Denis Ostapenko

Originally published on denisostapenko.com . How the same agent can run a live workflow, stop when either of us sees a problem, help me change the system, then go back to work without leaving the conversation. What this article covers The evening a logistics system finally exposed a database mismatch that had survived about a week of revisions. Why either the human or the agent should be able to call a tactical pause. How one agent can switch from executor to technical partner and return to execution in the same window. What research on mixed-initiative systems, live programming and interactive code generation says about this way of working. A practical prompt for defining stop conditions, authority and the before-and-after check. Full article For about a week we couldn't understand why a dispatch system for collecting and analyzing freight orders kept producing the wrong result. The data and the fields were there, and each part looked reasonable when we inspected it alo...

Originally published on denisostapenko.com . Part II of "AI Is Shortening the Road Into Small Business" What this article covers How AI can support the first weeks of a real operating business. A post-construction cleaning job where photos, staffing, chemicals, and deadlines collide. What already works in hiring, purchasing, scheduling, quality control, and daily reporting. Where ordinary business software ends and the new AI layer begins. Why more affordable attempts may create more companies, purchases, contracts, and jobs. Full article In Part I, I wrote about the shorter path from an idea to a first serious business test. Here I want to follow the next step: the first real job, where a plan meets the floor, the workers, and the customer. Imagine a multistory office building at the end of construction. The client wants the final cleaning completed floor by floor so the building can pass acceptance. On paper there is a schedule, a team, equipment, chemicals, a d...

Um módulo, uma pergunta, seis artefatos locais e um coordenador que sabe onde o sistema pode falhar O que este artigo cobre Por que a estrutura de pastas não cria uma fronteira real sem decisões, entradas, saídas, proibições e evidências explícitas. Como módulos com uma pergunta só contêm erros e tornam as recusas diagnosticáveis. Quais seis artefatos locais transformam um módulo numa unidade de trabalho verificável. O que um coordenador deve validar, o que ele não deve reinterpretar e onde a liberação humana continua necessária. Quando dividir o trabalho melhora o isolamento de falhas e quando o custo de coordenação piora o sistema. Na primeira parte eu expliquei por que um contexto enorme e um modelo caro não salvaram um projeto anonimizado de otimização de rotas. O agente escrevia código. O sistema não conseguia explicar qual decisão tinha eliminado uma rota viável. Agora vem a parte de engenharia. A versão curta é simples: não divida uma aplicação de agentes por substant...

One module, one question, six local artifacts, and a coordinator that knows where the system can fail What this article covers Why directory structure is not a real boundary until decisions, inputs, outputs, prohibitions, and evidence are explicit. How one-question modules contain errors and make refusals diagnosable. Which six local artifacts turn a module into a verifiable unit of work. What a coordinator should validate, what it should not reinterpret, and where human release remains necessary. When splitting work improves fault isolation, and when coordination cost makes the system worse. The first part explained why a large context and an expensive model did not rescue an anonymized route optimization project. The agent could write code. The system could not explain which decision had removed a viable route. This part is the engineering answer. The short version is simple: do not divide an agentic application by nouns. Divide it by decisions. "Everything about ord...

Every morning, before I can ask AI what we should do, somebody still has to establish what is true. If a company trades LVL beams or natural birch plywood, the useful questions are very concrete. What do our suppliers actually have in stock today? At what price and under which terms? Did a competitor change its price? Is a truck available on the lane we need? Has a construction company announced a project where our material fits? Did a university in Boston open a furniture supply tender? The answers exist somewhere. Usually they arrive through calls, emails, spreadsheets, manager chats, vendor portals and websites built for a person with a mouse. Then AI receives the result and makes a summary. That is useful. It is also a small part of what this technology should eventually do. AI still stops at the company door Inside a company, the current generation of corporate assistants can already review email, notes, CRM records, warehouse data, shipments, reports and documents. At NF E...

"Your container arrived in Baltimore." Six words, and for five seconds you think you can go get it. Then the demurrage clock starts. My first container taught me more than any course. No freight agent, a customs broker who replied every three hours, a box sitting at Seagirt, emails all day, hold music with the steamship line, the terminal and customs saying different things. Here is the timeline nobody explains up front. Before arrival. The Importer Security Filing (ISF) is due at least 24 hours before the vessel departs. Miss it: $5,000 per container. Discharge. The ship berths at Seagirt. The box isn't ready immediately, 12 to 24 hours after discharge before eModal shows "available for pickup." Customs release. Best case, 24-48 hours. With an exam, 5-7+ days and $500-1,000+ in fees. Free time and demurrage. You get about four business days free. After that, $150-350 per day. Pickup. Live load: a trucker takes the whole box to the warehouse and returns it ...

Why Do New Hires Leave? The Secret to Effective Employee Integration That Gets Overlooked We spend huge budgets on recruitment. We conduct interviews, verify skills, and negotiate salaries. Finally, the perfect candidate is found. They start the job, but a month later, their productivity is still near zero, or worse, they hand in their resignation. Why does this happen? Often, the reason isn't laziness or the complexity of the tasks. The reason is failed onboarding. The Myth of "Adults" In manual labour industries (cleaning, construction, manufacturing), a tough opinion often prevails: "We hired an adult. We pay them to work, here is the job site, let them go and do it. They will figure it out themselves." This is a fundamental mistake that costs businesses money. Put yourself in the newcomer's shoes. You join a new team. You don't know where to get inventory, who to ask if a machine breaks down, where to have lunch, or what the unwritten rules of commun...

Just sharing a couple of useful resources from my work in cleaning operations, hope they come in handy for someone! Check out these two presentations: Modern Chemistry Matters (Industrial Cleaning) Post-Construction Cleaning Best Practices Wishing everyone all the best and a great working week! · · · This is a note from my satellite blog. The main notebook lives at denisostapenko.com . Related: Why new hires leave: the onboarding gap · What really happens to your container at the Port of Baltimore .