Register and share your invite link to earn from video plays and referrals.

Ohans Emmanuel
@OhansEmmanuel
cofounder @ColdteaAI 5X author. Prev staff engr @Hellofresh Ex @Revolut
215 Following    4K Followers
Now make it actually follow them use Jev to enforce the rules linters cannot catch open-source:
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.
Show more
Finally got access to Jev Let's see if it holds up with a use case I'm keen to try
There's more to software than just spitting out code
At Anthropic, Claude now writes 80% of our code. Engineers ship 8x more code per quarter. Side effect: Tests grew 10x. CI jobs up 25x in 6 months. Here's what helped us scale:
Show more
Not sure about Markdown files but building a visual graph can help you understand your codebase a lot faster. This is how I work out costly mistakes in data flow across every PR Open source:
Show more
The most underrated artifact in AI engineering is a folder of markdown files. Before any agent touches code on a brownfield engagement, the team builds a knowledge graph: every module, dependency, data flow, and domain term documented. The agent reads this context before writing a single line. Every time. On one of our logistics clients, building the knowledge graph took 4 days. It saved roughly 4 months. The agent stopped generating code that violated naming conventions. Stopped importing deprecated modules. Stopped wiring services through patterns the team abandoned six months earlier. At another healthcare client, the same knowledge graph served double duty. AI agents used it for code generation context. Human engineers used it as onboarding documentation. I mean, most teams skip this because it feels like overhead. Four days of documentation before any code ships feels slow. But the teams that skip it spend those same four days spread across four months of rework, reviewing PRs that look right and break something upstream. We've seen this at @LimestoneHQ on dozens of engagements. The knowledge graph is the scaffolding everything else stands on.
Show more
500+ github stars since I shared this Thank you!
Mermaid diagrams are the floor. Every PR at @ColdteaAI ships with an interactive walkthrough Open source:
Mermaid diagrams are the floor. Every PR at @ColdteaAI ships with an interactive walkthrough Open source:
0
41
1.2K
73
Forward to community
Mermaid diagrams are the floor. Every PR at @ColdteaAI ships with an interactive walkthrough Open source:
0
41
1.2K
73
Forward to community
think Mermaid, but animated and built for agent diffs JSON in, diagram out. Open-source:
Every PR is about to come with a screenshot. Yours can come with the architecture, animated npx skills add coldteadotai/pr-lens
The higher you went up your career, the less code you wrote Whether managerial or IC Code's never been the end goal
A buttload of developers are going through a tough time right now. Their identity has always been tied to their ability to write code, so now they feel threatened by this new era where *anyone* can write code. If they don't write code anymore, who are they? I'm very pragmatic, and yet I've struggled with this too, so I totally understand how tough it must be for others. You'll hear from these people everywhere. They are the ones fighting with everything they've got against AI-generated code. But they must understand this is an uphill battle. Manually writing code is destined to disappear. There's no going back.
Show more
Go even further make the architecture and data flow just as easy to understand open source:
/show-me is a phenomenal skill Makes PR descriptions extremely easy to read Basically a toolbox of "nice ways to look at code" Nice work, @dexhorthy
Every PR is about to come with a screenshot. Yours can come with the architecture, animated npx skills add coldteadotai/pr-lens
Every PR is about to come with a screenshot. Yours can come with the architecture, animated npx skills add coldteadotai/pr-lens
every terminal should let you annotate agent output like a PR review. we spend hours a day in that loop
I don't trust a single model to review my code anymore. so I pair Claude and Codex. One builds, the other tries to tear it apart. Last cycle: 5 P1s across 4 rounds. for now, I still read code output. I imagine we will for some time
Show more
Introducing Coldtea. The ADE for shipping self-driving software. Purpose-built for the entire software lifecycle. Other IDEs optimise for one thing: Build. Run more agents in parallel, ship faster, orchestrate better. But software engineering is not just about building. @ColdteaAI brings your coding agents, agentic end-to-end testing, and production monitoring agents into ONE development environment, so you can move at agent speed without breaking anything.
Show more
0
69
275
105
Forward to community
Ran this in @ColdteaAI Real-world use case: run multi-agent collab (e.g., reviewer + implementer)
my favorite way to explain people herdr is to just open a new workspace, launch an agent and tell it to: read `herdr --skill` then split 10 other panels that make my computer look like some scifi hacker terminal from the movies
Show more
Introducing Coldtea. The ADE for shipping self-driving software. Purpose-built for the entire software lifecycle. Other IDEs optimise for one thing: Build. Run more agents in parallel, ship faster, orchestrate better. But software engineering is not just about building. @ColdteaAI brings your coding agents, agentic end-to-end testing, and production monitoring agents into ONE development environment, so you can move at agent speed without breaking anything.
Show more
0
69
275
105
Forward to community
Spending hours reviewing your teammate's AI-generated code? Review the plan that produced it instead. Code is cheap now. One bad decision in the plan → hundreds of lines of wrong code. Review the input, not just the output.
Show more
Damn. Since most of these are static (no new “emails”), they could mostly be static assets
Jmail has crossed 450M pageviews, and our Vercel bill has exploded, even after tons of cache mitigation. Many kind people chipped in to cover the bill, but it’s not sustainable. What are solid, cheaper alternatives?
Show more
Strange to say, but some would argue Cursor shipped too fast some months ago Seemed they've now slowed down / prioritised reliability