The requests-only rule is the right call. I have seen VPA-style changes cause trouble when they touch limits or fight the autoscaler. Keeping limits as the team-owned ceiling and leaving HPA and KEDA resources alone makes an agent like this much easier to trust in production.
Your Kubernetes Requests Are a Guess. groundcover Wants an Agent to Keep Fixing Them.
Please log in to comment on this post.
More Posts
- © 2026 Coder Legion
- Feedback / Bug
- Privacy
- About Us
- Contacts
- You Tube
- Tiktok
- Premium Subscription
- Terms of Service
- Early Builders
chevron_left
290Posts
175Comments
145Connections
LLM Training & Evaluation Specialist with hands-on experience building major AI models. As one of th... Show moreLLM Training & Evaluation Specialist with hands-on experience building major AI models. As one of the original six members of Google's Bard training team (now Gemini) and current Meta AI Business Assistant evaluator, I understand how these models work from the inside out—and how developers can optimize them fI write about technology solutions that make life simpler and easier for developers, engineers, and architects. I use AI extensively in that work — not as the subject, but as the tool that helps me research faster, verify accuracy, and get to the point.
That AI fluency comes from direct experience: I was one of the original six members of Google's Bard training team (now Gemini) and currently evaluate Meta's AI Business Assistant. I understand how these models work from the inside, which shapes how I write about them for a technical audience.
I specialize in LLM evaluation, prompt engineering, and RLHF methodologies, and I write about real-world implementation challenges — not theoretical possibilities. I attend major tech conferences to stay close to what developers actually face when deploying AI in production. Show less
That AI fluency comes from direct experience: I was one of the original six members of Google's Bard training team (now Gemini) and currently evaluate Meta's AI Business Assistant. I understand how these models work from the inside, which shapes how I write about them for a technical audience.
I specialize in LLM evaluation, prompt engineering, and RLHF methodologies, and I write about real-world implementation challenges — not theoretical possibilities. I attend major tech conferences to stay close to what developers actually face when deploying AI in production. Show less
More From Tom Smithverified
Related Jobs
- Senior Software Engineer II - Agentic IntelligenceHoneycomb.io · Full time · Canada
- Senior Software Engineer II - Agentic IntelligenceHoneycomb.io · Full time · Canada
- Senior Software Engineer I - Agent ObservabilityHoneycomb.io · Full time · Canada
Commenters (This Week)
nik-13
5 comments
fazal_mansuri_
1 comment
Nisse-Sec
1 comment
Contribute meaningful comments to climb the leaderboard and earn badges!