<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc" -->

---
title: Spec-driven Development: How AI Changed Everything (And...
description: A software engineer and consultant recounts moving from unstructured vibe coding to a spec-driven development workflow, describing his own lean process (the...
canonical: https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Spec-driven Development: How AI Changed Everything (And Nothing) by Simon Martinelli @ Spring I/O 26 | daily.dev
og:description: A software engineer and consultant recounts moving from unstructured vibe coding to a spec-driven development workflow, describing his own lean process (the...
og:url: https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc
og:image: https://api.daily.dev/og/posts/41KkDOskc.png
og:image:alt: Spec-driven Development: How AI Changed Everything (And Nothing) by Simon Martinelli @ Spring I/O 26
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Spec-driven Development: How AI Changed Everything (And Nothing) by Simon Martinelli @ Spring I/O 26

**[Spring I/O](https://daily.dev/sources/springio)** · 43 min read · 0 upvotes · 0 comments

## Summary

A software engineer and consultant recounts moving from unstructured vibe coding to a spec-driven development workflow, describing his own lean process (the 'AI Unify Process') built around system use cases and entity models rather than free-form prompting. He contrasts greenfield projects, where requirements engineers and business analysts co-author specs with AI, against brownfield/modernization projects, where AI reverse-engineers use cases from existing code, docs, and tickets. Using a reworked Spring PetClinic demo with Vaadin, Claude Code skills, MCP servers, and browserless Spring Boot tests, he shows how specs act as the source of truth, tests are generated per use case, and architecture choices (modular monoliths, self-contained systems) reduce the context AI needs. He stresses that despite AI's non-determinism, developers remain fully responsible for reviewing, understanding, and testing all generated code.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=35dH6q18UtI>

## Questions this post answers

### What is spec-driven development and how does it differ from vibe coding?

Spec-driven development means writing specifications first and treating them as the source of truth, rather than jumping straight into AI-generated code (vibe coding). When code seems wrong, developers return to the spec to diagnose the mismatch instead of patching code directly. Because AI is non-deterministic, output varies between runs even from the same spec, so developers remain fully responsible for reviewing, understanding, and testing everything generated.

_Explore more real-world takes on spec-driven AI workflows and use-case-based development on daily.dev._

### How can AI be used to reverse-engineer specifications from a legacy codebase for modernization?

In brownfield modernization, AI is fed the existing code, documentation, Jira tickets, Confluence pages, and business process descriptions, and it extracts use cases and an entity model describing the current system's behavior. Requirements engineers then verify each recreated use case against the running application before generating new code, effectively reverse-engineering specs rather than doing direct code translation like COBOL-to-Java conversion.

_Track practical approaches to AI-assisted legacy modernization and spec extraction on daily.dev._

### Why might MCP servers still be useful alongside AI coding skills instead of relying only on a CLI and skill files?

MCP servers remain valuable for documentation because they often use a vector store enabling similarity search, which is more efficient than plain CLI-based skill lookups. Examples include a Java doc MCP service and a Vaadin MCP server that let an AI agent query documentation directly, rather than requiring exported or manually referenced docs.

_Compare MCP servers versus skill-based workflows for AI coding setups on daily.dev._

## Similar posts on daily.dev

- [Spec-Driven Development: Why AI Is Bringing an Old Software Engineering Idea Back to Life](https://daily.dev/posts/spec-driven-development-why-ai-is-bringing-an-old-software-engineering-idea-back-to-life-jefbpvuoq) · The Serverless Edge · 193 upvotes · 25 comments
- [Beyond vibe coding: the case for spec-driven AI development](https://daily.dev/posts/beyond-vibe-coding-the-case-for-spec-driven-ai-development-vbdthzjvn) · The New Stack · 1 upvotes · 0 comments
- [The AI-Ready Redesign: How Spec-Driven Development Is Changing the Way Teams Build](https://daily.dev/posts/the-ai-ready-redesign-how-spec-driven-development-is-changing-the-way-teams-build-wqgzt63ey) · RUBYLAND · 0 upvotes · 0 comments

---

Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#claude-code](https://daily.dev/tags/claude-code), [#spring-boot](https://daily.dev/tags/spring-boot), [#spec-driven-development](https://daily.dev/tags/spec-driven-development)

[View this post on daily.dev](https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Spec-driven Development: How AI Changed Everything (And Nothing) by Simon Martinelli @ Spring I/O 26","url":"https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc"},"datePublished":"2026-09-27T07:26:35.660Z","dateModified":"2026-09-27T07:53:35.651Z","description":"A software engineer and consultant recounts moving from unstructured vibe coding to a spec-driven development workflow, describing his own lean process (the...","image":"https://i.ytimg.com/vi/35dH6q18UtI/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/35dH6q18UtI/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Spring I/O","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Spring I/O","logo":"https://media.daily.dev/image/upload/s--e-TcwM9B--/f_auto,q_auto/v1790493985/logos/springio?_a=BAMAMicg0","url":"https://daily.dev/sources/springio"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-coding,claude-code,spring-boot,spec-driven-development","timeRequired":"PT43M","video":{"@type":"VideoObject","name":"Spec-driven Development: How AI Changed Everything (And Nothing) by Simon Martinelli @ Spring I/O 26","description":"A software engineer and consultant recounts moving from unstructured vibe coding to a spec-driven development workflow, describing his own lean process (the...","thumbnailUrl":"https://i.ytimg.com/vi/35dH6q18UtI/sddefault.jpg","uploadDate":"2026-09-27T07:26:35.660Z","duration":"PT43M","url":"https://api.daily.dev/r/41KkDOskc","embedUrl":"https://www.youtube.com/embed/35dH6q18UtI"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Spring I/O","item":"https://daily.dev/sources/springio"},{"@type":"ListItem","position":3,"name":"Spec-driven Development: How AI Changed Everything (And Nothing) by Simon Martinelli @ Spring I/O 26"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/spec-driven-development-how-ai-changed-everything-and-nothing-by-simon-martinelli-spring-i-o-26-41kkdoskc#faq","mainEntity":[{"@type":"Question","name":"What is spec-driven development and how does it differ from vibe coding?","acceptedAnswer":{"@type":"Answer","text":"Spec-driven development means writing specifications first and treating them as the source of truth, rather than jumping straight into AI-generated code (vibe coding). When code seems wrong, developers return to the spec to diagnose the mismatch instead of patching code directly. Because AI is non-deterministic, output varies between runs even from the same spec, so developers remain fully responsible for reviewing, understanding, and testing everything generated. Explore more real-world takes on spec-driven AI workflows and use-case-based development on daily.dev."}},{"@type":"Question","name":"How can AI be used to reverse-engineer specifications from a legacy codebase for modernization?","acceptedAnswer":{"@type":"Answer","text":"In brownfield modernization, AI is fed the existing code, documentation, Jira tickets, Confluence pages, and business process descriptions, and it extracts use cases and an entity model describing the current system's behavior. Requirements engineers then verify each recreated use case against the running application before generating new code, effectively reverse-engineering specs rather than doing direct code translation like COBOL-to-Java conversion. Track practical approaches to AI-assisted legacy modernization and spec extraction on daily.dev."}},{"@type":"Question","name":"Why might MCP servers still be useful alongside AI coding skills instead of relying only on a CLI and skill files?","acceptedAnswer":{"@type":"Answer","text":"MCP servers remain valuable for documentation because they often use a vector store enabling similarity search, which is more efficient than plain CLI-based skill lookups. Examples include a Java doc MCP service and a Vaadin MCP server that let an AI agent query documentation directly, rather than requiring exported or manually referenced docs. Compare MCP servers versus skill-based workflows for AI coding setups on daily.dev."}}]}
```

