CodeScene is a multi-purpose tool bridging code, business and people. See hidden risks and social patterns in your code. Prioritize and reduce technical debt.
Joined May 2016
- Tweets 803
- Following 21
- Followers 1,238
- Likes 302
375 Photos and videos
Pinned Tweet
19 Mar 2024
In this tutorial we use CodeScene ACE to refactor code smells using Gen-AI and through a fact-checking validation we can make sure that the refactoring has preserved the behaviour of the code.🚀
youtube.com/watch?v=dXY6FyJV…
1
4
998
Jun 12
Agents perform worst where they are needed the most, in legacy codebases.
Why is that and what is missing for agents to operate reliably?
Our Principal Researcher Markus Borg explains. Tune in and happy Friday! 🎉
1
42
Jun 3
🚀New: Our Deterministic PR Refactoring Agent triggers Code Health-guided refactoring directly from a pull request. 60% defect risk when agents work on unhealthy code. 50% fewer tokens when they don't. Fix the foundation first. Read more: codescene.com/blog/determini…
53
May 29
Agents working on unhealthy code consume up to 50% more tokens. Read the full article: hubs.ly/Q04jm2QQ0
41
May 4
We’re proud to be featured once again in the @thoughtworks Technology Radar, a big thank you to the team for the recognition. 🙏
Read more and download the full Technology Radar:
thoughtworks.com/radar/tools…
1
94
Apr 29
We're live on Product Hunt, come and join the conversation and share your feedback 🚀
producthunt.com/products/cod…
3
2
64
Apr 20
We benchmarked Claude Code on refactoring tasks, with and without MCP guidance. The MCP-guided agent achieved 2–5x more improvements in Code Health compared to raw refactoring attempts.
Read the full blog post:
codescene.com/blog/making-le…
1
79
Apr 9
đź“ş How to guide AI agents with code health, and why it matters
youtube.com/watch?v=AycLVxKm…
1
63
Mar 27
We built the CodeHealth MCP server because we hit a very real problem.
AI can generate code quickly. But it doesn’t necessarily generate healthy code. We're changing that.
P.S..we’re opening early access.
codescene.com/early-access-c…
127
Mar 19
Raw vs. guided AI refactoring:
Claude Code out-of-the-box vs. guided by the CodeHealth MCP isn’t a small difference, it’s a step change. Across all scenarios, the MCP-guided agent delivered 2–5x more Code Health improvements than raw refactoring.
codescene.com/blog/making-le…
1
60
Mar 2
Why AI Performs Worst Where Enterprises Need It Most and What Leaders Can Learn from Code Health Research
Read the article:
techtimes.com/articles/31421…
1
44
Feb 16
AI-generated changes fail 30% more often in unhealthy code.
That’s what our peer-reviewed study (5,000 programs, 6 LLMs) shows.
Next week, we’re hosting a live webinar on:
How to scale AI safely, without increasing defect risk.
Join us 👇
codescene.com/resources/webi…
66
Feb 4
Sign up for our upcoming webinar where we explore how to adopt and scale AI coding safely, with real-world evidence from loveholidays.
We’ll also dive into how Code Health determines AI performance, when AI introduces defects, and how to avoid them.
👉 hubs.ly/Q041LHTz0
1
57
Jan 28
Code Health determines whether AI accelerates delivery or amplifies defects, and how you can mitigate the risk.
Read our latest whitepaper: hubs.ly/Q040FxfW0
ALT Whitepaper - AI-ready code: How Code Health Determines AI Performance
1
72
19 Dec 2025
How @loveholidays beats the trend and proves that you can scale up AI-assisted development, keep and improve high-quality throughput and measure ROI of AI.
We're happy to be featured on International Business Times with this story:
ibtimes.com/rewriting-rules-…
47
11 Dec 2025
Can you show real ROI of refactoring with an AI agent? Yes, you can. đź’Ż
33
5 Dec 2025
AI can write code fast. But without guardrails, it also writes technical debt.
Here’s a practical, research-backed “inner developer loop” to turn AI into a reliable engineering partner:
codescene.com/blog/strengthe…
43
24 Nov 2025
We’ll dig into why we now need a reliable code health metric more than ever, and what the toolkit for crafting healthy code looks like, whether or not you’re using AI agents.
P.S. We’ll also show you how you can make AI agents reason about code quality.
codescene.com/webinars/tools…
1
44
19 Nov 2025
📣 Only two hours to go — sign up for the webinar if you haven’t yet. We’ll dive into what it takes to make AI-generated code truly production-ready.
Sign up: codility.zoom.us/webinar/reg…
77
10 Nov 2025
Enabling AI coding assistants to understand the code health of both the existing codebase and the code they produce, so they can propose improvements, perform targeted refactorings, avoid introducing technical debt, and gain insight into design problems.
1
48
27 Oct 2025
Today’s LLMs can pass coding tests with ease, but that only tells part of the story.
Join us for a webinar where we will go through groundbreaking research from @codility that redefines how we evaluate AI-generated code.
hubs.ly/Q03Qdqg70
57