The practical AI library
AI workflows with something useful at the end
Work through financial commentary, contract obligations, meeting follow-ups and an internal-tool prototype with sample inputs and acceptance checks.
A workflow connects preparation, an AI-assisted step, review and a usable output. These examples include deliberately incomplete information so you can see where a good result should stop and ask for evidence. Try the fictional inputs before deciding how to use a workflow at work.
Choose an outcome
Turn meeting notes into action items with AI
Use a copyable prompt and action-item template to extract owners, deadlines and dependencies from meeting notes, then review before creating tasks.
WorkflowsBuild internal tools with AI: start with a request tracker
Build and evaluate a request-tracker prototype with a copyable brief, fictional data and permission checks. Compare an AI builder with an existing form.
WorkflowsExtract contract obligations with AI: build a checked register
Extract contract obligations with source clauses, owners and timing rules. Use a fictional agreement, copyable prompt and manually checked answer key.
WorkflowsWrite budget variance commentary with AI and source evidence
Turn a reconciled budget-versus-actual table into checked commentary. Includes fictional figures, an evidence-led prompt, answer key and review handoff.