Method
Build for the day it breaks.
The engineering habits behind the systems. Most started with a failed assumption, an incident, or a measurement that disagreed with the dashboard.
Architecture model. Scroll horizontally on smaller screens →
Ad mutations default to dry run. Campaigns are created paused. Inbound quotes wait for approval before send.
Every API mutation is verified against the response and re-read from live state. This rule came from auditing my own system and finding months of silent failures behind a green log.
Approval gates on inbound quotes, medium- and high-risk ad changes, and helpdesk replies. Automatic execution stays inside the policy defined for each workflow.
Any customer-facing claim is checked against retrieved data by a second pass before it can send. If the data does not answer the question, the system escalates to a person instead of guessing.
Each production incident gets a structured record: root cause, impact, what would have prevented it, mitigations. The mitigation lands as an enforced hook, gate, or test.
Observe, suggest, act-and-report, autonomous. Each step requires logged evidence: accepted suggestions, zero corrections over a period, confirmed reversibility.
Controlled A/B experiments, holdout groups, a head-to-head agency benchmark, anomaly detection against 30-day baselines, and a measured noise floor before reading a visual diff.
Runbooks, incident records, decision logs, and plain-language guides for the people who inherit the system. If it is not written, it did not ship.
Background
Seven years building systems for marketing, sales, and finance teams, first as a marketer who automated his own work, now as an engineer who ships the automation as product. The last three years have been on LLM APIs. I work daily in Claude Code and build the orchestration layer that other agents run inside. I am focused on the gap between the AI tooling companies buy and the output they actually get, and on the operating models that close it.
Roles: Head of Growth Engineering at a private-equity operator, directing a five-person marketing team and serving as technical counterpart to an enterprise software vendor through a year of monthly product reviews. Director of Business Development at a B2B wholesale ingredients business, where I built the operational stack solo. Earlier, Head of Digital Marketing for a multi-brand consumer portfolio, managing $150,000+ monthly ad spend and a four-person team.
Stack
What I can show in an interview
- Code walkthroughs of any system on this site, including the risk-tier taxonomy, the mutation verification layer, the RLS policies and cross-tenant tests, the guardian hook, and the two-layer send validation.
- Nightly engine reports, weekly executive reports, and the experiment log.
- Incident records and the controls each one produced.
- The cutover runbook and visual-diff output for the website re-platform.
What is deliberately not on this site
Client, franchise, and vendor names, revenue by client, private source code, and real screenshots. The diagrams and interface renderings illustrate the documented architecture. They are not live connections to the systems. Outcomes come from my résumé, with technical context from the supporting case studies. A walkthrough can cover the underlying evidence where disclosure is permitted.
Contact
andreasengelbertson@gmail.com. New York, NY. Open to engineer-titled roles at AI-native companies: applied AI, forward deployed, growth engineering, and agentic systems.