CodeMySpec – Lovable for engineers who care about the code

CodeMySpec has launched a full-lifecycle AI development platform for Phoenix applications that integrates requirements, specs, architecture, code, tests, and verification into a single dependency graph. The tool addresses a documented pattern where AI-assisted codebases show 60% less refactoring but 48% more duplication and a three-month velocity cliff, by providing a structured harness around AI coding agents. The platform is free during early access and requires users to bring their own model provider and API keys.

Full-lifecycle platform, not a point tool. Requirements → specs → architecture → code → tests → verification. One graph, one system. Every other tool owns a single phase and assumes you'll glue the rest together yourself. 01// the harness End-to-end specs, code, tests, and verification, Phoenix-native. CodeMySpec is the harness around your AI coding agent, so the code you ship still makes sense in two years. 02// the frame The hard part is what happens next. Codebases built with AI assistance are showing 60% less refactoring, 48% more duplication, a three-month wall where velocity drops off a cliff. Efficient technical debt machines. The problem isn't the model. It's the missing harness: no specs, no architecture, no verification, no lifecycle. Prompting is praying. That's the gap CodeMySpec fills. 03// how it works CodeMySpec tracks every artifact your Phoenix app needs specs, tests, implementations, BDD scenarios, QA results on a single dependency graph. Call get next requirement . Do one thing. The graph moves forward. Story interview. The Product Manager agent asks what you want and writes it as markdown with acceptance criteria. Map stories to Phoenix contexts. Validate the graph. No cycles, no cross-context leaks. spec-writer drafts component specs. test-writer generates ExUnit from assertions. TDD, the way you know it. code-writer writes to pass the tests. Continuous mode walks the graph until it satisfies every requirement. User-facing behavior captured as BDD scenarios in the Spex DSL, generated from acceptance criteria. QA agent opens a real browser via Vibium, drives the app, takes screenshots, files issues when reality diverges. It's the harness OpenAI spent six months building for Codex, productized for teams that don't have OpenAI's infrastructure team. 04// differentiators Requirements → specs → architecture → code → tests → verification. One graph, one system. Every other tool owns a single phase and assumes you'll glue the rest together yourself. Specs are plain markdown. Tests are standard ExUnit. The plugin works with Claude Code today and whatever agent wins next year. You pay Anthropic or OpenAI directly. CodeMySpec doesn't arbitrage your token spend. Generic AI tools blow through Phoenix contexts. They generate Ruby syntax in Elixir files, regress 1.7 codebases to 1.6 templates, and write defensive code that fights let-it-crash. CodeMySpec treats contexts, LiveView, Ecto, and OTP as first-class primitives, and respects how Phoenix is built. Every spec produces acceptance criteria and generated tests. The QA agent drives the live app with a real browser, not a mock. You know the feature works before you ship it, not after the alert fires. "The agent is commodity. The harness is the differentiator." CodeMySpec is the harness, ready to use, purpose-built for Phoenix. 05// the money shot Unit tests pass. BDD specs pass. Then the QA agent opens a real browser, clicks through the flow a user would take, and finds the bug anyway. That's the loop no other AI coding tool has. 06// proof Multi-context Phoenix app with Google Ads, Google Analytics, Facebook, and QuickBooks integrations. Built end to end with CodeMySpec. The codebase itself is the case study. Production client app built with CodeMySpec methodology. In UAT March 2026. Real customers, real uptime. The requirement graph you use is the requirement graph the product tracks itself against. The recursion is the proof. 07// objections 08// pricing CodeMySpec is free during early access. We'll price server-side platform features per-seat once we hit 1.0. You bring your own model provider and keys. We never charge a markup on your tokens. 09// install Two commands. No signup gate. See the harness for yourself. We can't find the internet Attempting to reconnect Something went wrong Attempting to reconnect