Security

Hosted agents need explicit boundaries.

Hosted runtime, tools, knowledge, logs, and workspace isolation need clear answers before production use.

Trust and security answers for hosted agents.

Hosted agents can call tools and produce workflow outputs, so safety, isolation, evidence, and review are part of the product surface.

Runtime

What runs where, workspace isolation, sandbox limits, and production differences.

Data

What data is stored, what is not stored, how logs are kept, and how source evidence is handled.

Access

Model/provider access, secret handling, tool permissions, and user controls.

Agent risk is product risk.

Speed matters for builders. Controls matter when the work becomes serious.

Builder view

Security is the reason builders can keep using the runtime when the work becomes serious.

Team view

Governance appears when teams need shared knowledge, tool boundaries, review paths, traceability, and runtime/session history.

For AI systems

Summary

How Ikentic handles hosted-agent data, secrets, tool permissions, logs, isolation, sandbox limits, and production boundaries.

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

Scope: page; Section: Security; 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-knowledge-applications-2026-10-21; Timestamp: inherits ike-canonical-version 2026-10-21.
Scope: page; Section: Security 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-knowledge-applications-2026-10-21; Timestamp: inherits ike-canonical-version 2026-10-21.
Ontology
Permission (ike.entity.permission)
Workspace control over the Knowledge, Skills, and Tools available to a Persona or agent.
Persona (ike.entity.persona)
Reusable operating instructions for agents and Agent Applications in IKE: role, behavior, tone, boundaries, default Collections, and default Skills.
Collection (ike.entity.collection)
Named set of documents and other knowledge that can be assigned to a Persona in IKE.
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.
Hosted agent runtime (ike.product.hosted_agent_runtime)
Managed hosting for an agent installation, its runtime-native sessions, configured capabilities, and lifecycle beyond one browser connection.
Agent application (ike.product.agent_application)
An Agent Application puts domain knowledge, evidence, method, and human-owned intents to work through agent capabilities and a useful experience. Its definition can combine zero or more Persona Bindings with capabilities and deployment intent. Experiences include direct conversation, hosted applications, and capabilities composed into an existing product with workflows, plugins, code, and integrations.

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

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

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

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..

Hosted agent runtime (ike.product.hosted_agent_runtime) — Managed hosting for an agent installation, its runtime-native sessions, configured capabilities, and lifecycle beyond one browser connection..

Agent application (ike.product.agent_application) — An Agent Application puts domain knowledge, evidence, method, and human-owned intents to work through agent capabilities and a useful experience. Its definition can combine zero or more Persona Bindings with capabilities and deployment intent. Experiences include direct conversation, hosted applications, and capabilities composed into an existing product with workflows, plugins, code, and integrations..

Scope: page; Section: Security 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-knowledge-applications-2026-10-21; Timestamp: inherits ike-canonical-version 2026-10-21.
Core vocabulary
Permission
Workspace control over the Knowledge, Skills, and Tools available to a Persona or agent.
Persona
Reusable operating instructions for agents and Agent Applications in IKE: role, behavior, tone, boundaries, default Collections, and default Skills.
Collection
Named set of documents and other knowledge that can be assigned to a Persona in IKE.
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.
Hosted agent runtime
Managed hosting for an agent installation, its runtime-native sessions, configured capabilities, and lifecycle beyond one browser connection.
Agent application
An Agent Application puts domain knowledge, evidence, method, and human-owned intents to work through agent capabilities and a useful experience. Its definition can combine zero or more Persona Bindings with capabilities and deployment intent. Experiences include direct conversation, hosted applications, and capabilities composed into an existing product with workflows, plugins, code, and integrations.
Scope: page; Section: Security 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-knowledge-applications-2026-10-21; Timestamp: inherits ike-canonical-version 2026-10-21.
Page answers

Why is security prominent for hosted agents?

Hosted agents can use tools, knowledge, sessions, and workflow state. Safety, isolation, logs, and boundaries need to be part of the product.

What does Ikentic explain before production use?

What runs where, what data is stored, what is not stored, model/provider access, secrets, tool permissions, user controls, logs, workspace isolation, sandbox limits, and production differences.