This two-day programme is built for business analysts and the product, requirements and delivery professionals who work on the same change. Business analysis produces the written record of that change: interview notes, requirement lists, user stories, process maps, data models, business cases and the summaries that keep stakeholders aligned. Generative AI drafts, structures, compares and summarises that record well, and an AI agent goes one step further: given a goal, it reads a raw backlog, applies the analysis rules, flags duplicates, conflicts and ambiguity, drafts the first user stories and hands the result to the analyst for review. The decisions that follow sit with the analyst: which work is handed over, under which rules, and on what evidence the result can be trusted in front of a stakeholder.
Day one establishes how generative AI works, takes every participant through structured prompting on their own analysis tasks, and applies AI across the business analysis lifecycle: elicitation and stakeholder communication, requirements specification and process documentation, and data modelling, analysis and insight generation. Day two moves from assistants to agents. Participants design and build a requirements analysis and user story agent on a customer portal backlog carrying realistic ambiguity and planted edge cases, instrument it and read its traces, metrics and costs, then set the rules under which AI-assisted analysis is acceptable in their organisation. The ninety-day plan closes the programme.
Every lab runs 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 each lab is verified against fixed acceptance criteria. Participants leave with a working requirements agent, a business analysis prompt library, an evidence pack of traces and metrics, governance starting points for AI in analysis work, and a ninety-day plan for their role. The programme finishes on where the field is heading: agentic AI, where an agent is given an analysis goal and plans and executes the work under the analyst's supervision, with context engineering, loop and graph engineering, agentic retrieval-augmented generation, the Model Context Protocol and multi-agent patterns.