Systems we've built, and what they replaced.
Seven systems, all running in production. An AI sales agent, a self-diagnosing operations system, an agent factory that builds automations, two content engines, an AI chief of staff and a voice-cloned appointment setter. Each write-up covers the problem, the build, the stack and the numbers, and ends with how the same pattern would work in your business.
Every system, in one place.
An AI Sales Agent That Runs a Publishing Business's Inbound Revenue
63 sales inboxes, one AI agent, about $105 a month. It answers every inbound enquiry for a digital publishing business, quotes the right price for the right site, handles objections, collects the content, chases the invoice and makes the upsell, with no human in the loop for a standard deal.
A Multi-Agent Factory That Builds Automations On Demand
Hand one agent a plain-language brief. Get back a deployed, tested automation. Behind that single point of contact, a crew of around 15 specialist agents plans, builds, reviews and tests the workflow for n8n, Zapier or Make, then records what it learned so the next build goes better.
A Self-Diagnosing Operations System That Replaced a Full-Time Role
60+ live sites, watched around the clock by an agent system that finds the real cause of each incident, proposes the fix and carries it out only after a human taps approve. It took over the work of a full-time technical operations hire.
A Content Engine That Takes Raw News to Published Article, Hands Free
From raw headlines to a live, illustrated, search-ready article, on a schedule, with no human steps per article. The pipeline pulls trending news from several sources, picks the strongest story, writes it in a controlled editorial voice, generates a matching image and publishes it, across multiple sites.
An AI Chief of Staff Running a Founder's Calendar, Inbox and Meetings
One assistant that runs the whole cycle around a founder's meetings. It books and manages the calendar, watches the inbox, sits in every meeting as note-taker, files the transcript, spots any follow-up meeting mentioned and offers to book it, and chases the documents needed before the next call.
Turning a Public Data Feed Into Editor-Grade Articles at Scale
Dry public filings in, original news articles out. A two-stage system watches a public filings feed, lets only records with a real story through a 10-filter quality gate, then routes each one across 26 filing types and 7 research paths to a writer that produces angle-led articles a human editor would sign off.
An Outbound Appointment Setter in the Operator's Own Cloned Voice
Every lead gets a personal voice note from the operator. The operator never records one. An outbound setting agent replies in the operator's own cloned voice, tracks how each prospect engages and follows up at the right moment, so warm leads turn into booked appointments instead of going cold.