Case study · 2025 → 2026 · AI adoption across a 20+ team

The agentic marketing stack

I started as a Salesforce developer, so when the team needed better instruments I built some of them and specified the rest. The pattern that held: give people an agent that remembers, and report only what changed.

Architecture only on this page. The code and its data belong to my employer; what follows is how the systems are designed, which is the part that transfers.

1. The SEO monitor: git as memory

A small engine I built with Claude Code runs on a schedule. Each run pulls Search Console, scores two things that matter — pages within striking distance of page one that earn no clicks, and query groups where the site competes with itself — and then diffs against the last snapshot committed to the repository. The report is a delta: NEW / RESOLVED / PERSISTENT, posted to the team's chat and committed back as the next baseline. Nobody reads a dashboard; everybody reads a diff.

Two design rules came from being wrong. The engine never exits non-zero — health is judged by the report's title, so a failed run is loud and a green check is not proof. And after the monitor once cried wolf, we added statistical guards (a longer control window, a trend window, impression floors) and wrote the post-mortem into the operating manual.

Run loop: checkout the repo → pull the last 14 days → score striking-distance and cannibalisation → resolve query→URL → fetch live titles → diff vs the last committed snapshot → write the full report and CSVs → post the short version → commit the snapshot. The repo is the memory.

2. Competitive intelligence that runs itself

I specified this one and a member of my team built it. A weekly workflow fetches four competitors' sitemaps, diffs them against last week's state kept in a spreadsheet, asks a language model for a short read-out on what shipped, and posts the digest. Fifteen minutes of a marketer's Monday, every Monday, without a marketer.

3. AI adoption as an operating change

The point was never a tool; it was that a 20-person team could ask an agent to draft, audit, or measure and get something reviewable back. We standardised on a small set of workflows — content briefs from search intent, on-page audits, answer capsules for AI-search visibility, outreach research — and wrote the rules of use down, including what an agent is not allowed to decide.

What I'd do differently

Write the statistical guards first. A monitoring system that can raise a false alarm spends its credibility faster than it earns it.

Proof

  • STATED Architecture as described; a redacted sample report is available on request. The essay on AI-search visibility draws on the same programme.

Every figure on this page carries a proof badge. PUBLIC links open for anyone; THIRD-PARTY corroborates direction from an independent source; STATED is internal analytics, quoted with its date, with a walkthrough available in conversation.

← A Q&A community from zero to 20K visits a month · Taking over sales enablement →