1. Navigate to askEdgi > My Workspace

2. Locate the object with status Failed

3. Select the Retry Upload action next to the failed object

1. The system re-attempts ingestion, either:

   1. Resuming from the last known progress (if supported), or

   2. Restarting the upload gracefully

2. Upload progress is updated in real time

3. On success, the object becomes Available for Analysis

System Behavior During Retry

If Retry Succeeds

• Upload completes successfully

• Object status updates to Ready

• Object becomes available for:

  • Discovery

  • Analysis

  • AI Chat

  • Recipes

  • Downstream workflows

If Retry Fails Again

• Status remains Failed

• The user can retry again or choose to delete the object

• The failure reason remains visible for troubleshooting

Global Search Across Workspace in askEdgi

The askEdgi search feature provides a unified interface for locating workspace assets, including data objects, folders, files, live connections, and previous chat interactions. This enhancement enables faster discovery across multiple content types while maintaining clear navigation and consistent behavior. Search results are grouped logically and support seamless redirection to the relevant view, improving efficiency and reducing time spent browsing the workspace.

Executing a Data Object Search

1. Navigate to the top section of the My Workspace panel where the primary navigation icons are located.

2. Select the Search icon to open the unified search panel.

3. View the list of recent items, grouped under time-based headers such as Yesterday and Older.

4. Enter the name of a data object, folder, file, live source, or chat in the search field.

5. Review the consolidated results list, where different result types are visually distinguished using appropriate icons.

6. If a data object is selected, the corresponding object view opens in the workspace.

7. If a folder is selected, the right panel updates to display the folder contents.

8. If a chat is selected, the associated conversation opens for review or continuation.

Data Catalog - Workspace Projects Integration

This section explains the functional details of the Workspace integration within AskEdgi and its behavior across modules, including Projects, Data Catalog, Business Glossary, Data Stories, and Search Results.

Operational Framework

The AskEdgi Workspace operates as a personal project within the Projects module and receives data objects from multiple areas, including the Data Catalog, Business Glossary, Data Stories, and Search Results. Tables and files can be added to the workspace from the AskEdgi interface. Still, direct workspace management actions from other modules are governed by clear rules to ensure consistent behavior and data governance.

“My Workspace” functions as a default personal project with defined validations, icon behavior, access checks, duplicate checks, workspace limits, and visual indicators. Only supported object types, including tables and files, can be added to the workspace. Other object types, such as glossary terms and data stories, remain restricted to standard projects.

Feature Details

1. Projects List View

Field	Behavior
Project Type	It will be displayed as My Workspace
Description	Non-editable to maintain workspace integrity

1. Data Catalog List View

Object Type	Workspace Icon Behavior
Tables and Files	Workspace icon visible
All other object types	The icon appears greyed out to indicate restriction

Manage Project navigation

• Log in as an Administrator.

• Navigate to the Data Catalog module from the main application menu.

• Select one or more data objects from the list.

• Click on the Nine-Dot menu.

• Select the Manage Projects.

• Click Add to Project.

• The system displays the list of eligible projects based on the selected object types.

• Choose a target project from the displayed list.

• The system validates duplicate entries, data access, and workspace limits.

• The system displays the relevant success or validation message.

• Data objects where the user has minimum Data Read access permission are added to the selected project.

Validation rules for adding to My Workspace

Validation Type	System Behavior	Message
Duplicate Check	If the object already exists, it is skipped	Some table(s) or file(s) already exist in your workspace and will not be added again
Mixed Duplicate and New	Some exist, and some are new	X of the selected tables or files already exist in your workspace. The remaining Y have been added successfully
Access Check	If the user does not have minimum Data Read access, the object is not added to the workspace.	X of Y data objects were not added due to access permission. Error message displayed.
Workspace Limit	Workspace limit reached	X of Y objects added to the workspace. Workspace has reached its limit of N tables or files. Please remove some objects before adding new ones.

Connector availability is validated before adding objects to ensure AskEdgi access readiness

3. Data Catalog Summary View

Add to Project

Selected Object Types	System Functionality
Only non-table or file objects	My Workspace is not displayed when Add to Project is clicked
Only tables or files	My Workspace displayed

Validation

Messages match those shown in Data Catalog List View

Examples

The selected table(s) or file(s) already exist in your workspace and will not be added again.

Workspace limit exceeded: Workspace has reached its limit of X tables or files. Please remove some objects before adding new ones.

4. Business Glossary, Data Stories, and Impact Analysis

Add to Project

Condition	System Functionality
Default Project is My Workspace	Only tables and files are supported
Business Glossary Terms and Data Stories	Cannot be added to My Workspace
Alternate routes, including bulk selection	My Workspace is not shown

Icon

From the Business Glossary List View, the default project icon changes to a greyed-out state.

• Only data objects, including tables and files, are allowed in My Workspace.

• Glossary terms, Data Stories, and Impact Analysis items remain associated with standard projects.

5. Search Page Results

For Tables and Files

• My Workspace icon is displayed.

• Validation checks performed including

  • Duplicate check

  • Access check

  • Workspace limit check

For other object types

• The " Add to Project” button is greyed out.

askEdgi Workspace Health, Controls, and Upgrade Options

This section describes the required improvements to the AskEdgi Workspace to provide real-time visibility into system performance and the ability to take corrective actions when the workspace becomes slow or unresponsive.

Users experience situations where the AskEdgi Workspace becomes unresponsive or takes an extended time to load. The current interface does not display detailed workspace health information, and no recovery actions are available. Workspace stability, responsiveness, and management flexibility are critical for uninterrupted analysis and productivity.

The interface introduces health insights, session controls, and upgrade capabilities directly within the Workspace Status panel.

Workspace Status Interface:

• Click the Connected icon on the left side of the workspace. The workspace Status Interface will appear.

Feature Details

• Enhanced Workspace Status Interface The existing Workspace Status panel displays only the connection state and CPU utilization. The panel is expanded to include additional workspace management actions.

Workspace Status Options

Feature	Description	UI Placement
View Logs	Opens a modal with recent workspace logs including last N operations such as queries, uploads, joins, failures with timestamps and severity levels including info, warning, error	Displayed below the CPU Utilization bar
Restart	Restarts the workspace session. Clears DuckDB cache, reloads objects, and resets the state without removing uploaded files	Displayed beside the Logs button
Upgrade	Opens a modal or dropdown that offers workspace configuration upgrades including table limits, memory allocation, CPU quota. Initiates backend provisioning workflow	Displayed below the CPU Utilization

These actions provide transparency, control, and scalability within the workspace environment.

Force Restart Mechanism

The Reload action performs a controlled restart of the DuckDB session.

• On the Workspace status interface, click the “Reload” button. The Reload Container pop-up will appear.

• On the Reload Container pop-up, click the Reload Container button.

System Functionality

• Gracefully terminates the current DuckDB session

• Clears temporary workspace cache

• Reloads workspace metadata

• Displays a confirmation prompt

Completion Toast

• Workspace reloaded successfully

Restart actions do not remove files uploaded by the user.

Logs Management

A dedicated Logs Modal provides operational history for diagnostics.

• On the Workspace status interface, click the “View Logs” button.

• The logs pop-up will appear.

  

Logs assist in identifying performance issues and operational failures.

Upgrade Mechanism

The Upgrade option allows users to increase workspace capacity when limits are reached.

• Opening the Upgrade modal displays available configuration enhancements

• Selecting a container applies an upgrade to the workspace

• The upgrade is chargeable to the end user

Upgrades adjust workspace performance factors such as storage, table capacity, memory, and processing power.

Workspace Upgrade Steps

1. On the Workspace status interface, click the “Upgrade Now” button.

1. The Upgrade modal appears, displaying available container options.

2. Select the required container type: Standard, Medium, or Large.

1. Click the Select button to apply the chosen upgrade.

2. A Workspace upgrade initiated message pop-up appears, confirming the action.

Visual and UX Enhancements

The Workspace Status section includes animated indicators to reflect the live state of the workspace.

Indicator	Description
🟢 Connected	Workspace is active and available
🟠 Restarting…	Workspace is in restart or reload mode
🔴 Disconnected	Workspace is unavailable or failed to load

These indicators improve awareness of workspace responsiveness and system health.

Context Focus Selection

The Context Focus Selection feature enables targeted analysis by allowing users to pin specific workspace objects. This action directs the AI assistant to reference the selected items during interactions. The focused context remains persistent across sessions and supports multi-object analysis when multiple items are pinned.

Initiate Analysis Focus

• Locate the pin icon labeled "Pin to focus your analysis" adjacent to each file or data catalog object within the workspace.

• Select the pin icon for each relevant item to focus analysis on that specific dataset.

  

Execute Context Limitation

• The AI chat system automatically detects all pinned items.

• The assistant restricts its analysis exclusively to the selected objects.

• All subsequent queries and operations reference only the pinned dataset.

When multiple items are pinned, the AI assistant performs cross-object analysis and identifies relationships within the selected dataset. The focus remains active until manually cleared by deselecting all pinned items.

Folder Structure

The Folder Structure feature in askEdgi Workspace allows efficient organization of tables, files, and other objects. It enables logical grouping, simplifies navigation, and supports workspace management by allowing actions at both the object and folder levels. This functionality enhances workspace usability and provides a scalable foundation for managing various assets in a structured manner.

Objects must be successfully added to the workspace before they can be moved into folders.

Folder Creation

Folders can be created inside the workspace and assigned custom names.

Naming Conventions:

• Each folder name must be unique.

• Maximum length: 256 characters

• Minimum length: 1 character (empty spaces are not valid)

• Allowed characters: Letters, numbers, spaces, and special characters _ (underscore), - (hyphen), . (period), () (parentheses), [] (square brackets), @ (at sign), and # (hashtag).

Steps to Create a Folder

1. Navigate to askEdgi > Workspace.

2. Click the three-dot menu beside My Workspace Search.

3. Select Create a Folder.

1. Enter the desired folder name.

2. Click the tick mark icon to save and create the folder.

Object Management within Folders

Moving Objects into a Folder

Objects such as tables or files can be added to folders using drag-and-drop or selection options.

Steps to Move Objects

1. Select one or more objects in the workspace.

2. Drag and drop them into the desired folder.

3. Objects are automatically sorted alphabetically within the folder.

Removing Objects from a Folder

Objects can be moved out of folders using drag-and-drop actions.

Steps to Remove Objects:

1. Hold and drag the object from the folder.

2. Release it outside the folder area.

3. The object will no longer belong to that folder but will remain in the workspace.

Moving Multiple Objects between Folders

1. Click the three-dot menu.

2. Select Move Objects.

1. The Move Objects pop-up modal will appear.

2. Choose the target folder.

3. Confirm the move in the pop-up confirmation window.

4. The selected objects will be moved to the specified folder.

Folder Deletion

Folders can be deleted from the workspace with confirmation.

Steps to Delete a Folder:

1. Hover over the folder name to display the Delete icon.

2. Click the Delete icon.

3. A confirmation pop-up will appear.

4. Confirm whether to delete the folder or move the contained objects to another folder.

Removing All Objects from Workspace

1. Click Remove All from Workspace.

2. Confirm the action in the pop-up window.

3. All folders and objects will be removed from the workspace.

Pinning

• When an object inside a folder is pinned, only that object is moved to the top of the folder.

• The entire folder does not move to the top of the workspace.

AI Prompt Validation, Execution Progress & Hover Insights

askEdgi now supports prompt validation with preview mode, execution progress tracking, and hover-based execution summaries to help users validate AI enrichment logic before processing large datasets.

This enhancement improves accuracy, transparency, performance efficiency, and user confidence when running AI enrichment workflows.

Validate Prompt (Preview Mode)

Users can validate AI prompts by executing AI enrichment on a small sample set (default: 5–10 rows).

Functionality

• Executes AI enrichment only on sample rows.

• Displays preview output within the enrichment modal.

• Allows users to edit prompts and re-validate before running full execution.

• Supported across Prompt Analysis, Sentiment Analysis, Intent Analysis, and all AI Enrichment functions.

• Preview does not modify actual table data.

Execution Control & Progress Tracking

Execution Behavior

• Full execution is initiated only after prompt validation (if enforcement is enabled).

• UI displays:

  • AI function name

  • Execution status

  • Row-level progress percentage (0–100%)

  • Live progress updates for multiple sequential enrichment functions

User Guidance

• If a user attempts execution without validation, the system displays: “Please validate your prompt before execution.”

Hover Card Details (Post-Execution Function Summary)

After execution, users can hover over the AI function badge to view a detailed summary card containing:

• Function type (Prompt Analysis, Sentiment Analysis, etc.)

• Input column(s)

• Output column

• Prompt text (if applicable)

• Total rows processed

• Success/failure record count

• Confidence or AI accuracy score (when available)

• Execution timestamp

• Processing duration

Purpose

• Improves auditability and traceability

• Helps users understand how AI outputs were generated

• Supports debugging and validation of enrichment logic

Thoughts Feature in askEdgi

askEdgi includes a Reasoning Transparency Panel, accessible through a Thoughts button on AI-generated responses. This feature provides visibility into how the system interprets user prompts, selects relevant data sources, applies policies, and constructs final answers.

The panel is designed to improve transparency, trust, explainability, and troubleshooting while ensuring that sensitive internal reasoning remains secure and sanitized.

Why Reasoning Transparency Matters

Users often need clarity on:

• How askEdgi interpreted a prompt

• Why certain tables, columns, or glossary terms were selected

• Which sources contributed to the answer

• How policies and permissions influenced the result

This feature helps:

• Reduce misunderstanding of AI responses

• Improve prompt refinement and analytical accuracy

• Support debugging for internal teams and support users

• Build confidence in data-driven insights

Accessing the Thoughts Panel

A Thoughts button appears next to every AI-generated response in askEdgi.

The button:

• Appears only for messages generated by the askEdgi AI agent

• Does not appear for user messages

• Opens a modal overlay when selected

The Thoughts icon visible only within the current active chat and disappears when the user switches to a different chat.

Thoughts Modal Content (MVP)

When opened, the modal displays structured and sanitized reasoning details in multiple sections.

1. Searching and Interpreted Intent

This section explains how askEdgi understood the user request, including:

• Interpreted user query

• Detected entities

• Classified intent such as aggregation, join, or comparison

This helps users understand how their prompt was parsed and interpreted.

2. Source Objects Used

This section lists all internal sources referenced while generating the response, including:

• Catalog objects accessed

• Glossary terms referenced

• Workspace tables and columns used

• Lineage paths traversed

• Metadata such as classifications, policies, and descriptions

Each source entry displays:

• Object name

• Object type

• Reason it was used

Sources are presented in a structured and organized list.

3. Reasoning Summary

This section provides a high-level summary of how the answer was formed, such as:

• Identifying entities and relevant metrics

• Matching columns using synonyms or metadata

• Applying access controls and governance rules

• Determining relevant joins or calculations

The reasoning is sanitized and summarized, ensuring the internal chain of thought is not exposed.

4. Execution Steps and Query Plan (If Applicable)

When relevant, the modal may include:

• Steps executed by the AI agent

• Query planning or execution context

• Applied filters and policy constraints

If query execution fails, the reasoning is displayed up to the failure point, along with a failure message.

Security and Sanitization Principles

The Thoughts panel does not expose the raw internal chain of thought.

Instead:

• Reasoning is presented in a safe, structured, and summarized format

• Sensitive internal logic remains hidden

• Only high-level, explainable insights are displayed

This ensures transparency without compromising system integrity or security.

Post Analysis Actions and Operational Execution

askEdgi supports operational actions that can be executed based on analysis results. These actions allow users to convert analysis output into governed execution within the platform.

The action framework connects analytical results with downstream operations such as Projects, Data Quality, Service Desk, Governance Catalog, tagging, ticket creation, task management, and data quality rule creation, while maintaining control, consistency, and audit tracking.

Configure Action

Configure Action allows users (Recipe Creators) to define what action should be performed on analysis results. It is available from the three-dot menu on result tables and is used to map output columns to the required fields of the selected action.

Once configured, the action becomes part of the recipe and can be executed later through Take Action. If an action is already configured, opening Configure Action directly shows the mapped configuration, allowing updates or removal.

• Click the three-dot menu on result tables, alongside Download and Fullscreen options.

Key capabilities

Capability	Description
Single Action	Only one action can be configured per output table
Field Mapping	Map output columns to action fields
Mandatory Validation	Required fields must be mapped before saving
Static Values	Default/static values can be assigned

Once configured:

• The configuration is linked to the recipe/output

• The Take Action option becomes available

• The configured action becomes available for execution

• The configuration can be updated anytime

• Only one action can be active per output table at a time

• Removing an action clears all mapped configurations

• Configuration is reused during execution without re-mapping

Supported Actions

askEdgi supports multiple operational actions that can be configured on analysis outputs. These actions allow users to directly act on insights without leaving the analysis context.

The supported actions include:

• Assign Tag: Apply tags to selected data assets based on analysis results.

• Create Data Quality Service Desk Ticket: Raise service desk tickets for identified data quality issues.

• Create Data Quality Rule: Define and create data quality rules from analytical outputs.

• Create Project Tasks: Convert results into structured tasks within Projects for execution and tracking.

• Post Question: Post questions to the Question Wall for further clarification or collaboration.

Each action is designed to convert analysis results into a specific operational outcome within the platform, while maintaining governance and control.

Field Mapping

Field mapping defines how columns from the askEdgi output are linked to the required fields of the selected action. This ensures that the execution uses structured and relevant data from the analysis.

During configuration, users map output columns to action fields. Some fields are mandatory and must be completed before the configuration can be saved or updated. The system validates these fields and enables the Save or Update option only after all required mappings are provided.

Optional fields can be left unmapped if they are not required for execution. In such cases, the system either ignores those fields or applies default handling where applicable.

In addition to dynamic mapping from output columns, users can also define static values. This is useful when a fixed value needs to be applied across all records, such as a constant priority, category, or status.

Once configured, the mapping is saved as part of the recipe. This ensures consistency across executions and allows the same logic to be reused without reconfiguration. Users can revisit and modify the mapping later through the Configure Action flow, and any updates will overwrite the existing configuration.

Unassign Action

Users can remove an existing action configuration.

Steps:

1. Click Configure Action

2. Click Unassign Action

3. Confirmation popup:

   1. Yes: Action removed, action list displayed

   2. No: Return to mapped configuration

Take Action

Take Action enables users to execute configured actions on analysis results directly from the askEdgi output. It acts as the execution layer of the action framework, allowing users to convert analytical results into governed operations within the platform.

The Take Action option is available on the result table. When an action is already configured and the recipe is executed, it is also displayed as a primary button for quick access. If no action is configured, users can still access Take Action through the three-dot menu.

All executions are performed as background jobs to ensure scalability and performance. The system provides execution tracking through Job IDs and displays the final outcome within the chat interface.

Execution Flow

The execution process follows a structured and controlled sequence to ensure accuracy and governance:

1. The user reviews the analysis output and selects one or more rows from the result table.

2. The user clicks Take Action from the available options.

3. The system displays the configured action details along with the mapped fields for the selected records.

4. The user reviews the data and confirms the execution wherever applicable.

5. Once confirmed, the system initiates a background job to process the request.

6. A Job ID is generated and displayed to the user for tracking purposes.

7. The system processes each selected record based on the configured action logic.

8. Upon completion, the system displays a detailed execution summary in the chat.

Execution Result Summary

After the job is completed, the system presents a clear and structured summary of the execution outcome. The results are divided into two sections:

• Successfully processed records

• Failed records

Each section is displayed separately with corresponding data entries, allowing users to easily understand which records were processed and which require further attention.

Action: Create Project Tasks

The Create Project Tasks action allows users to convert analysis results into structured tasks within the Projects module. This helps in operationalizing insights by assigning ownership, tracking progress, and ensuring accountability.

Project Resolution Logic

When the action is executed, the system determines whether to use an existing project or create a new one.

Field Mapping and Requirements

During configuration, users map output columns to task-related fields. Among these:

• Task Name and Assignee are mandatory and must be provided for task creation.

• Other fields, such as descriptions, object references, and dates, are optional and can be mapped if required.

If optional fields are not provided, the system applies default handling wherever applicable.

Task Type Determination

The system automatically determines the type of task (object or non-object) based on the availability of object-related fields:

• If Object Type and Object ID are provided, the task is created as an object-linked task.

• If these fields are not provided, the task is created as a non-object task.

The same logic applies to parent tasks using Parent Object fields.

Parent-Child Task Handling

The system supports hierarchical task creation based on the presence of parent task information:

• If the Parent Task Name is provided, tasks are grouped under a parent task.

• If the Parent Task Name is not provided, tasks are created as standalone entries without any hierarchy.

For grouping:

• Parent task names are normalized using trimming and case-insensitive comparison.

• If parent object fields are provided, grouping is based on Parent Object ID instead of name.

This ensures consistent grouping and avoids duplicate parent creation.

Additional Execution Behaviors

• If the task name is missing in a row, that row is skipped, and processing continues for the remaining records.

• If duplicate object tasks are detected, the entire action fails due to validation rules in the Projects module.

• If the assignee is inactive or not found, the task is assigned to the Project Owner.

• All valid assignees are automatically added as members of the project.

• If start and end dates are not provided, tasks inherit dates from the project configuration.

Execution Characteristics

• Task creation is executed asynchronously using the Take Action job framework.

Action: Create Data Quality Rule

The Create Data Quality Rule action allows users to convert analysis results into enforceable data quality rules directly within the Data Quality module.

Configuration and Mandatory Fields

To ensure valid rule creation, the following fields must be mapped during configuration:

• Object Type

• Function (rule logic)

• Success Criteria

• Rule Name

• Rule Purpose

• Dimension

The system does not allow saving the configuration unless all mandatory fields are mapped.

Execution Behavior

This action follows a controlled and review-based execution process:

• Rules are configured by the recipe creator but executed by the user.

• During execution, users must review the rule details for each selected row.

• Users explicitly approve the creation before execution begins.

• Multiple rules can be processed within a single job.

Execution Flow

1. The user selects one or more rows from the result table.

2. The user initiates Take Action and selects the Data Quality Rule action.

3. The system displays rule details for review.

4. The user approves the selected entries.

5. A background job is triggered.

6. Rules are created in the Data Quality module upon successful execution.

State Management

• The review and approval state is tied to a specific execution.

• If the recipe is executed again, previous selections and approvals are reset.

• Only newly generated results are considered for action.

Audit Trail Tracking

All actions performed through Take Action are recorded in Audit Trails to ensure traceability and governance.

Logging

Each action execution captures detailed information, including:

• Action name

• Job ID

• Execution status (start and completion)

• The user who triggered the action

• Execution date and time

Module-Level Tracking

Depending on the action performed, logs are recorded in the respective modules:

• General Take Action logs are stored under askEdgi in Audit Trails

• Service Desk actions are tracked under the Service Desk module

• Tag assignments include a source indicator marked as “askEdgi”

• Data Quality Rule creation is tracked in both Audit Trails and rule-level history

• Term creation is tracked within the Governance Catalog

• Only one action can be configured per output table at a time.

• All executions follow user permissions and governance controls.

• Actions are executed asynchronously to support scalability.

• Results are always displayed in the chat with a clear success and failure summary.

Service Desk Templates - Legacy Data Quality Status

A template-level property, Legacy Data Quality Status, supports capturing and storing historical data quality issue context.

This capability is designed to ensure that data quality remediation insights are preserved and made available for downstream systems, including RAG-based context retrieval.

The feature is applicable only to Data Quality Issue request types and is controlled through template configuration.

Template Property Configuration

A new configuration property is introduced at the template level:

• Property Name: Legacy Data Quality Status

• Configuration Key: legacydataqualitystatus

• Type: Checkbox (True / False)

Default Behavior

• Default value: False

• For Data Quality templates: Enabled (True) by default

• Hidden for all other template types

Functional Behavior

When the Legacy Data Quality Status property is enabled:

1. A new status becomes available:

   1. Status: Legacy Data Quality Issue

   2. Action: Mark as Legacy Issue

2. When a service request is moved to this status:

   1. A backend fulfillment job is triggered automatically

   2. The job captures and stores the data quality context

3. This process is system-driven and does not require user intervention beyond status change

Job Funtionality

An internal fulfillment job is triggered when the request status changes to Legacy Data Quality Issue.

Key Characteristics:

• This is a system-level job

• It is not visible in the UI

• It is automatically linked to the template property

Context Capture Logic

When the status is moved to Legacy Data Quality Issue:

1. The system reads the Corrective Action field provided by the approver

2. If the field contains data:

   1. The content is stored as a data cleanup context

   2. The context is attached to the corresponding object

3. If the field is empty:

   1. No context is captured

This context is then used for downstream processing, including RAG-based retrieval.

askEdgi Integration

• When a request is marked as a Legacy Data Quality Issue, the associated context is captured for that object.

• Context is stored at the object level (Table/File).

• Multiple contexts can exist for the same object.

This enables improved contextual understanding for future analysis and recommendations.

Status and Action

A new system-defined action and status are introduced:

• Action: Mark as Legacy Issue

• Status: Legacy Data Quality Issue

This status is controlled by the template property and is available only for Data Quality Issue requests.

Scope:

• System-controlled

• Enabled/disabled through template configuration

Data Quality Context - Cleanup and Staging

askEdgi supports governed handling of data quality issues by incorporating structured cleanup context into the analysis workflow. This enables the system to distinguish between issues that can be resolved through governance and those requiring runtime remediation.

Legacy Issue Classification

Data quality issues are classified during service request approval:

• Non-legacy issues are resolved through standard governance processes

• Legacy issues represent persisted inconsistencies that cannot be corrected at source

Only issues marked as legacy are eligible for runtime cleanup.

Steps:

• Provide context for the Data Quality service request by classifying the issue as a Legacy Data Quality Issue and defining the required cleanup rules.

• Open the dataset in the askEdgi workspace, where the option “Clean up this dataset without data quality debt” is displayed when a valid cleanup context is available.

• Click the cleanup option to proceed.

• A pop-up is displayed showing the defined cleanup rules, with options to Clean Data or Cancel.

• Click Clean Data to apply the approved cleanup logic and generate a cleaned dataset for consumption, or click Cancel to exit without any changes.

Cleanup Context Management

For legacy issues, approvers must define explicit cleanup logic:

• Stored at the object level

• Must be governed, approved, and executable

• Used as the sole basis for data transformation

This ensures all remediation is controlled and traceable.

Execution

When a dataset with legacy issues is used:

• askEdgi checks for approved cleanup context

• Users can apply cleanup within the workspace

• A transformed dataset is generated for analysis

Key Functionality

• Cleanup is executed only when an approved context is available

• Transformation logic is derived exclusively from service request inputs

• Cleaned datasets are generated within the workspace for downstream use

• Source data remains unchanged

Separation from RAG Processing

This capability operates independently of the RAG pipeline:

• No embedding-based retrieval is used

• No impact on retrieval, ranking, or scoring

• No modification to semantic processing

Data retrieval and data correction remain strictly separated.

Controlled Transformation

Cleanup results in a derived dataset:

• Used only within the workspace session

• Can be removed to revert to original data

• Does not affect source systems

Explainability and Governance

All cleanup actions are fully governed and transparent:

• Based only on approved context

• Clearly explains the issue, logic, and remediation

• Fully auditable and traceable

Workspace Data Download Control

askEdgi supports controlled data download across all workspace objects. This capability enables users to download datasets generated or accessed within the workspace while ensuring enforcement of role-based access control and consistent behavior across all interaction points.

Download Availability Across Workspace

Data download is supported for all types of workspace objects, irrespective of their origin. This includes:

• Catalog tables

• Non-catalog tables

• AI-generated datasets

• Uploaded files

• Derived or transformed datasets created during analysis

Download functionality is consistently available across the following views:

• Workspace object list

• Analysis results (tabular outputs)

• Chat / askEdgi responses where data is rendered

• Recipe execution outputs

This ensures a uniform experience for users working across different analysis and interaction modes within askEdgi.

Role-Based Access Control

askEdgi provides controlled access to data download within the workspace using a role-based configuration. This ensures that only authorized users can download data while maintaining consistent behavior across all areas where data is displayed, including analysis outputs, chat responses, and recipe results.

Role Evaluation and Access Control

The system evaluates the roles assigned to the logged-in user before enabling the download capability.

• A configurable list of roles is maintained at the system level.

• During runtime, the user’s assigned roles are compared against this configured list.

If the user has at least one matching role:

• Download functionality is enabled

If the user does not have any matching role:

• Download functionality is restricted

This evaluation is performed dynamically for every relevant data view to ensure that access is always aligned with the latest role configuration.

Consistency Across askEdgi Views

The download control is applied uniformly across all areas where data is rendered within askEdgi. This ensures a consistent and predictable user experience.

The same access logic is enforced for:

• Workspace object list (tables, files, datasets)

• Analysis result tables generated from queries or prompts

• Chat / askEdgi responses where tabular data is displayed

• Outputs generated from recipe execution

Regardless of how the data is generated (catalog, non-catalog, or AI-generated), the download behavior remains consistent.

User Interface

The visibility and state of the download option are dynamically controlled based on the user’s access.

For users with download permission:

• The download option is visible in the UI

• The option is enabled and actionable

• Users can initiate a download through:

  • Context menu (three-dot menu), or

  • Action icons (where applicable in the workspace)

For users without download permission:

• The download option is not exposed in the UI (preferred behavior), or

• It is displayed in a disabled state with a tooltip indicating restricted access

This ensures that unauthorized users are clearly restricted without ambiguity.

Configuration

Download access is controlled through a system configuration.

Field	Value
Module Group	OVALEDGE_APP
Configuration Type	SECURITY
Key	askEdgi.workspace.download.allowed.roles
Value	<role_list>
Description	Configure which roles are allowed to download data from the askEdgi workspace, including analysis and chat outputs

The configuration defines which roles are authorized to download data from askEdgi, including all analysis outputs and chat-based results.

---

Copyright © 2026, OvalEdge LLC, Peachtree Corners, GA USA