Nine AI GTM systems live, all built solo
CreativeOS, FinGuard, AdGuard, MarketingOps, Career Capybara, Hyper Creator, TikTok Miner, TechSpy and AdRadar. Every one has a real public URL, and every one runs LLM pipelines with a human in the loop.
When the stack can't do it, I open an editor
Most GTM teams hit a wall in the stack and file a ticket. I stopped filing tickets. After ten years running marketing for B2B fintech and SaaS, I started shipping the software myself.
At PingPong I owned marketing for the cross-border payments line end to end, the line that went from $2M to $76M in year one and past $250M by year two. Sales closed the deals and finance ran the payment rails; every campaign, channel and lifecycle touch that fed their pipeline was mine. I personally cut LinkedIn CPL from $300+ to ~$160 and Google registration cost from $90+ to ~$35, and I governed the 8-tool GTM stack that carried it all: Salesforce, HubSpot, Webflow, 6sense, Zapier, ZoomInfo, Salesloft, and GA4 with Tag Manager. Before that, as VP of Marketing at ToLocal, I ran a $10M annual media budget at 80%+ ROI leading a team of 7.
I built the 200+ workflow layer that collapsed lead handoff from ~12 hours to 1–2 minutes. That was my build, wired into a stack I governed, feeding a sales team that worked the leads. I wrote the LLM pipeline that turned a messy monthly report from one to two hours of manual work into an under-five-minute run producing eight different reports from a single cleaned dataset. My LinkedIn title line reads “GTM Systems Builder” because that is the job I actually do.
Three kinds of evidence, and what each one settles
Ordered by what they settle, not by date. The systems are the artifact, each on a URL you can open right now. The case studies show the same method applied inside a company, with other people in the loop. The writing shows the reasoning before the result was known.
Systems, all live
Competitor RadarA cheap model labels every competitor ad, a frontier model reads the strategy off the labels. Cost decided the architecture. TechSpyA real browser and a HAR capture instead of a fingerprint database, with confidence stated and blocked scans admitted. CreativeOSPolicy as structured records the generator reads while writing, then scores against afterwards. One source, used twice. FinGuardThe regulator's rulebook as data, maintained by compliance themselves rather than by me. Career CapybaraThirty-five prompts under one governed console, each pinned to a model with an audit trail. All nine, side by sideThe full set with the stack each one runs on.The same method, inside a company
Reusable multi-agent systemsAgent teams with guardrails, including the review layer that caught a real failure before a customer saw it. Agent-native reportingThe weekly status compiled from source systems, which is the version other people depend on. Content enginesAgents produce, review and package; a person approves. The boundary is the design. AI sales intelligenceA dead roster turned into a ranked, reachable book that sales actually worked. AI video pipelineBrief to finished film with no crew, which is the same argument in a different medium.How I think, written down
Search ads research as an agent pipelineFour models each doing the part it is good at, on 3,156 keywords, with the routing explained. Automating a messy monthly reportWhere the accuracy actually broke, and why the redesign went into the review step rather than the prompt. An AI lead scoring assistantScoring one question at a time so a rep can see the reason beside the score. A scored content pipelineTurning an editorial judgment into a rubric a model can apply consistently. Automation for a one-person support deskThe smallest version of the whole idea, with the limits stated.From a marketing pain
to a public URL
01 · Start from a pain I've paid for
Every system began as a GTM problem I lived with as a marketer: ad copy dying in policy review, leads going cold over a ~12-hour handoff, a monthly report eating an afternoon. I write the problem down with a number attached before I write any code.
I ask for the number the pain costs before I build02 · Ship the smallest system that closes the gap
CreativeOS is the pattern. I built it to write platform-ready ad copy for Google, Meta, LinkedIn and Bing with formats and character limits enforced, checking every line against platform ad policy and custom compliance rules as it writes. Next.js, an LLM API, Vercel. No committee, no roadmap review.
Ship the narrow thing, then stop adding to it03 · Wire it into the stack
A tool that lives outside the stack is a demo. At PingPong I wired the winners into 200+ workflows across an 8-tool stack I governed myself, which is how I took lead handoff from ~12 hours to 1–2 minutes. Software that touches revenue has to sit inside the plumbing, so I build the plumbing too.
A tool nobody has to open is a tool nobody uses04 · Keep a human in the loop
All nine of my systems ship with human-in-loop review, because GTM software touches money and brand. The model drafts, extracts or flags; a person approves. I measured what happens without that gate as a marketer, so I refuse to ship without it as an engineer.
The model drafts; a person stays accountableDoes “marketer who codes” mean scripts?
One TikTok URL in, a queryable intelligence system out
No. TikTok Miner is a full ETL and RAG system: paste a TikTok URL and it transcribes the video, extracts frame-level metadata, embeds everything into a Pinecone vector store, and serves RAG chat plus engagement analytics on top. React 19 and TypeScript on the front, multiple AI models behind it, built solo.
The messy monthly report I automated went from one to two hours of hand-assembly to under five minutes, with eight different reports generated from a single cleaned dataset. Different size of problem, same posture: I measured the pain, built the pipeline, shipped it to a URL anyone can visit.
9 systems live · full ETL + RAG · report time 1–2h → under 5 minDaniel is a fantastic member of the team with his ability to blend very deep technical knowledge with great interpersonal skills. He is able to quickly understand business requirements and then present a solution in a motivational way in terms appropriate for any level of the audience.
Emma YuSenior Product Manager, TikTok
Hiring for AI GTM?
Hand me the GTM problem. I will ship the system that fixes it and give you the URL.