Information architecture is the work that decides whether Copilot succeeds
Generative AI answers are only as good as the content behind them. The preparation that determines quality happens before any licence is assigned.
Practice Lead, AI and Copilot
Nadia Farouk
Nadia leads Avanteria work on Copilot, agents and retrieval. She spends most of her time on the part of generative AI that decides whether it succeeds: the content it is grounded on, the permissions it inherits, the review points around it, and whether people still use it three months after launch.
Focus areas
- Microsoft 365 Copilot
- Copilot Studio
- Retrieval design
- Responsible AI
- Adoption measurement
Published
5 pieces by Nadia Farouk
What actually blocks a Copilot rollout
Licensing is rarely the constraint. Five things stop deployments in practice, and four of them are decided before any technical work starts.
A practical Copilot readiness guide
A structured way to assess whether an organisation is ready to deploy Microsoft 365 Copilot, covering data, permissions, licensing, governance and adoption.
Grounding quality is a content problem, not a model problem
When a grounded assistant gives a wrong answer, the model is usually working correctly. Where the fault actually lies, and how to find it.
Designing agents that know when to stop
The most important design decision in an AI agent is the boundary: what it must not attempt, and what happens when it reaches the edge.