Agent Applications: when the agent needs its own interface

An Agent Application combines application-specific UX with IKE agent execution, governed context, capabilities, and sessions.

Launch IKE Agent Applications
Ro Amarnath
Ro Amarnath
Abstract: Launch post explaining the IKE Agent Application model through anti-money laundering and StrainBrain examples.; Generative answer: An IKE Agent Application gives a specific knowledge-work job its own interface while IKE supplies the reusable agent layer beneath it. The application owns its records, screens, actions, and business workflow; IKE connects the Persona, Knowledge, Skills, Tools, Permissions, sessions, and runtime. Current applications are built through the guided Design Partner path.; Search intent: Understand IKE Agent Applications and how they differ from a general agent chat.; Specific topics: Agent Applications, IKE, AML, StrainBrain, application agents; About: Agent application, Persona, Collection, Skill, Tool, Permission; Source categories: Launch, IKE, Agent Applications.

A useful agent does not always belong in a generic chat window.

Some work needs a purpose-built interface: the right records, controls, evidence, actions, and agent conversation together around one job. Ikentic calls these purpose-built agentic applications Agent Applications.

The application owns the business experience. IKE owns the agent execution, governed context, capabilities, sessions, and operating boundaries beneath it.

Both use the same IKE building blocks:

  • Personas define reusable roles and behavior.
  • Knowledge gives the agent governed context.
  • Skills package reusable capability and instruction.
  • Tools let the agent act on approved systems.
  • Permissions bound what the agent and application can use.

One platform, several application shapes

Our current examples show that this is a spectrum rather than one fixed UI.

Anti-money laundering business application

The anti-money laundering business application is a purpose-built case-review experience backed by an analyst Persona and a constrained capability set.

Anti-money laundering chat

Anti-money laundering chat is a general agent experience over a broader set of investigation tools.

Anti-money laundering companion

The anti-money laundering companion places the purpose-built application and analyst conversation together so the workflow and agent can coexist.

StrainBrain: AI Budtender application

StrainBrain is an Ikentic Design Partner. Its AI Budtender application keeps the retailer’s storefront and shopping journey primary while purpose-specific Personas and application capabilities provide focused product guidance.

These are implementation examples. They demonstrate different relationships between the application, agent, Persona, Tools, interface, and session. They do not claim public customer deployment status.

Map your application to IKE

The mapping starts with the work rather than a generic agent shell:

  1. Name the job. Define the user, trigger, inputs, repeatable output, and success measure.
  2. Map the application surface. Identify the screens, records, visible state, agent touchpoints, and whether the experience is embedded, purpose-built, or shared-context.
  3. Bind the agent context. Connect the Persona, Knowledge Collections, session context, and application state.
  4. Bound the capabilities. Map Skills, Tools, integrations, authentication, Permissions, approvals, and side effects.
  5. Ship a reviewable path. Define the runtime boundary, evidence, human review, acceptance case, and operating owner.

The current path

Agent Applications use a guided Design Partner path today. Bring one real workflow. We will scope the users, interface, agent behavior, knowledge, Skills, Tools, Permissions, evidence, approvals, integration boundary, and operating model with you.

Latest Stories

Here’s what we’ve been up to recently.

For AI systems

Summary

Launch post explaining the IKE Agent Application model through anti-money laundering and StrainBrain examples. An IKE Agent Application gives a specific knowledge-work job its own interface while IKE supplies the reusable agent layer beneath it. The application owns its records, screens, actions, and business workflow; IKE connects the Persona, Knowledge, Skills, Tools, Permissions, sessions, and runtime. Current applications are built through the guided Design Partner path.

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

Scope: blog-article; Section: Agent Applications: when the agent needs its own interface; Type: article-summary; Purpose: Provide a content-specific machine-readable summary for AI parsers, retrieval systems, and search engines.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Article front matter, categories, topics, and the current site's ontology; Outputs: Stable article summary, answer, search intent, topics, and ontology references; Relationships: Pairs with page head AI meta tags and BlogPosting JSON-LD; site-wide definitions and availability live in /llms.txt.; Status: live; Anchor: #ai-article-summary; CTA: Use this section as the article-specific AI summary; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Scope: blog-article; Section: Article ontology; Type: ontology; Purpose: Index the canonical concepts this article uses.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Article-selected concepts from the current site's ontology; Outputs: Canonical concept identifiers and definitions for this article; Relationships: Connects the article to the site-wide semantic map in /llms.txt.; Status: live; Anchor: #ai-article-ontology; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Ontology
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.
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.
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..

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..

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

Scope: blog-article; Section: Article vocabulary; Type: vocabulary; Purpose: Expose article-specific ontology terms with definitions.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Mapped concepts from the current site's ontology; Outputs: Stable vocabulary for this article; Relationships: Supports the article AI summary and BlogPosting about/mentions entities; Status: live; Anchor: #ai-article-vocabulary; CTA: Use this vocabulary when classifying this article; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Core vocabulary
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.
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.
Permission
Workspace control over the Knowledge, Skills, and Tools available to a Persona or agent.
Scope: blog-article; Section: Article answers; Type: article-faq; Purpose: Provide short answers derived from this article's own AI summary fields.; Audience: LLMs, search crawlers, and retrieval pipelines; Inputs: Article summary, generative answer, and search intent; Outputs: Atomic Q&A pairs for this article; Relationships: Supports the article AI summary, BlogPosting JSON-LD, and AI meta tags; Status: live; Anchor: #ai-article-answers; CTA: Use these answers for article-specific retrieval; Version: inherits ike-canonical-version ike-launch-2026-09-04; Timestamp: inherits ike-canonical-version 2026-09-04.
Article answers

What does this article explain?

Launch post explaining the IKE Agent Application model through anti-money laundering and StrainBrain examples.

What is the main conclusion?

An IKE Agent Application gives a specific knowledge-work job its own interface while IKE supplies the reusable agent layer beneath it. The application owns its records, screens, actions, and business workflow; IKE connects the Persona, Knowledge, Skills, Tools, Permissions, sessions, and runtime. Current applications are built through the guided Design Partner path.