Case study, 2026
AI CMO: a digital marketing lead that plans, drafts and learns from the numbers
Small teams know what to say, but rarely have the time to plan, write, publish and measure every week.
What I built
- The concept: a digital CMO that turns business goals into a weekly marketing plan and keeps it moving.
- Specialist agents research the audience, plan the calendar, draft the content and review what performed.
- Every post and every budget change waits for a person to approve it.
This is confidential client work, so the product name is a stand-in and there are no product screenshots. The architecture and the sample run show how it works.
- Multi-agent systems
- Tool calling
- Analytics connectors
- Human approval
How it works
Select any node to see what it does.
- 00.00cmogoal: more demo bookings this month
- 00.28researchertop questions from the audience gathered
- 01.05plannerfour week content calendar drafted
- 01.52writerfirst three posts waiting for approval
The architecture, step by step
Each part of the diagram, in the order a run moves through it.
- Business goalWhat the business wants this month, in plain words.
- CMO agentTurns the goal into a plan and keeps every step moving.
- ResearcherLearns what the audience asks about and what competitors say.
- PlannerBuilds the content calendar around the goal.
- WriterDrafts posts and emails in the brand voice.
- AnalystReads the results and suggests what to change next.
- ToolsThe agents act through the brand guide, social channels, analytics and approvals.
Related work
Crewline
A platform that provisions digital employees.
AI CFO
A digital finance lead that reads the books and explains them.
Pathfinder
A multi-agent assistant for the whole job search.
Study Mode
Gemini-powered study sessions built from your own notes.
Research crew
A team of agents that researches a market and writes the brief.
Knowledge assistant
Answers from company documents, with every claim cited.
Evals and tracing
Every agent run traced, scored and compared before it ships.