Why this exists.
One Painter workspace with a separate brand kit for each client. Every asset comes out looking like the client, not like the agency.
A patchwork that breaks.
- A shared spreadsheet nobody opens on time
- Prompts copy-pasted into a chat window
- A contractor who disappears for two weeks
- Output that lands in a different shape every run
A workflow that ships.
- One brief, one cadence, one place to read it
- Every claim cited, every step reviewable
- A finished artifact in your team’s format
- Agency margins stop getting eaten by endless rounds of revisions.
Four moves.
Painter runs each move with a preview attached — so you know what lands before you ever hit send. Skip freely once you know which parts carry the weight.
- 01Kickoff
Build a brand kit for each client.
Painter starts with the brief and asks only for what's missing. No boilerplate intake form, no setup meeting.
Chat · marieteYBuild a brand kit for each client.PPainter is working - 02Gather
Drop the brief into the right client's kit.
Sources are pulled, cleaned, and cross-checked against prior runs — every claim carries a citation you can trace.
checklist · step-02Source connected · drop the briefContext loadedFirst pass completeSource connected - 03Reason
Painter creates six on-brand versions.
The agent thinks out loud where it matters — trade-offs named, assumptions surfaced, judgments explained.
ranked results01One · multi brand0.9402Agency, · multi brand0.8203Brands · multi brand0.67 - 04Draft
The client signs off in hours, not days.
A first draft lands in the format your team already uses. You edit the last 10%, not the first 90%.
delivery · inboxPnewPainter → your teamjust now · scheduled weeklyOne agency, many brandsAgency margins stop getting eaten by endless rounds of revisions.Open briefing
Wire this in Painter.
Painter is a visual node-flow workspace — not a chat window. Here's the graph that runs this playbook, node by node. Each one is a real block you can drop in and wire yourself.
Inputs in, outputs out.
Painter runs on the inputs on the left and hands back the artifacts on the right. Skip any input — the agent will ask for it the first time it needs it.
- One source of truth (CSV, CRM, or warehouse)
- A one-paragraph brief on the goal
- The KPI you want to move
- A scored, cited brief you can forward
- A structured file for downstream automation
- An alert when anything material changes
A finished artifact, not a todo list.
Every run ends the same way — a packaged brief in the channel your team already reads. Here's a preview of what shows up.
Here's the brief for this week. I ran the playbook end-to-end, flagged anything that shifted against last run, and packaged the output for Slack and the shared drive.
- Build a brand kit for each client.
- Drop the brief into the right client's kit.
- Painter creates six on-brand versions.
- The client signs off in hours, not days.
Where teams stall.
Three ways we see this go sideways — and how to avoid each one.
Pointing the agent at stale or half-connected data. Clean the source once, compound every run after.
Running it once and forgetting. Put it on a weekly cadence so the numbers actually move.
Skipping the first review. Check the first run by hand — trust compounds from there.
Before you start.
Usually one source is enough to see value. Painter can run on a CSV paste for the first pass; connect the CRM, the data warehouse, or the tool of record once you want it to run on its own.
Most teams put this on a weekly cadence. That's the sweet spot between "too noisy to read" and "too stale to act on". Adjust once you see how the numbers behave.
Whoever owns the downstream action. Painter hands back a finished result — the value is in somebody actually reading it and shipping the decision the same day.
It usually isn't. The first pass is calibration — tell Painter what was off, rerun, and the second is close. By the fourth it reads like a teammate.