AI workflow playbooks
Practical AI workflow designs for real business work.
These field guides show how to scope AI assistance around source systems, review steps, controls, and evaluation metrics before trusting automation in an operating workflow.
Browse by operating area
Find the workflow pattern closest to your work.
Compliance
Implementation patterns for AI workflows that need change control, evidence, review paths, and clear boundaries.
1 reviewed playbook
Knowledge workflowsKnowledge
Patterns for retrieval, source freshness, permissions, and review when teams use AI over internal policies and docs.
1 reviewed playbook
Accounting workflowsAccounting
Practical workflow designs for invoice, reconciliation, month-end, and audit-support work where accuracy and review trails matter.
1 reviewed playbook
Workflow guides
Detailed examples with controls, evals, and handoff points.
Model evaluation change control
A practical AI workflow for reviewing model, prompt, retrieval, and tool changes before they reach production.
- Work item
- Reviewing AI system changes before release
- Human review
- required
HR policy RAG evaluation
A source-grounded evaluation workflow for internal HR policy assistants where freshness, permissions, and escalation matter.
- Work item
- Checking whether an HR policy assistant answers from the right source
- Human review
- required
e-Fatura reconciliation
A Portugal-specific accounting workflow for comparing e-Fatura records, ERP data, supplier records, and accountant review queues.
- Work item
- Reconciling e-Fatura records against internal accounting data
- Human review
- required
Have a messy workflow?
Send the work item, source systems, and current failure mode.
The useful first step is usually a small review loop: what data enters the workflow, what should stay deterministic, where a model can help, and which decisions need a person in the loop.