Field notes from real engagements.
Engineering culture, payments, staff augmentation, and the boring parts of building software that lasts. Written by the people doing the work.
- mvp
Building an AI MVP demo for your fundraise: what to show, and how to keep it honest
How to plan an AI MVP demo for a seed round: pick one workflow, show it on real data, be ready for the hard questions, and avoid a demo that falls apart after the meeting.
Read post - ai-integration
pgvector or a dedicated vector database? How a startup should choose
Choosing a vector database for your first AI feature: when pgvector in the Postgres you already run is enough, and the signals that it is time for a dedicated vector store.
Read post - ai-integration
AI for marketplaces: where it helps, and where it should never touch the money
Practical AI features for two-sided marketplaces, from better listings and search to trust and safety, and the guardrails to keep around payouts and payments.
Read post - ai-integration
Building an AI customer support agent that doesn't embarrass you
A practical guide to building an AI customer support agent for a startup: scope, knowledge, handoff, guardrails and how to launch it without surprising your customers.
Read post - ai-integration
Your AI prototype works in the demo but not in production: why, and what to fix
Why AI prototypes that impress in a demo fall apart with real users, and the engineering work that gets an AI prototype to production.
Read post - ai-integration
RAG not working? Chunking, retrieval and reranking mistakes to fix first
When a RAG feature gives vague or wrong answers, the model is rarely the problem. The chunking, retrieval and reranking mistakes to check first, in order.
Read post - mvp
What to put in an AI MVP spec: a one-page template for founders
A practical AI MVP spec template: the user, the job, the data, what good looks like and what the feature must never do. Copy it before you talk to any builder.
Read post - hiring
Hiring an AI developer vs an AI agency vs a freelancer: how startups should choose
Should you hire an AI developer, bring in an agency or use a freelancer? A practical guide for founders and CTOs, with the questions that decide it.
Read post - ai-integration
How to reduce LLM hallucinations in production: a playbook for startups
Hallucinations are an engineering problem, not a mystery. A practical playbook for reducing confident wrong answers in a production LLM feature.
Read post - ai-integration
Why your LLM feature is slow, and how to reduce LLM latency
Where the seconds go in an LLM feature, how to measure them, and the practical fixes that make AI features feel fast, from streaming to fewer model calls.
Read post - ai-integration
How long does it take to build an AI MVP? A week-by-week plan
A realistic AI MVP timeline: what happens in each of six weeks, what has to be ready before week one, and what usually causes delays.
Read post - ai-integration
How much does it cost to build an AI MVP?
What drives AI MVP cost, where the money actually goes, and how to scope a first version you can afford, with our own published prices as a reference point.
Read post - ai-integration
Do you need an AI agent, or a workflow with one smart step?
Agents are the most hyped way to build with LLMs and often the hardest to run in production. Here is how to decide whether your feature needs one.
Read post - ai-integration
Adding an LLM without leaking customer data
Your first enterprise customer will ask where their data goes when your AI feature runs. Here is how to have a good answer before they ask.
Read post - ai-integration
RAG or fine-tuning? How to teach an LLM about your business
Most startups that ask for fine-tuning need retrieval instead. Here is how to tell which one your feature needs, and what to build first.
Read post - ai-integration
Picking your first AI feature: start where being wrong is cheap
Most startups pick their first AI feature by what demos well. A better filter: pick the workflow where a wrong answer is cheap, the volume is high and you can measure success.
Read post - ai-integration
How to test an LLM feature before your users do
Most AI features ship on vibes: someone tries five prompts and says it looks good. A small eval set turns that into a number, and it takes less time than you think.
Read post - ai-integration
What will this AI feature cost to run? A back-of-envelope method
AI features have unit economics hiding inside them. Here is a simple way to estimate cost per request and per customer before you build, and the levers that bring it down.
Read post - engineering-culture
What "boring" engineering actually means
Boring is not slow, simple, or unambitious. Boring is the dial we turn up when reliability matters more than novelty — which is most of the time.
Read post - stripe
Stripe Connect: the playbook we wish we had
Five years of shipping Stripe Connect — marketplaces, payouts, dispute handling, and the edges that turn a working demo into a robust production system.
Read post - staff-augmentation
Staff augmentation done right: five anti-patterns to avoid
Staff aug fails for predictable reasons. Here are the five most common, and what to do instead — from someone who has seen both sides of the engagement.
Read post - architecture
Why we reach for Postgres first (and second)
Most products do not need a new database. They need someone who knows Postgres well enough to stop reaching for new ones. Here is our default, and the few times we break it.
Read post - cloud-devops
The deploy pipeline that does not page you at 3am
A good deploy pipeline is boring on purpose: small changes, fast rollbacks, and enough observability to know what broke before a customer tells you.
Read post - ai-integration
Shipping AI features without betting the company on them
AI features are easy to demo and hard to make reliable. The boring approach treats the model as one unreliable dependency inside a system you still control.
Read post - mvp-engineering
An MVP is not a disposable prototype
The "minimum" in MVP is about scope, not quality. The parts you cut and the parts you never cut are what separate a fast launch from a slow rewrite.
Read post - maintenance-support
The maintenance work nobody puts on the roadmap
Dependency updates, expiring certs, and quiet capacity creep never make the roadmap — until they cause the outage. Here is the boring upkeep that keeps software alive.
Read post