Design Partnerships now · IKE ADK private preview

Turn your expertise into applications.

IKE helps you build knowledge applications around your expertise, evidence, and method. Connect agent capabilities to the decisions and work people need to carry out, through conversation, a hosted application, or your existing product. Keep human judgment and review where the work requires them.

Illustrated AML agentic application workflow surface
The pattern

Put your expertise into everyday decisions.

Your team's expertise lives in documents, systems, working practices, and people's judgment. An application brings that expertise into the task at hand: what information matters, how to assess it, which actions are allowed, and when a person needs to decide.

We begin with SMEs and the material you already have. Agree vocabulary, relationships, evidence, stakeholders, and owners before accepting the application's intents. Those intents describe the outcomes, allowed behavior, and review points that guide composition and acceptance. Through a Design Partnership, Omni Arcs Product Studio works with you to build and prove that experience.

Establish the domain meaning and its sources.

Agree human-owned intents and success scenarios.

Map integration meaning, access, and permitted actions.

Prove the experience with its users and decision owners.

An Agent Application uses its Persona foundation and permitted capabilities through IKE. Enterprise systems exchange approved actions and results; models and tools exchange calls and results; people exchange review requests and decisions.
IKE ADK · Private preview

Build the application from a shared IKE layer.

The Application Development Kit (ADK) provides reusable contracts for intent, application definition, composition, and Builder workflows. IKE provides the connected knowledge and agent capabilities. Your application supplies its domain method, integration mappings, experience, and operating requirements. The composition and working application need to be verified together.

Agent definition

Agent Applications, Agent Groups, Personas, and Persona Bindings define the agent and its operating context.

Knowledge and artifacts

Collections, Knowledge Artifacts, and Ingestion Pipelines organize and update the sources an application uses.

Skills and tools

Skills, Tools, Blocks, and Capabilities describe reusable work the application can compose.

Interaction and work

Application Sessions, Conversations, Runs, Jobs, and Reviews carry work across chat and purpose-built experiences.

Policy and access

Principals, Roles, Policies, Entitlements, Sharing, and Authority govern who can use each capability.

Model configuration

Models, Model Profiles, embeddings, routing, guardrails, and provider configuration shape inference.

Deployment and runtime

Application Deployments, Hosting Providers, Gateways, Hosted Agents, and Runners realize the application at runtime.

Scope and isolation

Applications, Tenants, Workspaces, and Environments provide scope. Map reusable app knowledge, customer-specific rules, project evidence, and integration access explicitly; reuse does not grant cross-customer access.

See what we've already built with IKE.

Hosted OpenClaw brings a full agent framework, dedicated hosting, Personas, knowledge, authentication, and shared access together as a managed application. Omni Arcs Product Studio built and operates it with IKE. Bring us your complex knowledge workflow, the systems it needs to connect, and the constraints it must respect. We'll work with you to design, build, and operate the application around it.

Explore Hosted OpenClaw
IKE connects the Persona foundation and workspace chat to OpenClaw sessions. OpenClaw owns its framework and memory; Ikentic manages dedicated hosting.
Decorative device frame separator; no product content.
Illustrated anti-money laundering case workflow surface

Move an anti-money laundering case through a visible, reviewable workflow.

This Design Partnership is building an agentic offering around an established anti-money laundering product. It brings the product's investigation expertise, case records, agent-assisted analysis, and human review into one application for case work.

  • One case workspace

    Keep source records, controls, evidence, open gaps, and human closure together.

  • IKE behind the workflow

    Bind the analyst Persona, approved capabilities, knowledge, and session context to the case.

Read the anti-money laundering example
Decorative device frame separator; no product content.
Illustrated StrainBrain AI Budtender application surface
Built with StrainBrain

Add an AI Budtender to a retail experience without turning the experience into chat.

StrainBrain is an Ikentic Design Partner building an AI-guided retail experience for dispensaries.

  • The storefront stays primary

    Add product guidance while the retailer's shopping flow stays in the foreground.

  • IKE behind the assistant

    Supply the Persona, approved recommendation capabilities, and session context behind the experience.

Read the StrainBrain example

More application shapes

The same IKE layer can support a conversation or a combined work experience.

These examples show how Personas, capabilities, context, and sessions carry across different application surfaces.

AML agent conversation

A Persona-bound agent conversation that uses the capabilities behind an established AML product.

Read this example

AML workflow application

An agentic offering built around an established AML product to extend its customers' experience with visible case work and reviewable actions.

Read this example

See the bigger picture behind Agent Applications.

The technical whitepaper explains why knowledge applications require a different user and developer experience, and how human-owned intent connects to knowledge, application behavior and review. It sets out an architecture and ways to test its thesis. A Design Partnership establishes the scope and evidence for a particular application.

Read online
Choose the experience

Choose the experience the knowledge work needs.

An idea, prototype, established product, or data collection can lead to different experiences. Choose how people will use the knowledge and agent capabilities; an existing application can keep its interface while embedding new behavior.

Start with chat.

Direct Agent puts your Persona to work in a conversation, using its knowledge, skills, tools, and permissions. It runs on IKE’s shared, on-demand service, with each run scoped to your account and conversation. Create a free account to start.

Use a managed framework.

Smart Agent gives your agent dedicated resources running a framework that Ikentic hosts and manages. Hosted OpenClaw is the first option, bringing its tools, skills, channels, memory, and sessions into the application. Available with a paid plan.

Build around the workflow.

Agree on what the knowledge work needs to achieve. Give people the screens, records, state, actions, evidence, and review points to work through it. Connect the relevant Personas, agents, knowledge, plugins, integrations, code, and shared application context behind that experience.

From SME knowledge to a working application

Establish meaning, agree intents, then compose and prove.

Start with an SME's idea or wireframe, a prototype, a mature product, data, or a combination. The work joins domain knowledge, knowledge of how to build with IKE, and knowledge of external systems. Their relationships guide the build and the application's ongoing use.

01 · Establish meaning

Gather the expertise and agree the vocabulary.

Review work artifacts, evidence, policies, decisions, and stakeholder responsibilities. Establish an initial ontology and nomenclature with SMEs. For an existing app, reconcile its model and terminology before adding new behavior.

02 · Confirm intent

Describe the job and agree on success.

Capture the actors, outcomes, interactions, constraints, and review points in human-owned intent. Ambiguity returns to people before anything is generated.

03 · Define and compose

Connect the experience to its knowledge and capabilities.

Define surfaces, roles, source needs, and permitted actions. Map external records, operations, identities, permissions, and failure behavior. Resolve supported components and runtime choices into a composition the Builder and application can use.

04 · Build and review

Turn confirmed intent into reviewable work.

Builder's Resolve, Annotate, Materialize, and Skeptic phases connect intents to supported application details and reviewable workflow artifacts. Builders complete the integration, code, and experience around them, then review the visible outcomes with SMEs.

05 · Run and prove

Test the working application against the intent.

Demonstrate one end-to-end scenario with the right evidence, access, decision owners, and operating behavior. Carry approved decisions into the work. Review findings before promoting them into shared knowledge or a new application version.

Build with Ikentic now. Build with the IKE ADK soon.

Build your knowledge application with us through a Design Partnership. Your real-world requirements help refine IKE's Application Development Kit (ADK) as we prepare it for public availability. The ADK is currently in private preview.

For AI systems

Summary

IKE Agent Applications bring an organization's expertise, agents, people, knowledge, and existing systems together in an experience for everyday knowledge work. Start with the team's expertise and what already exists: an idea, prototype, product, or data. Establish meaning with subject-matter experts, agree human-owned intents, then compose the experience, agent capabilities, integrations, and operating boundaries. Prove the working application against the agreed outcome. Purpose-built applications are delivered through Design Partnerships; the IKE ADK is in private preview.

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

Scope: page; Section: Agent Applications; 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: Agent Applications 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
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.
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 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..

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: page; Section: Agent Applications 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
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.
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: page; Section: Agent Applications 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

What is an IKE Agent Application?

IKE Agent Applications bring an organization's expertise, agents, people, knowledge, and existing systems together in an experience for everyday knowledge work.

How do teams build an Agent Application with IKE?

Start with the team's expertise and what already exists: an idea, prototype, product, or data. Establish meaning with subject-matter experts, agree human-owned intents, then compose the experience, agent capabilities, integrations, and operating boundaries. Prove the working application against the agreed outcome. Purpose-built applications are delivered through Design Partnerships; the IKE ADK is in private preview.