How it works

The Marketing Brain

Product ships faster than marketing can keep up. The Marketing Brain is how one operator keeps up: it listens to sales calls, customer feedback, competitor moves and roadmap discussions all the time, so when a feature ships, positioning, messaging and every launch asset are already loaded, every team gets armed, and what the launch learns shapes what gets built next.

running today partial on the roadmap
10+
intelligence
sources
1
context
brain
35
PMM
skills
12
assets from
one doc
The 30-second version
The whole loop, at a glance · click any stage
It's a loop, not a line. What ships feeds what's learned, and what's learned feeds the next launch.
How it runs

The loop, stage by stage

The brain is always listening, so launch day starts at ninety percent. When a feature ships, every asset comes out and the whole company gets armed. And it does not stop at ship: adoption and measurement feed back in, shaping the next launch and what gets built next.

00
Intelligence in
The senses. Everything that tells you what to say, landing in one place instead of twenty tabs.
Know exactly how buyers describe the problemGong sales calls · reviews on G2, Capterra, App Store and Google Play (soon)

Positioning and messaging get written from how buyers talk, the language, the objections, the reasons deals are won and lost, pulled from real calls and reviews instead of from guesses.

See what every competitor is doing, liveTheir ads on Google, LinkedIn and Meta · their web pages · screen recordings of their product · a daily file on 20 competitors

A rival's whole strategy, read off what they ship and spend on, and already current the moment it is needed instead of a fresh research project each time.

Nothing the team learns gets lostInternal meetings, captured through Granola and Notion

Every product, sales and strategy conversation is captured and routed in, so it lives in the system instead of in one person's memory.

Every brief fully scoped before buildingA structured interview that captures the full plan first

The work starts from a clear, complete brief, with nothing important left assumed.

01
Memory + context
Memory and retrieval. One context layer that reads all of it at once. The moat is here, not the model.
On-brand, approved, and differentiated messagingEncoded brand voice · approved-copy library · the differentiated positioning

Every draft comes out in the brand voice, consistent with the copy already signed off, and carrying the differentiated positioning, not the generic line any competitor could write.

Every project and decision stays up to dateOperational reference rebuilt twice daily: priorities, people, products, projects, decisions, metrics

One reference covering the live priorities, the people, the products and projects, the decisions made and why, and the latest metrics is rebuilt twice a day from the latest meetings, so the work never runs off stale context. Each skill also keeps its own notes current, so the system sharpens over time instead of starting cold.

Everything ever learned is one search awayOne organised knowledge base · context loads itself for the task

Every project, person, decision and source lives in one place the system reads in full, with the relevant context pulled into whatever is being worked on.

02
Synthesis
The PMM craft chain. Intelligence becomes the launch, one ordered pass per feature.
research audience whitespace positioning messaging pricing GTM plan launch plan enablement
Gates over every draft: buyer-persona test · humaniser · fact-checker · refine-spec · council on high-stakes calls.
how the gates keep the bar high
Buyer-persona test. Every line checked against the real buyer's worldview and ban list before it ships.
Humaniser. Strips AI tells, kills the slop patterns, tightens to spoken rhythm.
Fact-checker. Claims verified against the source before they go out.
refine-spec. Pressure-tests the plan before anything gets built.
Council. A panel of reviewer agents that argues the high-stakes calls from different angles.
03
Outputs
One approved messaging doc fans out to every launch asset, in one voice.
GTM plan Sales one-pager Website updates Help article Blog Founder post Company-page post Messaging doc Lifecycle emails Battlecard Video walkthrough Asset for everyone to post
The engine that already works: the content-refresh skill turns one approved messaging doc into four derived assets in a single pass, with provenance on every claim and an approval gate before anything ships. Generalising that fan-out to the full list is build 01 on the roadmap.
04
Distribution
Arm every team. Each person handed a ready-to-post asset, staged to approve then publish on launch day.
Marketing Sales Product Lifecycle Social Founder Creator team
The rails: social posts staged on LinkedIn, X and YouTube for one-click approval · lifecycle email through the email platform · site updates straight to the website · collateral into the shared drive · internal amplification through Slack. Nothing publishes without a human approving it.
05
Adoption + lifecycle
The launch is not done when it ships. It is done when people use the thing. Move the user from seeing it to adopting it.
Lifecycle email journeys Welcome + onboarding series Activation tutorials · YouTube + in-app Personalised by segment In-app triggers Paid-feature adoption nudges Expansion + retention prompts
The in-app layer: partner with lifecycle and product to design the moment a user starts using a paid feature. Running on email today, the personalised in-app trigger is the next build. The content layer: activation tutorial videos, built from the questions sales and customers actually ask, run on YouTube and sit inside the product to pull users to first use.
06
Measurement
Close the loop. Did it land. What moved adoption, what fell flat, and what the next launch should do differently.
Win/loss capture Launch retro Signal back into the brain Feeds the product roadmap Adoption + usage metrics Campaign-level attribution
The honest gap: today the loop closes by hand, a retro written back into the intelligence layer. Automating the metrics-to-brain feedback is build 03.

The loop closes. What you learn at adoption and measurement feeds back into intelligence in, so the brain compounds and every launch starts smarter than the last.

The proof

Every PMM job, covered

The loop is how it runs. This is what it covers: the full PMM remit, every job mapped to a purpose-built skill, the framework inside it, and honest status on each. None of this is AI out of the box. Each skill encodes how a senior PMM does the job.

Strategy + insight
Competitive intelligence + battlecards
Maps the landscape, builds a battlecard per rival, and turns wins and losses into how-to-win messaging. pmm-competitiveproxy MCP live ads, 20-brand wiki.
running
Customer + market research
Defines the audience, runs customer interviews, sizes the market, and pulls objections and win-loss straight from real sales calls. pmm-research Jobs to be Done, Gong + Granola.
running
Audience + persona development
Maps the buyer's external, internal and philosophical problems, their resistances and survival filters, then runs the persona as a live content test. pmm-audience-insight empathy + resistance mapping, audience as hero.
running
Positioning
Finds the category to win and the angle that wins it, mapped attribute by attribute against the real alternatives. pmm-positioning Dunford Obviously Awesome, Fletch, Big Fish Small Pond.
running
Messaging + narrative
Turns positioning into a message hierarchy and a story that lands, benefit first then the machinery. pmm-messagingpmm-story-craft Make It Punchy, StoryBrand, reveal-tension.
running
Pricing + packaging
Sets good-better-best tiers from real value drivers and willingness to pay, by segment. pmm-pricing value-based pricing, packaging design, monetisation models.
running
Launch + GTM
GTM strategy
Tiers the launch, runs the readiness call on who, what, where, when and why, and sets the channel plan. pmm-gtm launch tiering, Lauchengco LOVED.
running
Launch planning, end to end
Runs the full checklist from strategic readiness to day-of execution to post-launch momentum. pmm-launch tiered launch, Rolling Thunder.
running
Sales + CS enablement
Arms sales and customer success with one-pagers, battlecards, talk tracks and objection handling. pmm-sales-enablement.
running
Win/loss feedback
Folds why deals are won and lost back into the positioning and the battlecards. pmm-competitive.
partial
Content + storytelling
Website + in-product copy
Writes positioning-led pages, persona pages and comparison pages. This whole site is the working example. pmm-homepage Fletch homepage process, 5-second clarity test.
running
Longform, social + blog
Runs the content engine, from search-led articles to a daily farmer that keeps the source material fresh. seo-contentcreate-farmer.
partial
Thought leadership + category POV
Builds the category point of view and the brand around it: podcast, newsletter, and a daily LinkedIn engine. intelligent-growthlinkedin-agency.
running
Video, demos + walkthroughs
Plans and records product walkthroughs and demo videos, with an auto-generated demo from a script. intelligent-growth-videoproduct-updates.
partial
Customer stories + proof
Runs case studies as a line: identify, score, interview, edit, publish, distribute, with ROI proof points and a customer reference program. case-study-production.
partial
Growth + adoption
Demand + product-led growth
Builds acquisition and retention loops across the full funnel. pmm-growthlifecycle-growth Balfour, Reforge.
partial
Demand gen + integrated campaigns
Turns positioning into multi-channel campaigns across email, social and paid, tied back to pipeline. campaigns-launchemail-journey-mapping attribution next.
partial
Lifecycle + in-app adoption
Audits the full lifecycle and rebuilds the welcome, onboarding and upgrade journeys to move a user to first value. email-journey-mappinglifecycle-growth in-app triggers next.
partial
Activation tutorials + explainer video
Turns the questions sales and customers actually ask into explainer videos, posted to YouTube and seated in-product to pull users to first use. explainer-demo-videos.
running
Creator partnerships + power users
Finds and ranks creators on real engagement, splits budget 70/20/10 micro to macro, tracks ROI by word-of-mouth lift, and activates power users for authentic UGC. pmm-creator-marketing.
partial
Measurement + operating system
Scoping + planning a build
Pulls the complete plan out of the operator's head with a relentless structured interview before anything gets built. process-interviewer.
running
Attribution + adoption metrics
The loop-closing layer: adoption, usage and campaign attribution piped back to the brain. pmm-metrics.
roadmap
Cross-functional partnership
One approved doc that arms every team, written to land in their context. pmm-internal-comms Wes Kao, Molly Graham, Commander's Intent.
running
Internal tooling + multiplier
Turns repeat workflows into shared CLIs and skills any teammate can run. printing-press.
running
Taste + editorial QA
Human-in-the-loop gates on every draft: an advisor council, an AI-tell humaniser, a claim fact-checker. councilhumaniserfact-checker.
running
Who runs it

Agents run the system. One operator directs it.

A manager agent runs a stack of worker lanes, one lane per task, each with the right skill loaded and its own memory of the work so far. Six primitives keep it honest.

Goals

A finish line it cannot fake

Every task gets a written goal with a measurable end state. The agent cannot stop until the condition actually holds, with proof in the transcript. Done means verified done, not "sounded finished".

Loops

Recurring work that paces itself

Work that repeats, like intel sweeps, monitors and content refreshes, runs as a loop that decides when to check back. The system keeps working between conversations, not just during them.

Workflows

Fan-out with a referee

When a job is genuinely parallel, like a research sweep or a review panel, it fans out to multiple agents at once, then adversarial verifiers attack the findings before anything is trusted.

Hooks

Every request routes itself

Before the agent writes a word, hooks load the right project context, pin the right skill, and route every file to where it belongs. Nothing depends on remembering to set things up.

Compound rules

The same mistake never twice

Every correction becomes a standing rule that loads into every future session. Feedback given once changes how the whole system works from then on.

Skill memory

Every run starts where the last ended

Each skill keeps its own log of decisions, files and learnings, synced automatically at the end of every session. The system sharpens with use instead of starting cold.

Always on
operational reference rebuilt twice daily competitor + creator intel sweeps asset go-live monitor self-healing health checks
Quality gates
buyer-persona testhumaniser fact-checkerrefine-spec council · reviewer panel
The rule
agents draft and verify · a human approves everything that ships

Real today as an operator workflow. The gaps are the roadmap.

Build 01

launch-content-refresh

Generalise the fan-out so one messaging doc produces all of the assets in a pass. Closes the biggest output gaps in one move.

Build 02

Launch orchestrator

One entry point that runs the whole loop as a gated chain: intelligence to synthesis to fan-out to arm-everyone to adoption, with an approval gate at each stage.

Build 03

Post-launch loop

Pipe the retro, the adoption metrics and the attribution back into the intelligence layer so every launch starts smarter than the last.

Build 04

Pipeline-aware content

Plug the brain into the CRM so it sees where deals sit, writes for the deals in flight, and ties every asset to what it touched and what it moved. Content gets the measurement paid already has.

Build 05

Next-play suggestions

The brain stops waiting to be asked. It reads what is coming in and suggests the next move for each launch: which channel, which story, which proof. The operator still makes the call.