•29d ago
Why are AI coding agents still hard to use in real engineering?
I ve been building NAEOS around a question:
What happens when AI coding agents move from write some code to actually participating in software engineering?
Most AI coding tools are getting very good at generating code.
But production engineering involves much more:
•1mo ago
Why did we build NAEOS?
AI coding agents are getting incredibly good at writing code.
But while building with them, we kept seeing the same problem:
The agent knows how to code, but doesn't always know how the system should be engineered.
Architecture decisions, security rules, testing standards, project conventions, and engineering context are often scattered across repositories, docs, and people's heads.
•1mo ago
Product Hunt Pre-Launch Thread 🚀
1/ We re getting ready to launch NAEOS on Product Hunt.
NAEOS is an AI Engineering Operating System for building production-ready software with AI coding agents.
Not another AI coding assistant.
We re building the engineering foundation around the agents.
•1mo ago
AI angle
The AI part deserves its own comment, because it's the part people react to most.
NAEOS compiles the engineering model into instruction sets for 6 AI tools: Copilot, Claude Code, Cursor, Gemini CLI, Codex, and OpenCode. Plus an MCP server. The idea: your AI assistant works from an accurate model of your system, not from guessing your repo's conventions.
The spec stays the source of truth so when it changes, the generated context changes with it. No stale context files.
If you're building AI-assisted workflows, I'd love to hear what your setup looks like today.
•1mo ago
Honest trade-offs
Since transparency builds trust: what NAEOS is not.
It's not a "no-code, describe and never code again" tool. For systems where the spec IS the artifact (APIs, services, schemas, governance), it shines. It's not magic for arbitrary bespoke UI.
The spec language has a learning curve ($ref, $include, $fn, $if). We document it thoroughly, but it's real syntax.
Generated code is a consistent starting point you own and modify it. The pipeline keeps the spec authoritative, and the diff engine shows drift.
I'd rather say this than have people discover it later. Questions welcome.
•1mo ago