University of Cambridge Judge Business School Executive Education
Programme finder

From AI pilots to scalable agentic workflows

Agentic AI: Design, Build, Govern

A 3-day, hands-on Cambridge programme where you build and stress-test AI agents, confront their limits, and design governance that makes them production-ready. Leave with a faculty-reviewed 90-day roadmap to launch your first agentic workflows.

Apply now
Next date
18 Nov-20 Nov 2026
Duration
2 days
Format
In-person
Area
Artificial intelligence (AI)

Overview

Agentic AI represents the next critical evolution in enterprise technology. While generative AI produces content, agentic AI takes action by planning, executing multi-step workflows, and adapting autonomously. Yet fewer than 12% of organisations have moved agentic AI beyond piloting. The barrier to scale is no longer the technology but the infrastructure. Moving beyond pilots requires a new operational blueprint focused on clean data, system visibility, and reimagined human-AI workflows.

In our hands-on labs, you build, deploy, and deliberately stress-test agent systems. This ‘break-to-build’ approach reveals the exact line between agent capability and system failure. You master the emerging standards, including MCP and A2A, to ensure your technical roadmap prioritises compatibility over restrictive vendor lock-in.

This programme redefines your operational design. You leave with a framework for defining autonomy levels and a faculty-reviewed 90-day action plan to launch your first agentic workflows. By balancing Cambridge rigour with practitioner reality, you gain the informed challenge and oversight required to lead in a world of autonomous agency.

Why attend the Agentic AI: Design, Build, Govern

Business challenges solved

  • Master agentic strategy: move beyond the hype to develop a genuine understanding of how autonomous systems work and how to assess them.
  • Gain practical experience: build and stress-test agent systems on a no-code platform to understand their capabilities and their limits.
  • Evaluate vendor claims: acquire the frameworks you need to challenge architectural decisions and vet third-party solutions with confidence.
  • Ensure production readiness: identify the governance and system visibility requirements that move AI agents from simple experiments to reliable enterprise tools.
  • Build your roadmap: leave with a concrete, expert-validated 90-day action plan tailored to your organisation’s specific growth targets.

Outcomes

  • Accelerate production deployment: move beyond experimentation and transition agentic AI into live, value-generating enterprise systems.
  • Optimise build-versus-buy decisions: equip your leadership to evaluate total cost of ownership and protocol standards before committing to long-term vendor contracts.
  • Ensure regulatory compliance: establish robust governance frameworks that align with the EU AI Act and emerging UK regulatory standards.
  • Achieve strategic clarity: master the distinction between workflow redesign and agent overlay to ensure your implementation delivers a genuine competitive advantage.
Business challenges solved
  • Master agentic strategy: move beyond the hype to develop a genuine understanding of how autonomous systems work and how to assess them.
  • Gain practical experience: build and stress-test agent systems on a no-code platform to understand their capabilities and their limits.
  • Evaluate vendor claims: acquire the frameworks you need to challenge architectural decisions and vet third-party solutions with confidence.
  • Ensure production readiness: identify the governance and system visibility requirements that move AI agents from simple experiments to reliable enterprise tools.
  • Build your roadmap: leave with a concrete, expert-validated 90-day action plan tailored to your organisation’s specific growth targets.
Outcomes
  • Accelerate production deployment: move beyond experimentation and transition agentic AI into live, value-generating enterprise systems.
  • Optimise build-versus-buy decisions: equip your leadership to evaluate total cost of ownership and protocol standards before committing to long-term vendor contracts.
  • Ensure regulatory compliance: establish robust governance frameworks that align with the EU AI Act and emerging UK regulatory standards.
  • Achieve strategic clarity: master the distinction between workflow redesign and agent overlay to ensure your implementation delivers a genuine competitive advantage.

Who should attend this programme?

Attendees include:

  • Senior leaders making strategic decisions about agentic AI deployment (C-suite, VP and Senior Director roles).
  • Leaders in strategy, operations, technology, digital transformation or innovation functions.
  • Professionals steering their organisations towards agent-based systems and seeking to bridge the pilot-to-production gap.
  • Managers looking to understand the governance, data readiness and operational requirements for agentic AI at scale.

Please note you are not expected to be an expert in AI programming, as we will be using no-code platforms.

What you will learn

Module 1: Understanding agentic AI (taxonomy, memory, RAG)
  • Structured debrief of pre-work agent interactions. Surfacing assumptions and establishing shared vocabulary.
  • Hands-on laboratory: rotate through four agent types — simple assistant, task agent with tools, autonomous research agent, and a deliberately ‘agentwashed’ tool. Observe reasoning, tool use, and memory in action.
  • Agent taxonomy: assistants, task agents, autonomous agents, and multi-agent systems. Decision framework for selecting the right approach.
  • Agent memory architectures and their strategic implications. Introduction to data readiness and RAG as the bridge between agents and enterprise knowledge.
Module 2: Navigating hype (diagnostic framework for ‘agentwashing’)
  • The ‘agentwashing’ phenomenon: a diagnostic framework for evaluating vendor claims. This lens applies throughout the remainder of the programme.
  • Live failure demonstrations: agents hallucinating, failing silently, going off-rails, amplifying bias, and leaking data. Distinguishing fundamental limits from areas of rapid improvement.
Module 3: Building and connecting (hands-on lab: MCP/A2A protocols)
  • Hands-on laboratory: build an agent for a business task from your pre-work brief. Configure skills and tools using MCP-style connections. Connect to data sources via RAG. Iterate as design choices shape behaviour.
  • Protocols and standards: MCP (Anthropic), A2A (Google), and ACP (IBM). Strategic implications for interoperability, vendor lock-in, and platform architecture.
  • Enterprise case study and practitioner panel: what worked, what failed, the real costs, and the workflow redesign required.
Module 4: Operational governance (lab: stress-testing and breaking agents)
  • Hands-on laboratory: systematically break your Day 1 agent. Adversarial inputs, prompt injection, edge cases, and tool manipulation. Design governance protocols in response.
  • Governance and trust frameworks: bounded autonomy, audit trails, and explainability. A practical four-level autonomy framework from human-directed to fully autonomous. Human-in-the-loop versus human-on-the-loop.
  • EU AI Act and emerging UK regulatory landscape. Positioning governance as an enabler of deployment.
Module 5: From pilot to production (observability, ROI, AgentOps)
  • Observability and agent operations: tracing multi-step reasoning, evaluation frameworks, cost monitoring, latency tracking, and regression detection. The observability stack: what to build, what to buy.
  • Economics of agentic AI: real deployment costs, cost optimisation as an architectural discipline, ROI measurement. The emerging agent ecosystem.
  • Workflow redesign versus agent overlay: why overlaying agents on legacy processes rarely succeeds at scale.
Module 6: Leading the agentic organisation (90-day action plan)
  • The tool-coworker challenge: agents defy the traditional tool-versus-worker binary. Four tensions leaders must navigate. Designing operating models for human-agent collaboration.
  • Skills and talent strategy: three layers of capability (agent skills, team skills, leadership skills). New roles and build-versus-hire-versus-upskill decisions.
  • Facilitated roadmap session: peer groups develop a 90-day action plan. Faculty and peer challenge. Presentations and close.

Why choose Cambridge Judge Executive Education

Cambridge Judge faculty

All of our programmes are designed and led by Academic Programme Director, who is a member of Cambridge Judge Business School faculty. They will also deliver substantial portions odf that programme.

Leading-edge research

The research conducted by Cambridge Judge Business School’s 20 research centres, across a diverse range of disciplines, flows directly into all of our programmes, bringing new insights to our programme content.

Small group learning

With small class sizes, we continue the Cambridge way of learning that emphasises high levels of interaction with both our world-class faculty and peers.

Fees and upcoming dates

What’s included with your fee

Fees include instruction, materials, lunch and breaks. Preferential rates may be available for groups, University of Cambridge alumni and members of the School’s Alumni Association. VAT is charged at the prevailing rate, which is currently 20%. Please note prices pre-registration are subject to change.

18 Nov-20 Nov 2026

  • In-person
  • 2 days

£5,000 + VAT

Apply now

20 Jan-22 Jan 2027

  • In-person
  • 2 days

£5,000 + VAT

Apply now

Artificial intelligence (AI) insights

View all
View all