I build systems people trust with authority.
Products where the hard question was what happens when the machine gets it wrong.
Two products, one idea.
Spending authority for autonomous software
Agents get a key instead of a credit card. Budgets that halt the agent rather than warn you afterward, a credential vault, and an escalation path that ends at a person.
The interesting problem was never making software capable. It was making capable software unable to spend money nobody approved.
Ethical analysis of documents, decisions, and processes
Bring it a contract, a policy, a process being designed, or a decision being weighed. It surfaces the ethical dimension — what is at stake, whose interests are affected, which values are in tension, and where the reasoning starts to drift.
Built on the work of Dr. A.C. Ping, whose methodology it runs on: indicators for reflection, never proof of intent. The decision stays with the person making it.
Most people selling this have never had to answer what happens when it’s wrong.
I’ve shipped two products whose whole job is that question. When something is talking to your customers, the failure mode is the product — not an edge case you handle later.
Everything I install assumes it will be wrong sometimes, and puts a person in the path before that costs you a customer.
One person, on your account.
Whoever scoped it builds it and answers the phone in month four. There is no junior team to hand you to — which is also why there’s one implementation a month.
Your tools, your team, your process. If the answer is to replace something you already pay for, that’s a different project and a different person.
Every automated action traces to the system that produced it. You should be able to check the result without asking me to explain it.