Examples

What good automation looks like

Anonymised composites of real scenarios — not client logos or guaranteed metrics. Each one shows the problem, the outcome, and where the human stays in the loop.

Supervised

Inbox triage (supervised)

Problem

Small team gets the same questions daily. Replying takes hours.

Outcome

Draft replies from your knowledge base. Human approves before send. Billing escalates.

Script

Weekly client update

Problem

You ship every week but client updates lag — summarising what changed is tedious.

Outcome

Script collects completed items, groups by topic, produces a draft. Human reviews, then sends.

Local

Local document assistant

Problem

Contract work under confidentiality. Uploading to a public AI site is not acceptable.

Outcome

Local indexing and queries on your machine. Nothing leaves unless you copy it out.

Skip

When we said: don't automate

Problem

Owner wanted AI to make strategic decisions that change weekly.

Outcome

We documented why automation would cost more than it saves. Proposed a checklist instead.

Have a workflow in mind?