Waleed Kadous (@waleedk) profile picture

Founder, @Cluesmith — makers of Codev + Multisage. Ex AI Eng Lead @Canva, Chief Scientist @anyscalecompute, Eng Strategy @Uber, Principal Engineer

San Francisco Bay Area, USA
Joined March 2009
Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)Photo by Waleed Kadous (@waleedk)
I used AI to manage AI that writes code. Just published a deep dive on what that actually looks like — directing autonomous AI builders on an 80K-line TypeScript codebase. Here's what worked, what didn't, and the real numbers. 🧵
2
1
6
833
The real question isn't "is AI fast?" — it's "can AI be disciplined?" Unstructured AI coding is fast but produces 2.9x fewer tests and zero deployment artifacts. Structured AI coding costs more but catches bugs that would otherwise ship silently.
1
2
470
Codev is free and open source. Full article: medium.com/@waleedk/a-tour-o… GitHub: github.com/cluesmith/codev Get started: codevos.ai/getting-started
2
491
PSA: If you're using Gemini CLI for coding, it runs 4.7x faster on a GCloud box than locally. We benchmarked Gemini CLI, Codex CLI, and Claude Code on the same task — local vs cloud. The difference for Gemini is wild.
1
6
901
Each LLM was run 10 times on 2 platforms (local Mac and GCloud) — 60 runs total. About $40 in tokens for the full benchmark.
222
Codev 2.0 just shipped. It's an OS for humans and AI to build production code together — not vibe coding, real software. The velocity chart tells the story: sustained double-digit issue closes per day, accelerating through the sprint. codevos.ai/getting-started
2
2
379
Around v2.0.7 something clicked. Codev builds itself — self-hosted from day one. Early on it was clunky. Builders needed hand-holding. Reviews missed things. Then the protocols matured. 85% autonomous completion rate. The tool building itself, well enough to trust.
1
212
I don't know if this scales to teams yet. Complex specs still overwhelm reviewers. False positive rate is ~18%. I'd rather you try it knowing the limits. If you want to see what structured AI development looks like: codevos.ai
149
Every so often an AI agent does something uncannily human. I told my backend architect to introduce itself to the frontend architect. No script, just "say hi." The message was perfectly sensible. But it closed with "Looking forward to working together."
3
272
🚀 Codev v1.5.x "Florence Series" is here! ✨ Secure Remote Access - SSH tunnel to Agent Farm from anywhere 🎨 3D Model Viewer - Native STL/3MF support with auto-reload 🏗️ New af architect command for streamlined workflows Install: npm install -g @cluesmith/codev Details: github.com/cluesmith/codev/d…
1
236
I'm back on X! I'll start more about what I'm working on at Cluesmith.
3
167
A concrete example of why multi-agent approaches win: every agent has strengths and weaknesses. GPT-5.2 is _really good_ at finding near-duplicate code and refactoring it. This is on Codev (github.com/cluesmith/codev). GPT-5.2. outperformed Claude by 115% in identifying duplicate code. The entire codebase is ~15,000 lines so roughly speaking, Claude got rid of 1% and GPT-5.2 got rid of another 1%. That is a _huge_ difference. I verified that the stuff GPT-5.2 was actual duplicate code.
4
225
Ephemeral chat is a terrible way to build software with AI. Google, Amazon, GitHub and indie devs all converged on the same fix independently. Context-driven development is having its moment. waleedk.medium.com/welcome-t…
1
191