Agentic Workflow Specialist

The opportunity

Redesign complex business work into effective human-agent workflows and translate process intent into executable orchestration, controls and acceptance criteria.

What you will be doing

• Decompose processes into goals, tasks, decisions, tools, exceptions and hand-offs suitable for agent execution.
• Design multi-agent orchestration, human approvals, escalation paths and fallback behavior.
• Define business rules, permissions, audit points and workflow-level acceptance criteria.
• Configure suitable workflow, automation or low-code components and collaborate on custom implementation.
• Facilitate simulation, user testing and iterative workflow improvement.
• Measure cycle time, quality, effort, throughput and other workflow-value indicators.

What we need from you

• 5+ years in process transformation, intelligent automation, business analysis, product ownership or workflow implementation.
• Strong process-mapping, requirements, controls and facilitation skills.
• Working knowledge of agents, APIs, workflow engines, low-code platforms and human-in-the-loop design.
• Ability to bridge operational users and engineering teams in agile delivery.

Relevant AI technologies and tooling

• Practical ability to model processes using BPMN or an equivalent notation and translate them into deterministic, agentic and hybrid orchestration patterns.
• Working knowledge of agent concepts including tools, state, memory, hand-offs, human approvals, exception paths, audit events and structured outputs.
• Experience with at least one workflow or low-code platform such as Microsoft Copilot Studio and Power Automate, Camunda, UiPath, n8n or equivalent; exposure to LangGraph or similar graph-based orchestration is desirable.
• Ability to define tool contracts, business rules and acceptance tests with engineers, including permissions, fallbacks, timeouts, retries and escalation criteria.
• Experience with process mining or task analysis tools such as Celonis, Microsoft Process Mining or equivalent is advantageous for identifying and measuring automation opportunities.

Measures of success

• Workflow value and performance improvement
• Quality of process and exception design
• User acceptance and adoption
• Reduction of manual hand-offs and unresolved exceptions
• Clarity of acceptance criteria and controls

Key interfaces

• Other members of the AI Transformation & Agentic Systems Practice
• PwC sector, functional, cloud, cyber, risk, Responsible AI and change specialists
• Client business owners, product owners, technology teams and operational users
• Technology alliance and implementation partners where relevant

Contribution to the practice

• Support proposals, client workshops and market development appropriate to seniority.
• Contribute reusable methods, patterns, code, assets and lessons learned.
• Coach colleagues and participate in the capability’s continuous learning agenda.
• Uphold PwC quality, independence, confidentiality and risk-management requirements.