Writing
Everything I publish, in one place. Each piece says how it was made: field reports carry numbers from systems I actually run, tutorials were run start to finish before they were written, reference pieces cite every claim, glossary entries define one term properly, and essays are just me thinking out loud.
- ReferenceAgentic GTMSep 25, 2026 · 10 min
Agentic go-to-market, and the parts I would not automate
A working definition of agentic GTM, the documented reliability limits, what a per-account research run costs, and the three patterns I would not ship.
- GlossaryAutonomous agentsSep 24, 2026 · 6 min
Autonomous agents, defined by who picks the next step
An autonomous agent is a software system that pursues a goal by choosing its own next action — usually a tool call — at each step, rather than following a path fixed in code.
- TutorialRunning a company with AISep 23, 2026 · 13 min
Start an AI company by building the meter first
A runnable FastAPI service that calls a model, prices every call from token usage, writes it to JSONL, refuses work over a cap, and reports to Stripe.
- ReferenceEntrepreneurship in the age of AISep 22, 2026 · 9 min
What Harvard actually measured about AI and entrepreneurship
Two Harvard field experiments — 758 consultants and 776 P&G professionals — give founders a routing rule, not a forecast. Here is the rule, and where it stops working.
- GlossaryAgentic GTMSep 21, 2026 · 7 min
An AI agent decides its own next step. That's the test
An AI agent is a software system that perceives its environment, chooses its own next action toward a goal, and acts through tools, repeating that loop until a stop condition is met.
- TutorialEntrepreneurship in the age of AISep 20, 2026 · 11 min
Start an AI startup by shipping one metered endpoint
Build a POST /v1/triage endpoint that runs a bounded agent loop, logs token cost per request to JSONL, and returns 402 when credit runs out.
- ReferenceRunning a company with AISep 19, 2026 · 10 min
What AI can actually do for a business, and what it costs
The four things AI does inside a company, each with a measured result, what a triage agent costs per run, and the two jobs I would not hand it.
- GlossaryAutonomous agentsSep 18, 2026 · 9 min
Multi-agent system, defined without the hype
A multi-agent system is two or more autonomous agents, each with its own state and instructions, that interact by messages or handoffs to complete a task none of them handles end to end.
- TutorialAgentic GTMSep 17, 2026 · 14 min
Build an AI agent: three tools, a step cap, a JSONL note
A build-along in Python: an agent that fetches a company's homepage, checks a CRM stub, and appends one qualification note — with the stopping rule outside the model.
- ReferenceRunning a company with AISep 16, 2026 · 10 min
Running a company with AI agents: what actually holds
How to split a company into agent-sized tasks, where the human signature still belongs, what the token bill looks like, and the three failures that show up in production.
- GlossaryAutonomous agentsSep 15, 2026 · 7 min
A computer use agent drives a GUI with pixels, not APIs
An AI system that operates a computer the way a person does — reading the screen as an image and issuing mouse and keyboard actions — instead of calling an API.
- TutorialEntrepreneurship in the age of AISep 14, 2026 · 12 min
Start an AI startup by shipping one metered agent endpoint
Build a POST /jobs endpoint that runs a step-capped agent loop, logs tokens and dollar cost per job, and returns HTTP 402 when a caller passes their spend cap.
- ReferenceAgentic GTMSep 13, 2026 · 11 min
Will sales be replaced by AI? Answer it task by task
The role survives. The headcount math doesn't. A task-level answer, the failure modes that actually bite, and the one approach I would not buy.
- GlossaryEntrepreneurship in the age of AISep 12, 2026 · 5 min
An AI moat is what survives when your rival uses your model
An AI moat is the part of an AI product's advantage that still stands when a competitor builds the same thing on the same model.
- TutorialRunning a company with AISep 11, 2026 · 13 min
Start a business with AI: ship one metered, capped endpoint
A build-along: a Python endpoint that grades inbound leads with an LLM, meters the token cost per customer key, and refuses the call when a spend cap is hit.
- ReferenceAgentic GTMSep 10, 2026 · 9 min
AI won't replace salespeople. It replaces the work between calls
The direct answer, the sales tasks agents already own, the failure modes that kill them in production, and the one architecture I would not run.
- GlossaryAutonomous agentsSep 9, 2026 · 6 min
AI agent memory: what it actually is, and the two senses
AI agent memory is the machinery outside the model that stores facts from one run and reads selected ones back into the prompt on later runs, so behaviour persists across sessions.
- TutorialAutonomous agentsSep 8, 2026 · 13 min
Build an AI agent loop with a step cap, allowlist and dry run
A ~120-line Python agent that routes three sample leads, halts at 12 model turns, refuses any tool not on its allowlist, and logs every call to JSONL.
- ReferenceEntrepreneurship in the age of AISep 7, 2026 · 10 min
Entrepreneurship in the age of AI: what actually changed
The model is a commodity input. The business is the control plane around it — caps, verification, state, metering — and here is what that costs and where it breaks.
- GlossaryAgentic GTMSep 6, 2026 · 6 min
Agentic state: the data an agent keeps between steps
Agentic state is the data an agent carries between steps — goal, message history, tool results, progress markers — stored outside the model so a run can resume, be audited, or be capped.
- TutorialRunning a company with AISep 5, 2026 · 13 min
Start an AI company by shipping one capped, metered endpoint
A build-along: a POST /run endpoint that extracts a lead with Claude, logs the token cost of every run, and refuses to spend past $0.25 or 6 model calls.
- ReferenceAutonomous agentsSep 5, 2026 · 10 min
Self-hosted AI agent platforms: what you actually control
Which layers of an agent stack you can really run yourself, what each project's license permits, and the approaches I would not use.
- GlossaryEntrepreneurship in the age of AISep 4, 2026 · 6 min
What AI SaaS actually means (and the two senses people mix up)
AI SaaS is cloud-delivered software in which a machine-learning model performs the product's core function, which makes the vendor's cost of goods rise with usage instead of staying near zero.
- TutorialRunning a company with AISep 4, 2026 · 11 min
Run a company with AI: your first agent, with hard caps
A four-file Python agent that drafts overdue-invoice reminders, refuses to send anything without your yes, and halts on a step cap or a dollar cap. Full code.
- ReferenceAgentic GTMSep 4, 2026 · 10 min
What agentic marketing actually is, and where it breaks
A working definition of agentic marketing, the components that have to exist before the label is honest, the documented failure modes, and the cost math.
- EssayBuilding in PublicMar 28, 2026 · 3 min
Two Years of Building with AI: What I've Learned as a CEO Who Can't Stop Creating
I've spent two years going all-in on AI at Metadata, shipping MetadataONE, Pixel, and an MCP server with 100 tools. Here's what's actually working and why I've never been more excited to build.