Intellectual Frontiers Press Fieldbooks

Running the Workforce

Operating an AI Workforce That Finds Who Is Ready to Act, from Its First Scheduled Job to Run

Every job and every gate reads the same dated records.

Quarry Lane Health is an 11-person company that sells a Site Readiness Setup and a platform subscription to independent clinical research sites. Its engineer tests the customer workforce in a March simulation, and the company hires its site development representative through a paid work sample. She runs the workforce from April until it reaches Run in September, and the company then starts a partner workforce on shared infrastructure.

Forthcoming. The book is in review.

Run a readiness workforce every day from dated records in Git, and make every decision that belongs to a person.

Each scheduled job, check, and audit is shown first as a prompt and then as the skill, MCP server, or script that runs it, with the labeled cases it has to pass before it runs unattended. Tools, versions, and law are stated as of the edition, and the online appendix keeps the dated tables current.

What you will be able to do

• run observation, enrichment, probes, and the second research pass as jobs that read and write records;
• check every state change against its gate and every contact against the suppression list;
• turn an operator's correction into a rule change and a test in the same commit;
• build the Actionboard and the audits from the records, then pass the simulation and the Crawl, Walk, and Run gates; and
• add a second workforce and move the automation line only on evidence from your own records.