{"slug": "smart-software", "title": "Smart Software", "summary": "TypeSafe founder Diogo Almeida has coined the term \"smart software\" to describe software that uses intelligence as part of how it operates, marking a shift from \"prompted intelligence\" to \"engineered intelligence,\" according to a post by Jev of @TypeSafeAI. The post argues that intelligence is becoming precision-engineered into software systems from the foundation up, rather than bolted on as a chatbot or sidecar, with programs encountering state, requesting bounded judgments, and using structured judgments as part of execution in a loop of state, judgment, bounded decision, authorized action, observation, and new state. The shift raises new engineering questions about what context a judgment receives, what outcomes it may produce, how uncertainty is represented, when the system may act, when a person must review, what evidence is retained, and what happens when the judgment is wrong.", "body_md": "### From prompted intelligence to engineered intelligence\n\nJev from [@TypeSafeAI](https://x.com/@typesafeai) finally makes the shift easier to see: intelligence is becoming part of how software works. Not as a chatbot or bolted on as some sidecar. But intelligence precision engineered into software systems from the foundation up.\n\nMuch of generative AI has worked through what I call **prompted intelligence**: we give a model instructions in plain language and get text back. Then we—or our software—have to interpret that text and decide what happens next. Or what I like to call \"toss spaghetti against the wall intelligence\", even tho its been enormously useful.\n\nEveryone has had a lot to debate about AI, but the mere existence of LLMs requires a new philosophy of software engineering. That philosophy enables a new evolution of the craft itself, which enables the next phase of AI: **engineered intelligence**. \n\nA program can encounter some state, ask a bounded question about what that state means, receive a structured judgment, and use that judgment as part of its execution.\n\nThese are semantic questions: questions about meaning. This is **semantic engineering**.\n\nThis means **interpretation of meaning can become part of the machinery of software.**  \n\nTypeSafe founder [Diogo Almeida](https://x.com/@CompleteSkeptic) has called this **smart software**. Its perfect.\n\n### **Smart software is software that uses intelligence as part of how it operates.**\n\nThat is different from software that was written with AI. It is different from an application with a chatbot attached to it. And it is different from using a model as an assistant that waits for a person to ask a question.\n\nThe distinction is where intelligence sits in the architecture. In the familiar prompt-and-response model, a human gathers context, asks for a judgment, interprets the response, decides whether to trust it, and determines what happens next. Smart software begins when some of that interpretation moves inside the system itself.\n\nThe application encounters a situation, requests a bounded judgment, evaluates the result within its rules, takes an authorized action, observes what happened, and continues.\n\nThat produces a different loop:\n\n**State → judgment → bounded decision → authorized action → observation → new state**\n\nOnce intelligence enters that loop, the engineering problem changes. It is no longer enough to ask whether a prompt produces a good answer. We have to ask what context the judgment receives. What outcomes it is allowed to produce. How uncertainty is represented. When the system may act. When a person must review the decision. What evidence is retained. What happens when the judgment is wrong.\n\nThat is the transition from **prompted intelligence** to **engineered intelligence**. Prompted intelligence asks a model to help us think. Engineered intelligence makes bounded judgment a designed component of a software system.\n\nAnd smart software is what becomes possible when we do that well.", "url": "https://wpnews.pro/news/smart-software", "canonical_source": "https://twitter.com/JAS0Nduncan/status/2101759688769454422", "published_at": "2026-09-22 03:16:23+00:00", "updated_at": "2026-09-22 03:53:38.070925+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research", "developer-tools"], "entities": ["TypeSafe", "Diogo Almeida", "Jev", "@TypeSafeAI"], "alternates": {"html": "https://wpnews.pro/news/smart-software", "markdown": "https://wpnews.pro/news/smart-software.md", "text": "https://wpnews.pro/news/smart-software.txt", "jsonld": "https://wpnews.pro/news/smart-software.jsonld"}}