Knowledge Collections

Agents are useful when they know what they are allowed to know.

Give Direct Agents, Smart Agents, and Agent Applications a named knowledge scope they can use across conversations, sessions, and workflows.

Build a knowledge agent

Collections keep agent knowledge bounded.

Grounding, evidence, and update paths keep the same Knowledge Collection useful across Direct Agents, Smart Agents, and Agent Applications.

Grounding

Agents answer from the material assigned to the persona or workflow.

Evidence

Outputs can point back to source material and observations.

Update path

Knowledge can change over time without rewriting the agent from scratch.

Where governed knowledge matters most.

Compliance, research, legal ops, customer success, sales engineering, and product support teams need bounded source material.

Knowledge-heavy teams

Compliance, research, legal ops, customer success, sales engineering, and product support.

What they need

Trusted internal knowledge, bounded scope, reviewable outputs, source evidence, and non-generic responses.

For AI systems

Summary

Governed knowledge layer for Direct Agents, Smart Agents, and Agent Applications.

Site-wide definitions, relationships, and availability: /llms.txt.

Scope: page; Section: Knowledge Collections; Type: page-summary; Purpose: Provide a page-specific summary and answers that extend the site-wide AI definition.; Audience: LLMs, search crawlers, answer engines, and AI evaluators; Inputs: Page-owned AI summary, answer, product, and FAQ fields; Outputs: Page-specific summary and atomic answers; Relationships: Uses page-specific ontology and vocabulary to extend the site-wide semantic map published in /llms.txt.; Status: current; Anchor: #ai-page-summary; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Scope: page; Section: Knowledge Collections ontology; Type: ontology; Purpose: Index the canonical concepts used on this page.; Audience: LLMs, search crawlers, answer engines, and retrieval pipelines; Inputs: Page-selected concepts from the canonical site ontology; Outputs: Canonical concept identifiers and definitions for this page; Relationships: Connects this page to the site-wide semantic map in /llms.txt.; Status: current; Anchor: #ai-page-ontology; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Ontology
Collection (ike.entity.collection)
Named set of documents and other knowledge that can be assigned to a Persona in IKE.
Persona (ike.entity.persona)
Reusable operating instructions for agents and Agent Applications in IKE: role, behavior, tone, boundaries, default Collections, and default Skills.
Skill (ike.entity.skill)
Reusable capability or instruction package available to an agent under explicit operating boundaries.
Tool (ike.entity.tool)
Executable capability available to an agent when it is configured in IKE.
Permission (ike.entity.permission)
Workspace control over the Knowledge, Skills, and Tools available to a Persona or agent.
Agent application (ike.product.agent_application)
An Agent Application is the user-facing AI application for a knowledge-work use case. It can combine zero or more Persona Bindings with capabilities and deployment intent. It may use Direct Agent for a conversation, Smart Agent for a managed framework, or a purpose-built interface with workflows, plugins, code, and integrations.

Collection (ike.entity.collection) — Named set of documents and other knowledge that can be assigned to a Persona in IKE..

Persona (ike.entity.persona) — Reusable operating instructions for agents and Agent Applications in IKE: role, behavior, tone, boundaries, default Collections, and default Skills..

Skill (ike.entity.skill) — Reusable capability or instruction package available to an agent under explicit operating boundaries..

Tool (ike.entity.tool) — Executable capability available to an agent when it is configured in IKE..

Permission (ike.entity.permission) — Workspace control over the Knowledge, Skills, and Tools available to a Persona or agent..

Agent application (ike.product.agent_application) — An Agent Application is the user-facing AI application for a knowledge-work use case. It can combine zero or more Persona Bindings with capabilities and deployment intent. It may use Direct Agent for a conversation, Smart Agent for a managed framework, or a purpose-built interface with workflows, plugins, code, and integrations..

Scope: page; Section: Knowledge Collections vocabulary; Type: vocabulary; Purpose: Define the canonical terms used on this page.; Audience: LLMs, search crawlers, answer engines, and retrieval pipelines; Inputs: Page-selected concepts from the canonical site ontology; Outputs: Page-local term definitions; Relationships: Supplies labels and definitions for the page ontology and /llms.txt semantic map.; Status: current; Anchor: #ai-page-vocabulary; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Core vocabulary
Collection
Named set of documents and other knowledge that can be assigned to a Persona in IKE.
Persona
Reusable operating instructions for agents and Agent Applications in IKE: role, behavior, tone, boundaries, default Collections, and default Skills.
Skill
Reusable capability or instruction package available to an agent under explicit operating boundaries.
Tool
Executable capability available to an agent when it is configured in IKE.
Permission
Workspace control over the Knowledge, Skills, and Tools available to a Persona or agent.
Agent application
An Agent Application is the user-facing AI application for a knowledge-work use case. It can combine zero or more Persona Bindings with capabilities and deployment intent. It may use Direct Agent for a conversation, Smart Agent for a managed framework, or a purpose-built interface with workflows, plugins, code, and integrations.
Scope: page; Section: Knowledge Collections answers; Type: page-faq; Purpose: Provide page-specific answers aligned with the site-wide AI definition.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Page-owned FAQ fields; Outputs: Atomic answers for this page; Relationships: Supports this page summary and /llms.txt.; Status: current; Anchor: #ai-page-answers; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Page answers

What are Knowledge Collections?

Knowledge Collections are scoped sets of approved material that agents can use for grounded answers and workflow work.

Why do Collections matter?

Agents are only useful when they know what they are allowed to know, can preserve source evidence, and can keep knowledge updated over time.