AI Agents at Work, by Scott Burk, Kinshuk Dutta, and Harman Kaur
Supercharge your organization with a practical, battle-tested playbook for deploying agentic AI, which are multi-agent systems that boost ROI, harden compliance, and turn everyday workflows into resilient, data-driven automation.
1.1 From Automation to Autonomy: Why Agentic Architecture Matters
1.2 Enterprise Blueprint: Readiness and ROI
1.3 When Agents Excel Beyond Traditional AI
1.4 Case Studies Across Verticals
1.5 Governance, Risks, and Inaction
1.6 Key Takeaways
1.7 Discussion Questions / Exercises
2.1 Introduction: Why Agent Systems Matter
2.2 Agent Taxonomy: Types of Autonomous Systems
2.3 Single-Agent Versus Multi-Agent Design Patterns
2.4 Reasoning Architectures That Power Autonomous Decision-Making
2.5 Frameworks for Deployment
2.6 Building the Foundation for Agentic Transformation
2.7 Case Study: Optimizing Patient Flow with Agent Systems at ClearPath Health
2.8 Key Takeaways
2.9 Discussion Questions / Exercises
3.1 Agent Technology for Business Workflows
3.2 A Modern Tale: When Automation isn’t Enough
3.3 Infrastructure and Platforms Necessary to Support Agent Orchestration
3.4 Cloud and On-Premises Solutions for Agent Deployment
3.5 Leveraging Modern Frameworks like LangGraph, CrewAI, and AutoGen
3.6 Case Study: Coordinated Agents in Manufacturing Operations
3.7 Key Takeaways
3.8 Discussion Questions / Exercises
4.1 Core Technical Depth
4.2 Integration Patterns
4.3 Workflow Resilience and Cost Allocation Models
4.4 Real-World Case Studies
4.5 Cutting-Edge Advancements (2023–2025)
4.6 Strategic Enterprise Guidance
4.7 Key Takeaways
4.8 Discussion Questions / Exercises
5.1 Core Technical Depth
5.2 Integration Patterns
5.3 Case Studies
5.4 Cutting-Edge Advancements (2023–2025)
5.5 Strategic Enterprise Guidance
5.6 Key Takeaways
5.7 Discussion Questions / Exercises
6.1 Core Technical Foundations
6.2 Failure Management and Resilience
6.3 Case Study: Scaling Claims Processing with Agentic Orchestration
6.4 Metrics and Implementation Guidance
6.5 Strategic Enterprise Guidance
6.6 Key Takeaways
6.7 Discussion Questions / Exercises
7.1 The Three Tiers of Agent Memory
7.2 Architectures for Durability and State Persistence
7.3 Case Study: Petrobras and Automation Anywhere: Agentic Memory in Tax Compliance
7.4 Strategic Guidance for CTOs
7.5 Key Takeaways
7.6 Discussion Questions / Exercises
8.1 Why Governance Matters Now
8.2 Master Agent Management (MAM): The Registry of Governance
8.3 AgentOps and Quality Assurance
8.4 Resilience and FinOps: Governing Cost and Availability
8.5 Case Study Tanium Autonomous Endpoint Management (AEM)
8.6 Governance Metrics and SLOs
8.7 Key Takeaways
8.8 Discussion Questions / Exercises
9.1 Ethical Frameworks for Agentic AI
9.2 Data Privacy and Sovereignty in Federated Architectures
9.3 Explainable AI (XAI) as a Technical Enabler
9.4 Immutable Audit Trails and Continuous Compliance
9.5 Microsoft: Policy-Driven Governance with Unified Auditability
9.6 ServiceNow
9.7 Metrics, KPIs, and SLOs for Responsible Agentic AI
9.8 Strategic Guidance for CTOs
9.9 Key Takeaways
9.10 Discussion Questions / Exercises
10.1 Technological Solutions for Addressing Agent System Failures
10.2 How Companies Use Agent Messaging, Event Streaming, and Coordination Protocols
10.3 Agent Integration Platforms for Seamless Enterprise Workflows
10.4 Use Case Vignette: Coordinated Agents in Real-Time Financial Risk Monitoring
10.5 Key Takeaways
10.6 Discussion Questions / Exercises
11.1 Monitoring Agent Systems with Real-Time Dashboards
11.2 Technologies That Enable Real-Time Reporting and Monitoring of Agent Systems
11.3 The Role of Visual Business Intelligence in Agentic AI Strategies
11.4 Real-time Agent Visualization for System Monitoring
11.5 Real-time Decision Delivery from Agent Systems to Business Applications
11.6 Operationalizing Agent-Driven Decisions
11.7 Business Use Case: Dynamic Claims Processing in Insurance
11.8 Key Takeaways
11.9 Discussion Questions / Exercises
12.1 Technological Solutions for Addressing Agent System Failures
12.2 Ensuring Agent Integrity and Ethical Use of Autonomous AI
12.3 Emerging Trends in Enterprise Agentic Technologies
12.4 Agent-Generated Insights and Their Impact on Future Business Systems
12.5 Business Use Case: Agentic AI in Enterprise Supply Chain Optimization
12.6 Key Takeaways
12.7 Discussion Questions / Exercises
13.1 The Acceleration Effect
13.2 Recap of Core Themes
13.3 Copilot Agents and Glean’s Agent Builder
13.4 Comparative Analysis: Copilot versus Glean for an IT Helpdesk Agent
13.5 When to Use Which
13.6 Racing into the Future of Work with AI Agents
13.7 Final Thoughts
From strategy to sprint, AI Agents at Work shows you how enterprises move beyond demos to durable outcomes: an end-to-end blueprint starting from planning and readiness, progressing to agentic architecture patterns, and finally to the orchestration of multi-agent systems (MAS). Learn from actual case studies spanning finance, healthcare, retail, supply chain, and cybersecurity, along with executive decision trees and implementation checklists from actual production deployments.
The authors map the full agentic stack: agent taxonomy (reactive, deliberative, utility-based, learning, and generative), reasoning frameworks (BDI, chain-of-thought, and optimization), and integration patterns for agent-to-system and agent-to-agent coordination. Learn how to operationalize graph-based workflows with DAGs, stand up resilient orchestration, and build an integrated memory fabric across vector databases and knowledge graphs. The result is not another LLM app, but adaptive agents that plan, negotiate, and execute across ERP, CRM, EMR, and IoT systems.
Since enterprise trust is non-negotiable, you’ll get deep guidance on Agent Governance and Performance Management: Master Agent Management (MAM), AgentOps quality gates, SLOs, immutable audit trails, XAI/Explainability, privacy and data sovereignty in federated architectures, and cost visibility with FinOps dashboards. Clear deployment playbooks compare cloud, on-prem, and hybrid models; security patterns (RBAC, API gateways, and ledgered logging) meet regulatory needs while preserving velocity. Practical matrices and maturity checklists help teams pick the right framework (LangGraph, CrewAI, and AutoGen), keep costs in check, and avoid the failure modes that sink pilots.
If your charter includes cutting process backlogs, accelerating time-to-decision, and shipping production-grade multi-agent systems with measurable ROI, AI Agents at Work is your launchpad.
Dr. Scott Burk is the founder of It’s All Analytics. He is the author of eight books on AI, data science, and analytics, including the It’s All Analytics Series. He currently teaches in the MS in Data Science program at CUNY and has taught and developed curriculum at Baylor, Texas A&M, and SMU. He has solved complex AI, statistical, and analytical problems at Dell, Texas Instruments, PayPal, eBay, Overstock.com, healthcare organizations, energy firms, semiconductor and manufacturing companies, startups, and many others worldwide. Scott holds a BS in biology and chemistry, MS degrees in finance, statistics, and data mining, and a PhD in statistics. Data has been the unifying thread across his professional experience.
Kinshuk Dutta is a technology leader with nearly two decades of experience driving innovation in Data, Integration & Cyber Security. He is the co-author of the recent best selling Data for AI, founder of Be Cognizant of Data (datanizant.com) where he advocates for responsible data practices and AI enablement, a named inventor on AI patent. Kinshuk is a Senior Member of IEEE, recognized for shaping the future of intelligent systems and guiding organization through AI-driven transformation.
Harman Kaur is an R&D leader focused on AI and automation with nearly a decade of cybersecurity experience and is a named inventor on multiple AI patents. She is a Cyberspace Operations Officer in the United States Air Force with 13 years of service across Active Duty and Reserve component. Harman holds an MBA from the University of Southern California.
Please complete all fields.
