IT & Data
Legacy system documentation generation
Generate readable documentation for undocumented legacy systems — data models, integration points, business logic, and dependencies — from source code, database schemas, and configuration.
50–70%
reduction in system discovery effort
Opportunity assessment
Minor improvement. Small efficiency gain with limited effect on overall turnover or bottom line.
Moderate effort. Requires configuration, prompt engineering, and testing. A capable team can get there but expect several months.
Light data requirements. Uses straightforward inputs — documents, product descriptions, customer records — that are usually accessible with minimal prep.
Low risk. Limited external exposure. A human reviews output before it reaches anyone outside the team.
Very easy to absorb. Runs quietly in the background or gives people a helpful new input. Makes everyday work easier with almost no friction.
Tooling required
Things to consider
Undocumented legacy systems are the single biggest hidden cost in most replatforming programmes, and the knowledge usually lives with two people who are close to retirement. Capturing it has value even if you never replace the system.
The model will describe what the code does, not why it does it. The business rationale for an odd rule still has to come from a person — use the generated documentation as the interview prompt.
Treat the output as a draft to be verified, not as fact. A confidently wrong description of a payment routine is more dangerous than a blank page.
Experiment starter: Pick one system a replatforming programme depends on. Generate the documentation, then have the two people who know it best mark it up. Time how long the markup takes versus the estimate for documenting from scratch.
Go deeper in the playbook
Section — Opportunity Identification, including the AI Opportunity Assessment ScorecardSection — The Experimentation FrameworkThis is an augmentation opportunity — see the relevant playbook section for how to approach it.More in IT & Data
IT service desk triage and deflection
Classify and route inbound IT tickets, resolve common requests through self-service, and draft first-line responses for the remainder using the internal knowledge base and past resolutions.
AI coding assistance for internal development
Equip internal developers with an AI coding assistant for code generation, refactoring, test writing, and code review, integrated into the existing development environment and review process.
Master data quality anomaly detection
Monitor product, supplier, and customer master data for anomalies — implausible values, duplicates, broken hierarchies, missing mandatory attributes — and route corrections to the owning team.
AI Transformation Playbook
Ready to assess your own opportunities?
The playbook gives you the full 150-opportunity directory, scoring tools, and 100+ templates for every stage of an AI transformation programme.