DirectoryWorkflowsCase studiesPodcastsWho's Noah Take the stack assessment

Case studies

Real systems, shipped. Priced.

Ten systems, and what each one is actually worth. Same story every time: manual work quietly capping the business, until the right system took it off someone's plate.

$446,000
a year across six of these ten systems. Figures are costed low on purpose. Where something was not measured, it is not counted.
Get a free stack assessment →

What I build, and who for

Ops systems

Insurance agencies

Documents read and filed, renewals flagged, quotes out the same day.

Onboarding systems

Financial advisors

New clients through paperwork and setup without the back-and-forth.

Front-office systems

Accounting firms

Enquiries, scheduling, and client chasing handled before they reach staff.

01 Insurance · 8 agencies

$318k a year back across eight insurance agencies

$318k/yr value across 8 agencies
6,000 hrs staff time back per year
~270 policies saved per year

Eight agencies ran on four different systems. Every quote, policy, and form was read and typed in by hand. The typing took ten minutes each. The waiting took far longer. In a busy week a document could sit for over a week, and by then the prospect had bought elsewhere. Now around 3,000 documents a month are read, checked, and filed automatically. That is 6,000 staff hours a year back, plus about 270 policies that used to go cold.

n8nPlaywrightLLM extractionOCRZod validationAMS360
Read the full case study →
02 Web-design agency

$43k a year of founder time back from one inbox

$43k/yr founder time back
720 hrs returned per year
3.5h → 0.5h on email per day

Michael ran his whole agency out of one Outlook inbox. No automation, no CRM. Email took about 3.5 hours of his day. We built a workflow that sorts every message, replies instantly to the safe ones, drafts the tricky ones for approval, and schedules follow-ups for leads and invoices. Inbox time dropped to about 30 minutes. That is three hours a day back, from the one person in the business who cannot be replaced.

n8nOutlook (Graph API)Google Sheets
Read the full case study →
03 B2B marketplace

$36k a year of rep time back from automatic follow-up tracking

$36k/yr rep time back
1,200 hrs returned per year
5 reps off manual tracking

Five reps managed more vendor relationships than anyone could keep track of. Status lived in memory and scattered notes, so follow-ups got missed. Each rep lost about an hour a day just working out where things stood. We built a system that tracks every relationship, prompts the rep when a follow-up is due, and turns their product documents into something searchable. That hour a day is the deliverable.

n8nLLM ingestionCustom relationship tracker
Read the full case study →
04 B2B SaaS · Support

$28k a year saved by answering the same question once

$28k/yr agent time back
1,120 hrs returned per year
8 min → <1 min per ticket

This support team spent its day answering questions it had already answered before. The answers existed, but they were buried in old tickets and docs, so each one took about eight minutes of searching and rewriting. We organized that history into something searchable, then added a layer that drafts a reply the moment a question arrives. An agent still approves every send. Eight minutes became under one.

HelpwiseLLM draftingCustom APIKnowledge-base dashboard
Read the full case study →
05 B2B data analytics

10% more opportunities in month one from better lead data

+$25k opportunities, first month
$0.06 per enriched lead
<3% false positives

This firm sells into enterprise accounts, and off-the-shelf tools only gave them surface-level data. We built a pipeline that turns a LinkedIn URL or domain into a full profile: hiring signals, exec appearances, org insights, clean job titles. It runs off a Google Sheet the team already used. Opportunities went up 10% in the first month, on about $1,000 a month of running cost.

n8nApifyGoogle SheetsSlackAI research
Read the full case study →
06 IT training & placement

Front-desk cover at a tenth of the cost, around the clock

~$12k/yr saved on the role
$0.08 per call
24/7 cover, not one shift

An AI voice agent answers the phone, works out what the caller wants, books consultations, handles basic support, and writes the outcome into Dynamics 365 with a transcript. It costs about $0.08 a call. It replaced an overseas front-desk hire, so the cash saving is modest at around $12,000 a year. The bigger change is cover: the role handled one shift, the agent handles all of them.

ElevenLabsTwilion8nCustom MCP serverDynamics 365Microsoft Teams
Read the full case study →
07 SaaS · Outbound

1,000 emails a day and ~11 meetings a month, hands off

~11/mo meetings booked
1,000/day emails sent, hands off
2% reply rate

This company had Clay for research and Smartlead for sending, but nothing reliable in between. Every launch meant wrangling CSVs, which was slow and hurt their sending reputation. We built one pipeline that runs the whole thing: clean intake, no duplicates, suppression lists, personalized copy by persona, sending caps, and reply sorting. At 1,000 emails a day and a 2% reply rate, that is around 440 replies and roughly 11 meetings a month.

n8nClaySmartleadSupabaseSPF/DKIM/DMARC
Read the full case study →
08 Professional services

One pipeline from first enquiry to work in progress

8 stages lead to delivery, one pipeline
1 system instead of CRM, docs, and sheets
0 deals sitting with no next step

This firm had GoHighLevel but was only using it as a contact list. Deals lived in someone's head between the enquiry and the invoice: estimates in spreadsheets, proposals in a docs folder, follow-ups only when someone remembered. We built the whole thing as one pipeline in GHL, eight stages from lead to operations, with the estimate feeding the proposal, the proposal feeding the follow-up, and a won deal opening itself as a project. Nothing gets to sit still with no next step.

GoHighLevelGHL workflowsGHL proposals & e-signn8nGoogle DriveGoogle Calendar
Read the full case study →
09 Local service business

Five posts a week that answer their own DMs

~$14k/yr vs buying the same output
5 / week posts published, hands off
~$115 / mo to run, posts and DMs

This business knew it should be posting and mostly wasn't. Someone would remember, put up three things in a week, then go quiet for a month. Hiring for it was hard to justify against everything else the money could do. We built a system that draws on the work the business already does, finished jobs, service list, seasonal patterns, writes and designs the post, puts it in a queue the owner clears from their phone, and publishes on schedule. Then ManyChat handles what the post starts: someone comments, they get a DM, and the useful ones arrive as a name and a number instead of a notification nobody opened. Five posts a week, running at about $115 a month.

n8nManyChatInstagram Graph APILLM copywritingAI image generationGoogle Drive
Read the full case study →
10 SaaS · Onboarding

A personal onboarding video for every signup, at 25 cents each

~$18k/yr vs buying and maintaining it
~600 / mo videos rendered per account
~$0.25 per personalized video

Onboarding was one twelve-minute demo recorded eighteen months earlier, against a UI that had moved on twice since. Most signups never finished it, and the ones who did asked support the same setup questions anyway. Now every account gets its own ninety-second video: their workspace name, their plan, and the three steps that matter for the use case they picked at signup. Creatomate renders it from an approved template, so a product change is a template edit rather than twelve re-records. About 600 videos a month, at roughly 25 cents each.

n8nCreatomateElevenLabsCustomer.ioPostgresS3 + CDN
Read the full case study →

Want a system like these run for your business? Start with a free stack assessment.

Take the stack assessment →