Abhay Padamani

Hey everyone

Like a lot of you, I use AI coding agents (Claude Code / Codex) daily, and token usage adds up fast especially on large codebases where the agent burns context just orienting itself.

I contribute to OpenObserve (open-source observability platform, large Rust + Vue codebase), and here's what's actually moved the needle for me:

1. CLAUDE.md / AGENTS.md files a short project map (architecture, conventions, key file paths) so the agent doesn't re-explore the repo every session. Biggest single win.

2. Scoped prompts over vague ones "fix the null check in parseQuery() in src/utils/query.ts" costs a fraction of "the query parser is broken, fix it."

3. Fresh sessions per task long conversations drag the entire history into every request. Clearing context between unrelated tasks cuts spend noticeably.

4. Plan first, execute second asking for a plan in plain text, approving it, then executing beats letting the agent trial-and-error its way through with expensive tool calls.

5. Right-sizing the model using cheaper/faster models for boilerplate and refactors, saving the big model for architecture and tricky debugging.

Hey everyone, I'm Abhay

I'm a software engineer contributing to OpenObserve, an open-source observability platform (Rust backend, Vue frontend). Most of my work is on the frontend design system and developer tooling lately I've been deep in a large component migration and building Claude-powered PR review automation with GitHub Actions.

One thing I'm genuinely trying to figure out: for those of you using AI in your code review or CI pipelines, where has it actually saved you time vs. added noise? I've found it great for catching style drift and missed edge cases, but I'm still tuning how much to trust it on architectural feedback.

Happy to share what I've learned about open-source contribution workflows or setting up AI code review in GitHub Actions if that's useful to anyone. Looking forward to being here!