Industrial Excitement Labs
AI workflows
Six artificial intelligence (AI) workflows built for a real team, and a proposal for an agency, each with a demo you can run. Each demo opens in its own window, with the same display and accessibility settings as this page.
Try this first: the six workflows built for a real team.
Built for a real team
Six AI workflows from a Claude plugin I built for a real content team, shown on an invented payments product. Each one says how it was built, how I tested it in Claude and Gemini, and what it delivered.
WorkflowsReal workWorkflow: the audit and reporting loop
One weekly run reads the whole help centre, checks it against the Content Design System, and publishes a report with a prompt for each issue. The fix pass waits for approval.
WorkflowsReal workWorkflow: customer insight to content
It reads the support history for customers' own words and the questions the chat bot handed to people. Then it drafts the missing article, with evidence beside every line.
WorkflowsReal workWorkflow: AI-readiness and answer engine optimisation (AEO)
It checks content against the Content Design System and four extra checks for AI search. Then it asks the same customer questions before and after the fixes.
WorkflowsReal workWorkflow: the media and course pipeline
One spec becomes a script, a voice-over, captions, a video, a course lesson, and a reference card. The pipeline releases nothing until a person has listened to every line.
WorkflowsReal workWorkflow: research synthesis
Survey comments, reviews, support conversations, and interview notes become behaviours and opportunities. A person checks the tagging and ranks the opportunities.
WorkflowsReal workWorkflow: journey and blueprint
A journey and service blueprint for a chargeback, then a future state that shows where an AI agent acts and where a person takes over.
Proposed for an agency
An example project: eight research workflows for a design and advertising agency, and the research hub to run them from. People keep every decision, and every run ends with a visual decision report.
The workflow runner lets you edit, drag and drop, and send results to a project plan. The research hub shows the portal a team would use every day, with its safeguards working.
WorkflowsProposalWorkflow runner: five research workflows
Interview synthesis, feedback and intent, an answer engine audit, a behaviour digest, and a journey draft. Each one stops for a person, and ends with a visual decision report.
WorkflowsProposalResearch hub demo: the agency portal
Start a project, follow every run, review AI drafts beside their evidence, search past research, and try to break the safeguards.