01 The pitch

Most companies are being sold AI tools. What they actually need is AI operators — someone to figure out where agents make sense in their marketing function, build them, and keep them running.

That's the job. I draw on a library of 60+ pre-built marketing agents, configure the ones that fit your business, and build custom ones where nothing off-the-shelf works. You end up with a small number of agents doing specific, useful work. Not a dashboard of demos.

02 What agents can do

Six categories. 60+ agents. All configurable.

Every agent can be tuned to your business, your ICP, your tools, and your decision logic. Below are the categories, with a few named examples in each. Most clients use 3–6 agents — we scope which ones during setup.

Keyword research
07 agents
  • Seed KW Expander — turns seed keywords into a full opportunity map filtered by your ICP.
  • Long-Tail Miner — surfaces high-intent, low-competition variations aligned to your priorities.
  • SERP Intent Analyser — maps SERP intent to the content types worth producing.
Content strategy
09 agents
  • Cluster Builder — builds topic clusters from your keyword data, mapping pillar to supporting content.
  • ICP Content Prioritiser — filters opportunities through your ICP so you rank for things that convert.
  • Article Brief Generator — produces structured briefs ready for the content engine.
On-page & technical
09 agents
  • On-Page SEO Scorer — scores pages against your criteria and surfaces prioritised fixes.
  • Schema Generator — identifies schema opportunities and produces validated markup.
  • Internal Link Opportunity Finder — surfaces specific link opportunities between pages.
Link building
06 agents
  • Competitor Backlink Analyser — finds replicable, high-value links from competitor profiles.
  • Digital PR Angle Generator — produces data-led PR angles from your expertise and industry news.
  • Link Velocity Tracker — monitors link acquisition and flags penalty-risk anomalies.
Competitive intel
06 agents
  • Competitor Top Page Tracker — alerts when a competitor publishes content worth countering.
  • Share of Voice Calculator — measures your share of voice across target keyword sets.
  • Cluster Competitor Analyser — maps competitor coverage to reveal strategic gaps.
Reporting & planning
08 agents
  • Weekly Digest Generator — writes a weekly marketing update from your analytics stack.
  • Content ROI Scorer — scores content by conversion contribution, not just traffic.
  • Content Decay Alerter — flags traffic and ranking decay before losses become significant.
— 45+ more agents available · custom builds where nothing fits
03 How it works

From conversation to running system.

No off-the-shelf dashboard. No generic automations. The agents are built around how your business actually works — and they live inside the tools your team already uses.

STEP 01
We work out which agents you need
Not all 60. Usually 3–6. We sit down, look at your marketing function, and identify where agents would meaningfully save time or produce better output than whatever's happening now.
STEP 02
I configure them to your business
Your ICP, your product, your decision logic, your output format. Each agent is tuned to your company — not configured to an industry average. Custom-built where no pre-built agent fits closely enough.
STEP 03
They plug into your stack
Output lands in the tools your team already works in — your CMS, your analytics, Slack, a shared doc, email. No new interface to learn. No separate platform to log into.
STEP 04
I run them, you review
Ongoing ops: monitoring, maintaining, tuning as models and markets change. You get the output. I keep the machines working. Documentation lives in your drive — no black box, no lock-in.
04 Who does what

I build and run. You provide context and sign-off.

Agents only work when the inputs are right. Here's what each side is on the hook for.

— I do this
  • Scope which agents make sense for your business
  • Configure agents from the 60-agent library to your context
  • Build custom agents where nothing off-the-shelf fits
  • Integrate agents with your existing stack (CMS, analytics, Slack, CRM)
  • Monitor, maintain, and retune agents as models and markets shift
  • Document everything in your drive so you're never locked in
— You do this
  • Give me access to the data and tools the agents need to run
  • Provide the context — ICP, product, decision logic, quality standards
  • Review and sign off on configuration before anything goes live
  • Act on the output — agents surface insights, your team makes decisions
  • Flag when something upstream changes (new product, new market, new ICP)
05 Who this is for

Agents work best when the business is ready for them.

This is a fit if

  • You have repeatable marketing tasks eating time — research, reporting, competitive monitoring, briefs
  • You have a small marketing team (1–10) and no appetite to hire five more
  • You have a clear ICP, product, and sales motion — agents need context to be configured well
  • You're willing to let automation take on judgment-free work, so humans can do the rest
  • You want to own the documentation so you're never held hostage by the person running this

Not a fit if

  • You want a ChatGPT subscription and some prompt templates — that's a much cheaper problem
  • Your marketing doesn't know what it's doing yet — agents amplify what's there, not invent it
  • Your data is genuinely chaotic — we'd fix the data problem first, agents later
  • You expect agents to replace strategy or judgment — they don't, and they shouldn't
  • You want one "AI assistant" to do everything — specialised agents beat one generalist every time
06 Honest answers

Three things people ask me before they sign anything.

"Isn't this just Zapier with a nicer name?"

Zapier connects tools and triggers actions. Agents make decisions. The difference matters: a Zap sends the same email every time a CRM field updates; a competitive-intel agent reads a competitor's blog post, decides whether it's worth flagging, writes the summary, and drops it in Slack only if it meets your criteria.

Zapier is plumbing. Agents are the thinking layer sitting on top of the plumbing. Often I'll use both — a Zap to handle the trigger, an agent to handle the judgment.

"What happens when the model breaks or you stop working with us?"

Everything gets documented in your drive from day one — the configuration, the prompts, the integrations, the review steps. If I disappear tomorrow, another competent operator can pick it up. The agents live on your stack, not mine.

On models breaking: this is an ongoing ops cost, not a surprise. Providers shift, capabilities change, prompts drift. Part of the monthly fee is me watching that, retuning when something degrades, and swapping underlying models when something better ships.

"How do I know any of this is working?"

Before we build anything, we define what "working" looks like for each agent — hours saved, briefs shipped, alerts that actually triggered the right action. That becomes the review metric.

Monthly, you get a one-page report: what ran, what it produced, what it cost in time and dollars, what changed. If an agent isn't earning its keep, we retire it. No agent runs indefinitely just because it was built once.

07 Pricing

Priced per agent. Scales cleanly.

Each agent has a one-off build fee and a monthly operating fee. No packages, no tiers, no "unlimited agent" plans. You pay for what you run.

— Per agent

Build & configure

from$1,200
/ £950 · one-time, per agent

Discovery, configuration (or custom build), integration into your stack, and sign-off. Pre-built agents from the 60-agent library come in at the lower end. Custom-built agents, or ones that need complex integrations, scale from there.

Most clients start with 3–6 agents.

— Per agent

Monthly operation

from$450
/ £350 · per agent, per month

Monitoring, maintenance, retuning, model upgrades, monthly performance review. If an agent stops earning its keep, we retire it — you stop paying. No minimum-agent-count fees.

Three-month minimum. 30 days' notice to cancel after that.

— Example · 4-agent build
Setup · 4 agents × $1,200 × 4 $4,800
Monthly ops · 4 agents × $450 × 4 $1,800 / mo
Year one total setup + 12mo $26,400

Pricing shown is a starting point, not a fixed quote. Final numbers depend on agent complexity, integration scope, and whether custom builds are needed. I'll quote properly once we've talked.

08 Start here

Let's work out which agents you'd actually use.

One conversation. We'll look at your marketing function, identify the 3 or 4 agents that would save the most time, and figure out whether this is worth building — or whether one of my other services is closer to what you need.