Agent Integration
The IB-X Knowledge Ingestion Service integrates with AI-powered activities to provide grounded, context-aware, and semantically relevant responses using organization-specific knowledge.
Knowledge ingested through the Knowledge Ingestion Service becomes part of the semantic retrieval context associated with the owning Agent.
AI Agents and Conversational Agents can retrieve semantically relevant knowledge from their configured ingestion sources and supply the retrieved context to the AI model before response generation.
This architecture enables Retrieval-Augmented Generation (RAG) experiences within the IB-X platform.
Agent-Specific Knowledge Isolation
Knowledge ingestion in IB-X is Agent-specific.
Each Agent maintains its own isolated semantic knowledge space consisting of:
- Ingestion sources
- Semantic embeddings
- Retrieval context
- Ingestion runs
- Specialized collections
Only the owning Agent can retrieve and use its ingested knowledge.
This isolation model helps improve:
- Retrieval relevance
- Knowledge ownership
- Domain specialization
- Security boundaries
- Response quality
Retrieval Flow
During execution, AI-powered activities can perform semantic retrieval against the knowledge associated with the owning Agent.
The retrieval workflow typically follows the sequence below:
- User submits a request, prompt, or message
- AI activity performs semantic similarity search
- Relevant embeddings are identified
- Related semantic chunks are retrieved
- Retrieved context is supplied to the AI model
- AI model generates a grounded response
- Response is returned to the workflow or user
This retrieval pipeline enables the Agent to generate responses using organization-specific knowledge instead of relying only on foundational model knowledge.
Supported AI Activities
The Knowledge Ingestion Service can be consumed by multiple AI-powered activities.
Currently supported integrations include:
| Activity | Purpose |
|---|---|
| Conversational Agent | Multi-turn conversational experiences |
| AI Agent | Single-turn AI execution within workflows |
| Knowledge Base | Direct semantic retrieval from workflows |
Semantic Retrieval
The Knowledge Ingestion Service stores semantic embeddings inside the configured Vector Store.
During retrieval, AI-powered activities such as AI Agent, Conversational Agent, or Knowledge Base can perform semantic similarity search to identify the most contextually relevant knowledge chunks associated with the owning Agent.
Semantic retrieval allows the platform to retrieve information based on:
- Meaning
- Intent
- Context
- Conceptual similarity
instead of relying only on keyword matching.
Grounded Responses
The retrieved semantic context is supplied to the AI model before response generation.
This grounding process helps the Agent generate responses that are:
- Context-aware
- Organization-specific
- Knowledge-driven
- More accurate
- Less hallucinated
Grounding significantly improves enterprise conversational reliability and retrieval quality.
Specialized Collection Usage
The Knowledge Ingestion platform supports specialized semantic collections that improve retrieval organization and contextual relevance.
Supported collections currently include:
| Collection | Purpose |
|---|---|
| FAQs | Frequently asked questions |
| Products | Product-specific information |
| API References | Technical and API documentation |
| Code Snippets | Source code and implementation examples |
These collections help improve downstream semantic retrieval quality for targeted conversational scenarios.
Benefits
Using the Knowledge Ingestion Service with AI-powered activities provides several enterprise advantages.
Context-Aware Responses
Agents can retrieve and respond using organization-specific knowledge.
Reduced Hallucinations
Grounded retrieval reduces dependency on generalized foundational model knowledge.
Semantic Search
Retrieval is based on contextual meaning instead of only keyword matching.
Domain Specialization
Each Agent can maintain its own specialized semantic knowledge space.
Enterprise Knowledge Grounding
Organizations can ground AI experiences using internal documentation, websites, files, videos, and other knowledge sources.
Supported Knowledge Sources
AI-powered activities can retrieve knowledge ingested from:
- Website URLs
- Uploaded files
Additional source types may be supported by future ingestion providers.
Related
Notes
- Knowledge retrieval is isolated to the owning Agent.
- Semantic embeddings are stored in the configured Vector Store.
- Relationship-based retrieval scenarios may use the configured Graph Database.
- Ingestion infrastructure is configured globally from the root tenant.