anatoliikmt

What kind of tasks have you been using it for?

Yes, exactly. I made the Context Layer into a skill where I describe the structure. So when I say, "reindex", the agent knows to check and update the index files. Also it knows if it modifies any file, it needs to also update the index. Works really well!

I found progressive discovery works very well. I have an INDEX.md file in every folder with a table describing what files are in that folder and what they do.

Very cool! I see the default way to collect data in the tool comes from Ginlix API, so I was wondering what is the self-hosting story? Is there a way to achieve the same functionality as the default website?

Currently looking for a good solution for exactly this. Druid looks very cool and thought-through. Two major blockers for me to use it in my workflow:

- Sandbox-only environment. For certian workflows I may want to run agents directly on my machine. - No Cursor agent support. Cursor supports ACP, so should in principle plug-in neatly in the existing framework.

Using the same approach for dev documentation storage: https://ctxlayer.dev/

Has been working for me for a couple of months already. So far human curation of context is the way to go.

Has been a game-changer for me. The following cases are where it shines:

- Figuring out the architecture of a project you just came into

- Tracing the root cause of a bug

- Quickly implementing a solution with known architecture

I figured out that above all, what makes or breaks success is context engineering. Keeping your project and session documentation in order, documenting every learning you've made along the way (with the help of AI), asking AI to compose a plan before implementing it, iterating on a plan before it looks good to you. Sometimes I spend several hours on a plan markdown document, iterating on it with AI, before pressing "Build" button and the AI doing it in 10 minutes.

Another important thing is verification harness. Tell the agent how to compile the code, run the tests - that way it's less likely to go off the rails.

Overall, since couple of month ago, I feel like I got rid of the part of programming that I liked the least - swimming in technicalities irrelevant for the overall project's objectives - while keeping what I liked the most - making the actual architectural and business decisions.

I wrote a blog recently about the approach that works for me: https://anatoliikmt.me/posts/2026-03-02-ai-dev-flow/

And this is a tool for context engineering I made specifically to support such a flow: https://ctxlayer.dev/