NO.
05.
Neighborly
Embedded four weeks inside Neighborly's in-house creative team. Turned the repetitive work behind 19 home-service brands (resizes, US to Canada versions, seasonal edits, briefs, color checks) into eight documented AI workflows the team now runs on its own.
The brief
FIG. B · 01Neighborly is the parent company behind 19 home-service brands, Mr. Handyman and Molly Maid among them, across the US and Canada. All of that creative runs through one lean in-house design team. Five to seven requests a day, 400-plus last quarter, and a lot of it the same work in a different size.
The graphic designer carried the highest-volume tickets: display and banner resizes for every placement, and US plus Canada versions of the same campaign, often 40-plus assets from a single request. The associate creative director had already built a ChatGPT script that spits out 68 print templates from a dropdown, and still spent her days hunting for files across systems.
AI was in the building. Everyone used it a little, each from a different starting point. But the first passes kept coming back off-brand. The tools started from a blank slate every time, with no idea what Gotham Bold or a brand's exact blue looked like.
So the engagement was four weeks embedded with the team, role by role. Find the highest-leverage repetitive work, build the AI workflow for it on a live ticket, document it so anyone could run it, and leave the team running without me.
The approach
FIG. A · 02The operating principle went up on day one: stop starting from zero, start from one.
Every session ran on a real ticket. A Mr. Handyman trifold that needed new copy. Three social graphics that needed the same photo swapped in, and (the fun one) a stock house photo that needed fall, 10 p.m., and string lights along the trim. If a workflow couldn't survive the actual request, it didn't get documented.
The Keep/Change prompt formula became the spine: say exactly what to touch and what to leave alone, then name the output you want back. Around it, the habits that make the model behave, like four options instead of one, a fresh chat per job, and the model writing and fixing its own prompt. All of it written down so a new hire with zero AI experience could follow it and get the same result.
The guardrails went in before the builds. Talent contracts that restrict altering a person's likeness got a hard line, and anything touching brand marks was staged behind legal. Then I specced the permanent fix for the off-brand first pass, a brand-context layer with one ChatGPT project per brand holding its guidelines, font files, logos, color values, and a handful of approved examples, so every edit starts on-brand.
GPT Image 2.5 shipped in the middle of week two. The playbook got re-tested and rewritten around it that same week, with every original step preserved.
The work
FIG. W · 03Eight workflows documented, tested on Neighborly tickets, and running without me, with five more scoped and staged. Copy changes on a finished layout in one pass, and US to Canada versions from one prompt (the Canadian logo, the .ca URL, neighbourly with a u). One photo into five sizes, all five landing. Seasonal and holiday edits off a single base photo, four options at a time, plus photo swaps across a whole batch of graphics and transparent cutouts of the brand elements the models like to mangle. Weekly reporting straight off the monday.com export. And a color-guide QA workflow that reads about 60 swatches across all 19 brands and cross-checks the CMYK values against four models before a vehicle-wrap printer ever sees them.
Brief assembly, the creative PM's bottleneck at 15 to 60 minutes per request and about eight requests a day, dropped to under a minute. Raw form data in, formatted brief out.
All of it lives in a shared Notion hub: step-by-step documentation, copy-paste prompts, and the session recordings, built to survive turnover. The creative director owns adoption now, and the graphic designer who opened the month saying AI wasn't her first instinct closes tickets with it by default.
The last session was a lunch and learn for the wider marketing team, a dozen people in the room, so the habits had somewhere to spread. Four weeks in, the design team runs it without me.