How to put an AI agent into production
A demo is not enough: production needs data, integrations, evals, guardrails, monitoring, and operational ownership.
Read articleGuides and articles on AI in business.
How we design software, build AI agents and bring these tools into companies. Guides, real projects and decisions explained in detail.
Article preview
Type a question or choose a topic. Relevant articles appear here as you explore.
Where to begin
Other paths
Claude Cowork for companies: a practical guide
The lightest way to make the company brain usable: files, decisions, routines, and work state in a workspace the AI can reread.
How to integrate AI into existing business systems
Standard-First: integrate AI into existing systems only when process, data, APIs, and governance can hold.
All articles
33 of 33 articles
The vibe coder’s quote: what missing security costs
What 2026’s numbers say about software written with AI and never read by anyone, who pays for what the quote leaves out, and five questions to ask before you sign.
Read articleThe AI supply chain is the new security perimeter: the LiteLLM case
LiteLLM, npm packages, coding-agent configuration: October’s attacks did not break the network, they came in through the tools. What changes for the people who decide.
Read articleFrom patch to attack in a few hours
The time between a patch and the first attack used to be weeks. Now it is hours. What that means for the people who set priorities, suppliers and budgets.
Read articleIntarget: making customer knowledge accessible
How to make customer knowledge accessible and maintainable in everyday work.
Read articleUninform: four days from AI tools to a project
The story of Module 3 in the AI for Business Processes master’s programme, built around practice, testing, and real workflows.
Read articleAI voice agent for sales: pricing, scripts and objections
How to design the conversation around defined products and prices, sales scripts, objections, and voice refinement.
Read articleArsenale: the concept, the specification and the Node demo
Why a supply chain’s production capacity has to be seen in real time, federated and verifiable, with no company handing over its data. Manifesto, node demo and open specification 0.1.
Read articleAI in a defense factory without a byte leaving
Classification, authorized tools, rules written by management. The four-step method with a filled-in example, and the NIS2 questionnaire questions for a supplier.
Read articleThe invisible supply chain: defence SMEs and their suppliers
Supply-chain digitization came down from the top for the prime’s compliance. It gave SMEs obligations. What is needed is a federated, sovereign layer, one node per plant.
Read articleHow much can you produce in 90 days: how to answer in an hour
The question your customer will ask in 2027, the calculator that answers in one minute, and the anonymous survey on Italy’s supply chain.
Read articleThe production capacity map must stay in Italy
Industrial data sovereignty with the numbers: what the filings say, “enterprise” protection, the AI and Defense Strategy, EDIP. And the four tests to run on any vendor, Yempik included.
Read articleThe seven-day cycle: what Ukraine teaches factories
From 7 to 500 drone makers, a seven-day redesign, cost per target from $60,000 to $1,000. The lesson for manufacturers, with the Vertesa example and the short-cycle checklist.
Read articleEuropean rearmament is won in the factory
The bottleneck of European rearmament is the capacity to produce and to see the supply chain. Numbers from Kubilius, Rheinmetall, and the Commission, plus three moves for an SME.
Read articleWhere knowledge dies: what a company loses when it works with AI
Every AI session produces decisions, rules, corrections. When it ends, they are gone. The problem, the evidence, and the requirements of an answer.
Read articleThe impossible question: the AI value experts don’t see
Experts ask for features and automation of the visible. The gold is in the solidified processes they never mention. The question that surfaces it at the first table.
Read articleCompany brain, knowledge base and wiki: the differences
A wiki is an archive that ages; a company brain is live context that people and agents use. When a wiki is enough, and how you move.
Read articleWhy 95% of AI projects leave no mark
It’s not the model’s fault. What’s missing is the layer underneath: the company brain that gives context. Agents fail because they don’t know the company.
Read articleFrom tacit knowledge to the agent: the method
The person who’s good at a process can’t explain it. The method to pull it out: start from the real last time, dig into the "usually", write rules with a source.
Read articleThe Yempik case: how our Company Brain works
AI assistants propose, a person approves. How we work with Claude, ChatGPT and Codex on the same company knowledge.
Read articleData sovereignty: who owns your company’s brain
Your company’s brain shouldn’t live rented inside a US vendor. For sensitive data and regulated sectors, owning it matters: files, GDPR, EU data.
Read articleCompany Brain Maturity Model: what level are you at
Five levels, from “lives in heads” to “agent-operated”. Take the self-check and find your next step.
Read articleAI governance for CTOs: the production checklist
Access, data, human-in-the-loop, audit trail, evals, owner. The checklist we use to take an agent from demo to production, with numbers and sources.
Read articleHow to build a company brain on files
The hard part is not creating folders: it is transferring knowledge between humans and machines. The method with 1:1 interviews, STT, files, and validation.
Read articleWho owns your company brain
Decisions, rules, and work state are becoming AI memory. The question is not whether you need it: it is where it lives and who governs it.
Read articleOrganizing work in Claude Cowork
Why AI stays a throwaway chat, and the method to give it a readable operating context with Cowork: structure, rules, routines. With a free kit and a mockup of the result.
Read articleHow to automate data entry with Claude Cowork
What manual data entry costs, how to drop it starting Monday with Claude Cowork, and when a plain spreadsheet still does. With a calculator and a mockup of the result.
Read articleHow to measure the ROI of AI
The formula, total cost of ownership, a baseline and control group to isolate the AI’s contribution, and a calculator to estimate payback and return.
Read articleWhich process should you automate first?
The 4-step funnel to find the first process to automate: map it, filter with signals, find the constraint, score it with the scorecard.
Read articleHow to standardize a process before automating it
The five steps to make a process repeatable and measurable before automating it: map the as-is, capture tacit knowledge, make the rules explicit, unify the data, write the SOP.
Read articleHow to get your team to adopt AI
Adoption is the last link: without it, all the upstream work produces nothing. Champions, training in the flow, leaders who model the behavior, and how to measure real adoption.
Read articleAI governance for SMEs: risks, rules and tools
Shadow AI, how to classify the risk, and the 30-day plan to govern AI in your company without a compliance department.
Read articleWhen you don’t need AI: the cases where we advise against it
The real cases where we advise against AI: low volumes, unstable processes, AI for show, a broken process upstream. Honesty before the project.
Read articleAI agent vs chatbot vs no-code: what to choose
What they actually do, lock-in vs your own code, costs, and when each one makes sense. A comparison with no marketing.
Read articleHave a project to discuss?
Tell us what you want to improve in your business. We’ll help you decide where to start and what makes sense to build.