Foundation · Start here
Foundation
The first step into AI at Xebia: what the models actually do, where they help, where they fail, and the habits to build before anything else.
AI Usage Playbook
Foundation first. Then the common ground. Then your specialisation.
Foundation builds the baseline understanding of AI. The common playbook sets the operating model everyone shares — tooling, model choice, cost and privacy. Only then do you move into the stage or lane you actually work in. Each playbook ends with an exam, so progress is something you can prove.
FoundationCommon playbookYour stage or lane
All playbooks
Across all stages
Common playbook
The rules that belong to no single specialization: tooling, model selection, pricing and session economics, privacy and organisation-wide usage.
Stage · Discovery
Discovery and requirements
Framing the problem, clarifying scope, preparing requirements and documenting assumptions with AI support.
Stage · Development
Development
The specialist playbook for implementation work: planning with the agent, coding, review, verification and safe delivery.
Stage · Quality
Quality and testing
Test strategy, meaningful test generation, defect prevention and review of the edge cases people miss.
Lane · Data
Data playbook
A lane of its own: data preparation and lineage, experimentation, evaluation standards, governance and controlled access.
How to use the playbooks
Open Foundation. Build the baseline before any specialist guidance.
Read the common playbook. Tools, models, cost and privacy in one place.
Go to your stage or lane. Local standards for your role and deliverable.