--- title: "Things built, things learned, things I think." url: "https://simonebova.com/en/writing" lang: "en" author: Simone Bova alternates: it: "https://simonebova.com/md/it/writing" en: "https://simonebova.com/md/en/writing" pl: "https://simonebova.com/md/pl/writing" --- # Things built, things learned, things I think. - [The codebase is a society: what Luhmann teaches people who build with agents](https://simonebova.com/md/en/writing/la-codebase-e-una-societa) (2026-11-09, Frontier): For Niklas Luhmann a society is made of communications. Applied to a codebase where many agents work, it changes how I write handoffs, reviews and stops. A hypothesis, with the rules I took from it. - [It was never multi-agent. It's multi-context.](https://simonebova.com/md/en/writing/non-e-mai-stato-multi-agent) (2026-11-09, Method): The same prompt leads to a different decision when the place the agent works in changes. How I designed motive's markets by moving the question from the repo to my second brain. - [When the agent repeats a mistake, change the code before the prompt](https://simonebova.com/md/en/writing/cambia-il-codice-prima-del-prompt) (2026-11-08, Method): The reflex after a bad agent output is a new line in CLAUDE.md. The order I follow is code first, then a check, instructions last. Examples from my own repos. - [Nobody reads every line anymore. Put the safety in the system.](https://simonebova.com/md/en/writing/nessuno-legge-ogni-riga) (2026-11-08, Method): When agents write the code, a human reading every diff is the wrong safety net. How I ship at agent speed, where I agree with Anthropic and where I side with Theo. - [The bulletin is for today: what off-piste skiing teaches about shipping AI to production](https://simonebova.com/md/en/writing/cosa-insegna-il-fuoripista) (2026-11-04, Fuoripista): A check tells you something about one moment, then it expires. Lessons from a WhatsApp agent and from our company brain on when a piece of evidence stops counting. - [The keyword is no longer enough: what I got wrong measuring visibility in AI assistants](https://simonebova.com/md/en/writing/la-fine-della-keyword) (2026-10-28, Frontier): With ads in ChatGPT the brief becomes the buyer's situation, and ads, unprompted answers and outcomes need separate measurement. The mistakes I made building motive. - [Own the harness, swap the model. What you actually need to own](https://simonebova.com/md/en/writing/possiedi-l-harness) (2026-10-21, Frontier): Owning the harness means owning state, authority, rules and verification, with native tools underneath. What I learned from DeepSWE, CVing and Yempik's Company Brain. - [CONTEXT IS GOLD: a company brain the next agent can use without you](https://simonebova.com/md/en/writing/context-is-gold) (2026-10-14, Company brain): Context is worth something when another agent can find it, tell when it holds, correct it and reuse it. Rules from Yempik's company brain and my second brain. - [Anyone can buy the model. Knowing which work to remove is rare.](https://simonebova.com/md/en/writing/il-modello-e-una-commodity) (2026-09-29, Method): Anyone can use a frontier model. The edge is knowing which work to remove, which judgment to leave with the expert, and how to prove the result. Cases from Lia and CVing. - [The smart model is the bottleneck. Spend it on decisions.](https://simonebova.com/md/en/writing/il-modello-intelligente-e-il-collo-di-bottiglia) (2026-09-18, Method): I orchestrate Claude Code and Codex subagents every day. A delegation with gaps hands your architecture to the worker: where to spend the strong model, and what it cost me. - [deploy to prod. make no mistakes. The mistakes a deploy can't see](https://simonebova.com/md/en/writing/deploy-to-prod-make-no-mistakes) (2026-09-04, Field notes): Yempik's Company Brain was in production and search came back empty. What “make no mistakes” really asks for: whole paths, long sessions, approvals that mean something. [simone@yempik.ai](mailto:simone@yempik.ai) · [Book a call](https://calendar.app.google/LKDrQPKGV2EAFCMN9)