Duncan AndersonIndependent systems
Back to selected work

Business monitoring · Production operations system

The Lineup AI Operations

Four specialized AI workers monitor the business—but they cannot quietly change production.

The result

The recurring checks now happen on a schedule, issues are kept in one review queue, and production changes cannot happen without explicit approval.

What can be verifiedFounder, system designer, and operator

Before this system, I moved between scripts, dashboards, and notes to check whether feeds were stale, models had run, growth work needed attention, or a business commitment was slipping. Now the relevant worker records the issue, recommends one next step, and stops if that step could alter production. A completed check is not treated as a completed fix.

  1. 01Four named workers in one review system
  2. 02Scheduled and manual checks with a recorded finding and next action
  3. 03Approval and reliability checks keep incomplete or blocked work visible
How the system worksIllustrated example

The Lineup

Business monitoring

Four workers
Data and pricing
Models and forecasts
User growth
Business priorities

Latest finding

Freshness issue needs review

01Issue recorded
02Next step proposed
03Production change paused
Duncan must approve the change

Illustration based on the private review dashboard · no production data shown

What changed

Before

  1. 01I checked provider feeds, model jobs, growth work, and business priorities in separate places.
  2. 02A finished automated check did not prove that the underlying problem was fixed.
  3. 03Any action that could affect customers or production needed to stop for approval.

After

  1. 01Four workers run on a schedule or when I ask for a specific check.
  2. 02Each material issue is recorded with one proposed next action and its current status.
  3. 03Production changes wait for approval, and a fix is only marked complete when newer evidence supports it.

What I owned

I built four internal workers for the checks I was repeatedly doing by hand. One watches sports data and prices, one watches model jobs and forecasts, one watches customer growth, and one reviews business priorities. Each worker records what it found and proposes one next action.

  • 01The shared request and review system
  • 02Workers for data, models, growth, and business priorities
  • 03Approval rules that stop protected production changes
  • 04The review dashboard, reliability checks, and automated tests

What still needs a person

The workers can inspect and recommend; they cannot quietly deploy, suppress a model, contact a customer, or make another protected production change. I review and approve those decisions. The system also keeps a check separate from a verified fix.

Technical detail

PythonNext.jsPostgreSQLSupabaseAutomation schedulingApproval checksReliability tests

Have a similar operating problem?

Bring one recurring process and the point where it keeps breaking. We will decide whether it has a clear enough finish line for a sprint.