This two-day programme is built for project managers, programme managers and PMO leads who have to decide where AI belongs in project delivery. Project and programme work runs on documents and data: charters, schedules, risk registers, contract packs, minutes, progress reports and steering packs. Generative AI drafts, compares, extracts and summarises that material well, and an AI agent goes one step further: given a goal, it reads the plan, the risk register and the budget, flags what is blocked, overdue or at risk, and drafts the weekly status report for the project manager to review. The decisions that follow sit with the delivery leader: which work is handed over, under which checkpoints, and on what evidence the result can be trusted in front of a sponsor.
Day one establishes how generative AI works, takes every participant through agentic prompting on their own project documents, and applies AI across the project lifecycle: documents and reporting at project scale, planning, risk tracking and resource forecasting, and stakeholder communication. It closes with what an AI agent is and how a working routine becomes a reusable agent skill. Day two builds. Participants construct a project health and status report agent on a project carrying live tasks, a risk register and a budget with planted edge cases, instrument it and read its traces, metrics and costs, then lift the view to programme level: cross-project visibility, dependency tracking, benefits realisation and the executive brief. Data governance, responsible use and the ninety-day plan close the programme.
The build labs on day two run in a pre-configured cloud environment opened from a browser, with no software to install. Participants choose a visual build track or a coding-agent track, and the project agent is verified against fixed acceptance criteria. Participants leave with a working project health agent, a project prompt library and reusable agent skills, an evidence pack of traces and metrics, governance starting points for AI in project delivery, and a ninety-day plan for their projects and programmes. The programme finishes on where the field is heading: multi-agent orchestration, context engineering, agentic retrieval-augmented generation, loop and graph engineering, and agentic browsers.
