CKS - Information Architecture for AI Solutions

Course Description

This two-day course introduces the principles and practices of Information Architecture and demonstrates how IA supports knowledge management, enterprise content management, search, user experience, and modern AI solutions. The course emphasizes how content models, metadata, taxonomies, ontologies, governance, and retrieval design improve the performance, trustworthiness, usability, and explainability of AI systems, especially generative AI, retrieval-augmented generation, copilots, intelligent search, and agentic AI solutions.
‍

Course Objectives

Explain the role of Information Architecture in organizing, structuring, governing, and retrieving enterprise information.
Develop foundational IA artifacts, including content inventories, content models, metadata schemas, taxonomies, and governance plans.
Explain how IA supports knowledge management, enterprise content management, search, analytics, and AI.
Design IA structures that improve AI grounding, retrieval quality, prompt performance, content reuse, and knowledge discovery.
Identify how poor IA creates AI risk, including hallucinations, poor retrieval, duplicated content, weak provenance, inconsistent terminology, outdated content, and lack of auditability.
Apply IA principles to RAG, enterprise copilots, AI assistants, knowledge graphs, and agentic AI workflows.
Develop an IA-informed AI readiness checklist for enterprise content, knowledge repositories, and AI use cases.

Two-Day Course Flow

Day

Theme

Modules

Day 1

IA Foundations and AI-Ready Content

Module 1: Introduction to IA and Why IA Matters in AI
Module 2: Content Audit and AI Readiness Assessment
Module 3: Content Models for Structured Content and AI Retrieval
Module 4: Metadata Schemas for Search, Governance, and AI Trust

Day 2

IA Application, Governance, and AI Solution Design

Module 5: Taxonomies, Ontologies, and Semantic Layers for AI
Module 6: Applying IA to Search, UX, and AI Experiences
Module 7: IA Governance for Content, Knowledge, and AI
Module 8: IA in KM, ECM, and Enterprise Intelligence
Module 9: Integrating IA into AI, RAG, Copilot, and Agentic Solutions
Capstone: IA-for-AI Solution Blueprint

Module 1: Introduction to Information Architecture and Why IA Matters in AI

Existing Topics to Retain

What is Information Architecture?
IA areas of practice
Understanding IA success
IA benefits
IA roles and responsibilities
IA components: content model, metadata schema, taxonomy
Introduction to course case study

IA-for-AI Enhancements

IA as the foundation for trustworthy AI
Difference between having content and having AI-ready content
How IA improves retrieval accuracy, semantic search, RAG performance, prompt grounding, AI response consistency, explainability, traceability, content governance, and knowledge reuse
How weak IA contributes to hallucinations, conflicting answers, duplicated content, poor search relevance, unclear source authority, and AI governance risk

Exercise

Exercise 1A: Identify AI-readiness gaps in enterprise content. Learners review sample content and identify issues that would affect AI retrieval and response quality, such as missing metadata, inconsistent terminology, unclear ownership, stale content, weak structure, and duplicate records.

Module 2: Performing the Content Audit and AI Readiness Assessment

Existing Topics to Retain

Content audit overview
Content audit step-by-step process
Content audit tools
Exercise: Perform a content audit using the case study

IA-for-AI Enhancements

Auditing content for AI use, not just human consumption
Identifying authoritative versus non-authoritative content
Determining whether content is current, complete, structured, reusable, and suitable for AI ingestion
Capturing source, owner, effective date, review date, sensitivity, retention, and usage rights
Identifying duplicate, obsolete, trivial, conflicting, and low-value content
Evaluating whether content can be chunked, embedded, retrieved, and cited effectively
Mapping content to AI use cases: chatbot, copilot, RAG system, enterprise search, knowledge assistant, agent workflow, and decision support

Exercise

Exercise 2A: AI content audit scoring. Learners score content against accuracy, authority, completeness, currency, metadata quality, sensitivity, structure, reusability, searchability, retrieval suitability, and risk level.

Module 3: Creating Content Models for AI Retrieval

Existing Topics to Retain

Content model overview
Constructing the content model
Steps toward constructing the content model
Content modeling best practices
Review of content modeling standards, guidelines, and best practices
Exercise: Construct the content model using the case study

IA-for-AI Enhancements

How content models help AI understand document types, business objects, relationships, and context
AI-relevant content types: policies, procedures, FAQs, standards, guidelines, case studies, lessons learned, product information, service records, training content, and decision logs
Structuring content for retrieval through titles, abstracts, summaries, purpose statements, audience fields, business process alignment, source attribution, version history, and related content
Designing content chunks for LLM retrieval
Difference between human-readable content and machine-retrievable content
Content models as the foundation for prompt grounding and response consistency

Exercise

Exercise 3A: Build an AI-ready content model. Learners extend the case study content model to include fields needed for AI retrieval, citation, ranking, governance, and reuse.

Module 4: Developing Metadata Schemas for Search, Governance, and AI Trust

Existing Topics to Retain

Metadata schema overview
Create metadata schema step-by-step process
Metadata schema tools
Exercise: Develop the metadata schema using the case study

IA-for-AI Enhancements

Metadata as the control layer for AI
Descriptive, structural, administrative, technical, governance, and AI-specific metadata
AI metadata fields: content owner, source system, review date, expiration date, version, sensitivity classification, data classification, legal/regulatory constraints, audience, business function, process area, jurisdiction, confidence level, approved for AI use, approved for external use, retrieval priority, and source authority ranking
Metadata and vector search filtering
Metadata and AI access control
Metadata and explainability
Metadata and auditability
Metadata and hallucination mitigation

Exercise

Exercise 4A: Design an AI metadata schema. Learners create a schema that supports search facets, RAG retrieval, content governance, sensitivity filtering, and answer citation.

Module 5: Developing Taxonomies, Ontologies, and Semantic Layers for AI

Existing Topics to Retain

Introduction to taxonomy
Case study overview
Interactive exercise: analyzing the case study
Taxonomy development process
Hands-on exercise: creating a taxonomy through card sorting
Best practices and common pitfalls

IA-for-AI Enhancements

How taxonomies improve AI retrieval and answer relevance
Controlled vocabularies and synonym management
Taxonomy versus ontology versus knowledge graph
Business terms, domain concepts, entities, and relationships
Semantic enrichment for entity extraction, topic tagging, concept mapping, acronym resolution, synonym expansion, and relationship modeling
How taxonomies improve semantic search, recommendation engines, RAG pipelines, copilot responses, knowledge discovery, and agent task routing
Taxonomy governance for AI

Exercise

Exercise 5A: Build a taxonomy for AI retrieval. Learners expand the case study taxonomy with synonyms, preferred terms, non-preferred terms, entity types, and retrieval filters.

Module 6: Applying IA to Search, UX, and AI Experiences

Existing Topics to Retain

IA content model
Content template
IA and UI/UX design
Wireframes
IA and search
Search facets

IA-for-AI Enhancements

IA and user experience for AI systems
Designing information experiences for enterprise search, AI assistants, copilots, chatbots, knowledge portals, and decision dashboards
IA and conversational UX
Designing facets and filters for AI retrieval
Designing source citation patterns
Designing answer confidence indicators
Designing escalation paths when AI cannot answer
Designing “show your source” and “why this answer” experiences
Using IA to structure prompt libraries and reusable prompt patterns
IA considerations for multimodal AI content, including text, images, audio, video, and documents

Exercise

Exercise 6A: Design an AI search and assistant experience. Learners design facets, source citations, filters, answer structure, confidence indicators, and feedback loops.

Module 7: IA Governance for Content, Knowledge, and AI

Existing Topics to Retain

IA planning
IA governance
IA governance model
IA governance plan
Planning and executing an IA initiative

IA-for-AI Enhancements

IA governance as part of AI governance
Roles and responsibilities: IA lead, content owner, knowledge manager, data steward, taxonomy manager, AI product owner, AI risk manager, legal/privacy/security reviewer
Governance policies for AI-ready content
Content lifecycle governance: create, review, approve, publish, reuse, retire, and archiveAI content approval workflows
Data sensitivity and access control
AI use restrictions by content type
Governance for prompt libraries, RAG knowledge bases, taxonomies, ontologies, and metadata schemas
Monitoring content drift, retrieval drift, and answer quality
IA metrics for AI: search success rate, retrieval precision, content freshness, metadata completeness, duplicate reduction, source citation accuracy, AI answer usefulness, escalation rate, and user trust score

Exercise

Exercise 7A: Create an IA governance plan for AI. Learners define roles, policies, review cycles, approval workflows, and quality controls for AI-ready content.

Module 8: IA in Knowledge Management, ECM, and Enterprise Intelligence

Existing Topics to Retain

Incorporating IA into KM strategy
Incorporating IA into ECM strategy

IA-for-AI Enhancements

IA as the bridge between KM, ECM, search, analytics, and AI
How IA supports enterprise knowledge reuse
IA and knowledge-grounded AI
ECM repositories as AI knowledge sources
KM repositories as RAG sources
Records management and AI retrieval restrictions
SharePoint, content management systems, knowledge bases, and AI indexing
IA in enterprise intelligence platforms
How AI changes KM and ECM requirements
Designing an enterprise knowledge layer for AI
Preparing content for Microsoft Copilot, ChatGPT Enterprise, Claude, Gemini, and internal AI assistants

Exercise

Exercise 8A: Map KM and ECM content to AI use cases. Learners identify which repositories should support AI use cases and determine the IA controls required for each.

Module 9: Integrating Information Architecture in AI Solutions

Existing Topics to Retain

IA in AI solutions
Basics of large language models
Constructing effective prompts for LLMs
Interactive workshop: writing effective prompts

IA-for-AI Enhancements

IA in AI solutions: IA as the organizing layer for enterprise AI and its relationship to data architecture, knowledge architecture, and AI architecture
Basics of LLMs: what they do well, what they do poorly, why they need grounding, and why prompts alone are not enough
RAG and IA: source selection, content preparation, chunking, embedding, indexing, metadata filtering, retrieval, ranking, prompt assembly, answer generation, citation, and feedback
IA and prompt engineering: role prompts, task prompts, context prompts, constraint prompts, source-grounded prompts, evaluation prompts, summarization prompts, classification prompts, and extraction prompts
IA for AI agents and agentic workflows: task planning, tool selection, knowledge retrieval, action boundaries, human-in-the-loop checkpoints, agent memory, and audit trails
IA and AI governance: provenance, source authority, risk classification, sensitivity, approved knowledge sources, transparency, explainability, auditability, human oversight, review, and recertification
Designing an AI-ready IA blueprint that includes use case, target users, source systems, content types, content model, metadata schema, taxonomy, facets, retrieval rules, access controls, governance model, prompt patterns, evaluation criteria, feedback loop, and risk controls

Exercise

Exercise 9A: Design an IA blueprint for an AI assistant. Learners use the course case study to design content sources, metadata, taxonomy, retrieval rules, prompt template, governance controls, risk considerations, and evaluation metrics.

Recommended Capstone Activity

Capstone: Build an IA-for-AI Solution Blueprint

The course will close with a take-home practical capstone where learners apply the entire two-day learning experience to a realistic AI assistant or RAG solution scenario.

Capstone Scenario

The organization wants to deploy an AI assistant that answers employee questions using approved enterprise content.

Learner Deliverables

AI use case description
Content inventory summary
AI-readiness audit findings
Content model
Metadata schema
Taxonomy structure
Search and retrieval strategy
Prompt template
Governance plan
AI risk and mitigation summary
Success metrics

Team Presentation Focus

Findability
Retrieval quality
Source trust
Response accuracy
Governance
User experience
AI risk management

Course Handouts and Templates (Part of the IA-AI Toolkit)

Template / Handout

Purpose

AI-Ready Content Audit Checklist

Assesses whether content is accurate, authoritative, current, structured, retrievable, and appropriate for AI use.

AI Metadata Schema Template

Defines metadata fields needed for retrieval, filtering, governance, sensitivity management, and citation.

AI Content Model Template

Structures content types, attributes, relationships, and reuse rules for AI solutions.

Taxonomy and Synonym Design Worksheet

Captures preferred terms, non-preferred terms, synonyms, acronyms, entity types, and semantic relationships.

RAG Readiness Checklist

Evaluates whether sources, content, metadata, chunking, indexing, and retrieval patterns are ready for RAG.

Prompt Library Governance Template

Documents prompt purpose, approved sources, variables, owners, review status, restrictions, and evaluation criteria.

IA-for-AI Governance RACI

Clarifies ownership across IA, KM, content, data governance, AI product, legal, privacy, security, and risk roles.

AI Assistant IA Blueprint Template

Provides the final design structure for source systems, content types, metadata, taxonomy, facets, prompts, governance, and metrics.

AI Retrieval Evaluation Scorecard

Measures retrieval precision, source citation accuracy, answer usefulness, escalation rate, and user trust.

AI Content Risk Classification Matrix

Classifies content by sensitivity, authority, use restrictions, external exposure, and AI approval level.

IA-for-AI Design Pattern

IA Artifact

AI Contribution

Common Risk if Missing

Content audit

Identifies authoritative, current, high-value, reusable content for AI ingestion.

AI retrieves stale, duplicate, conflicting, or low-quality content.

Content model

Defines content types, structure, relationships, and reusable components.

AI lacks context and cannot distinguish policies, FAQs, standards, procedures, and guidance.

Metadata schema

Enables filtering, ranking, access control, provenance, citation, and governance.

AI cannot reliably identify source authority, currency, sensitivity, or audience.

Taxonomy

Normalizes language, improves semantic search, supports synonyms and concept matching.

Users and AI systems use inconsistent terms, causing poor retrieval and weak answer relevance.

Ontology / knowledge graph

Models relationships among entities, concepts, processes, products, people, and decisions.

AI misses business context, dependencies, and relationships needed for reasoning.

Search facets

Supports precise retrieval and user-controlled narrowing of results.

Search and AI responses become broad, noisy, and difficult to validate.

Governance model

Controls ownership, review cycles, approved sources, access, and quality assurance.

AI uses unapproved, unmanaged, or expired knowledge sources.

Prompt library

Creates consistent, reusable, source-grounded instructions for AI use cases.

Prompts become inconsistent, unmanaged, hard to evaluate, and difficult to audit.

Register Now!
Next Class: July 28-29, 2026

Earn the CKS in Business Taxonomy and Ontology
‍(2-day class plus online "KM Foundation" course for New Students).

Standard rate for new students: $1,995
Past Grads (CKM/CKS): $1,595*

Package includes the 2-day Master Class, Course Workbook, KM Foundation Online Program, Online Exam, Certificate/Badge, and "Knowledge Hub" access to new instructional videos on KM and related topics -
no expiration.

And - you get the original Taxonomy Design self-paced course (free!) as part of your package -
10 hours of bonus material.

‍*Past Grads (CKP/CKM/CKS) may bypass the "KM Foundation" program and start with the Master Class.
Contact KMI today for your special quote.

Questions?

Call (US): 703-327-7096
Or email: training@kminstitute.org

‍We are standing by to help!

CKS - Information Architecture for AI Solutions

Course Description

Course Objectives

Two-Day Course Flow

Module 1: Introduction to Information Architecture and Why IA Matters in AI

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 2: Performing the Content Audit and AI Readiness Assessment

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 3: Creating Content Models for AI Retrieval

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 4: Developing Metadata Schemas for Search, Governance, and AI Trust

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 5: Developing Taxonomies, Ontologies, and Semantic Layers for AI

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 6: Applying IA to Search, UX, and AI Experiences

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 7: IA Governance for Content, Knowledge, and AI

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 8: IA in Knowledge Management, ECM, and Enterprise Intelligence

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Module 9: Integrating Information Architecture in AI Solutions

Existing Topics to Retain

IA-for-AI Enhancements

Exercise

Recommended Capstone Activity

Capstone: Build an IA-for-AI Solution Blueprint

Capstone Scenario

Learner Deliverables

Team Presentation Focus

Course Handouts and Templates (Part of the IA-AI Toolkit)

IA-for-AI Design Pattern

Register Now!Next Class: July 28-29, 2026

Questions?

How to Contact Us

What's Coming Up

Certified AI & KM Professional Class for North America

Certified Knowledge Manager (CKM) for North America

Register Now!
Next Class: July 28-29, 2026