Status
Live
Production-ready
Strategic Intelligence
Dataset Registration Agent
Runs the full database discovery pipeline to catalog all tables, relationships, and hub entities in the system. Automatically registers datasets, records discovery results as system processes, and includes a self-healing
Intelligence & AnalyticsLiveInternal (Colaberry Enterprise)Verified
Department
Strategic Intelligence
Intelligence & Analytics department for Colaberry Enterprise agents
Source
Internal (Colaberry Enterprise)
Built by Colaberry
About
About the Agent
What this agent does, the challenges it addresses, and where it delivers value.
Runs the full database discovery pipeline to catalog all tables, relationships, and hub entities in the system. Automatically registers datasets, records discovery results as system processes, and includes a self-healing retry mechanism for transient failures.
Challenges This Agent Addresses
- 1**Platform Setup**: Automatically discovers and catalogs all database entities when the platform initializes
- 2**Data Governance**: Maintains an up-to-date registry of all tables and their relationships for the intelligence layer
- 3**Self-Healing**: Recovers from transient database or network failures without manual intervention
Workflow
How the Agent Works
Step-by-step operational flow showing how this agent processes tasks end-to-end.
1
Step 1
Checks if a discovery run is already in progress (prevents concurrent execution)
2
Step 2
Invokes `runFullDiscovery()` from the dictionary builder to scan the database schema
3
Step 3
Records the successful discovery as a system process with metadata (tables found, relationships, hub entity)
4
Step 4
On failure, records the error as a failed system process
5
Step 5
Automatically retries once after 30 seconds if the initial run fails (self-healing)
6
Step 6
Provides a status check function to retrieve the most recent discovery result
7
Step 7
Includes an `ensureDatasetsCovered()` utility that triggers discovery if no datasets exist in the registry
Execution Modes
Trigger: on-demand (invoked at startup or when no datasets are registered)
Data
Inputs & Outputs
What data this agent consumes and the artifacts or actions it produces.
Input Data
- Database schema metadata (discovered automatically via the `dictionaryBuilder`)
- Existing dataset registry state
Deliverables
- `DiscoveryResult` containing:
- Number of tables discovered
- Number of relationships found
- Hub entity identification
- Discovery duration in milliseconds
- System process record logged to the `SystemProcess` table
Core Tasks
- Strategic Intelligence
Integrations
Systems Connected
Internal systems, APIs, and tools this agent integrates with.
Tools & APIs
Invokes the **Dictionary Builder** (`runFullDiscovery`) for schema analysisWrites results to the **DatasetRegistry** modelLogs process status to **SystemProcess** tableDiscovered datasets are consumed by the **Intelligence Assistant** for query planning
Specifications
Agent Specs
Technical specifications, requirements, and deployment details.
Related
Related Agents
Other agents in the same department or industry.
Enterprise AI
Ready to deploy this agent?
Schedule a walkthrough with our team to see how this agent integrates with your workflows.