A twelve-person marketing team, rebuilt around AI

The situation

An in-house B2B marketing team was carrying twelve people across LinkedIn, email, blog, SEO, and sales outreach. The work was real, but most of it was high-frequency and low-judgment: exactly the shape that gets expensive when humans do it and gets sloppy when a large model does it carelessly.

What we did

We built a coordinated AI system that sized each task to the smallest model that could do it: a fast, cheap model for high-frequency work, a stronger model reserved for judgment calls. Both sat behind a deterministic harness that handled sequencing and formatting, so the models only did the part that actually needed a model.

Custom MCP connectors wired the system into the real stack, meaning Apollo, HubSpot, and a custom Outlook connector, instead of a parallel universe of exports. Sales staff review every outbound message before it leaves.

The result

The team went from twelve to 2.5 FTE at roughly $33 a month in model spend. The cost story is striking, but the transferable lesson is the architecture: most of what a marketing team does does not need a frontier model, and a deterministic harness around cheap models beats an expensive model doing everything.

• Operating leadership · Multi-sector · Lower-middle-market portfolio

  Growing portfolio revenue from $10M to $180M

• M&A · Healthcare · Media · B2C · Revenue cycle management

  Buying and selling companies, and getting the deal closed

• Turnaround · Out-of-home media

  A million a month in losses, taken to break-even