Skip to main content
Software Engineering Daily

Engineering in the Age of Agents with Yechezkel Rabinovich

50 min episode · 2 min read
·
Yechezkel Rabinovich

Episode

50 min

Read time

2 min

Topics

Productivity, Remote Work, Design & UX

AI-Generated Summary

Key Takeaways

  • eBPF Instrumentation: Groundcover uses eBPF sensors to capture logs, metrics, and traces directly from the kernel without modifying application code, providing 100% visibility including unknown dependencies like third-party API calls that developers didn't explicitly instrument.
  • AI Code Review Strategy: With AI generating code at superhuman speed, code review must focus on test quality first, then context-dependent factors like performance for high-throughput systems versus simple input-output validation for low-risk libraries with no side effects.
  • MCP API Design: Effective LLM integration requires restricting API parameters beyond human SDKs, making certain fields required to force proper investigation flow, limiting results to 20 items, and exposing simpler endpoints first to prevent agents from requesting overwhelming data volumes.
  • Bring Your Own Cloud: Groundcover runs entirely within customer cloud accounts, keeping all observability data and AI analysis inside their security perimeter, addressing privacy concerns when LLMs process logs and traces that may contain PII or sensitive architectural information.

What It Covers

Yechezkel Rabinovich, CTO of Groundcover, explains how eBPF-based observability captures system behavior without code instrumentation, addresses AI-generated code challenges, and approaches root cause analysis in distributed microservices architectures.

Key Questions Answered

  • eBPF Instrumentation: Groundcover uses eBPF sensors to capture logs, metrics, and traces directly from the kernel without modifying application code, providing 100% visibility including unknown dependencies like third-party API calls that developers didn't explicitly instrument.
  • AI Code Review Strategy: With AI generating code at superhuman speed, code review must focus on test quality first, then context-dependent factors like performance for high-throughput systems versus simple input-output validation for low-risk libraries with no side effects.
  • MCP API Design: Effective LLM integration requires restricting API parameters beyond human SDKs, making certain fields required to force proper investigation flow, limiting results to 20 items, and exposing simpler endpoints first to prevent agents from requesting overwhelming data volumes.
  • Bring Your Own Cloud: Groundcover runs entirely within customer cloud accounts, keeping all observability data and AI analysis inside their security perimeter, addressing privacy concerns when LLMs process logs and traces that may contain PII or sensitive architectural information.

Notable Moment

Rabinovich describes creating a TypeScript library without knowing TypeScript by manually crafting test scenarios and letting AI generate implementation, never reading the actual code because the library's simple input-output nature made implementation details irrelevant for that specific context.

Know someone who'd find this useful?

Episode Transcript

Modern software platforms are increasingly composed of diverse microservices, third party APIs, and Cloud resources. The distributed nature of these systems makes it difficult for engineers to gain a clear view of how their systems behave, which can slow down troubleshooting and increase operational risk. Groundcover is an observability platform that uses eBPF sensors to capture logs, metrics, and traces directly from the kernel. Critically, GroundCover runs on a bring your own Cloud model, so all data remains within the user's own environment, which gives increased privacy, security, and cost efficiency. The company is also focused on adapting to how AI generated code is changing observability. Code can now be produced at superhuman speed, which increases the challenges for reviewing code before it enters production. This means that observability is likely to play a growing role in code validation and providing guardrails. Yaheskel Rabinovich, or Chez, is the CTO and cofounder of Groundcover. He joins the podcast with Kevin Ball to discuss his journey from kernel engineering to building an eBPF powered observability company. The conversation explores the power of eBPF, the realities of observability in modern systems, the impact of AI on software development and security, and where the future of root cause analysis is headed. Kevin Ball, or Kate Ball, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He cofounded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI in Action discussion group through Latent Space. Check out the show notes to follow Kbal on Twitter or LinkedIn, or visit his website, kbal.llc. Hey, Chez. Welcome to the show. Hey. Thank you. Nice to be here. Yeah. I'm excited to have this conversation. Let's maybe start a little bit about you. So can you give our listeners just a little bit of your background and then how you got to ground cover, where we are today? Yeah. Sure. More than a decade in software engineering, specialized in, Linux and distributed systems. So mainly worked on, kernel modules until I, got sick of it and then, kinda got in love with eBPF. Then we founded Browncover, which I'm I'm the CTO and cofounder, that's what I'm doing for the last four years. EBPF is really cool. We did another episode about that, and I hadn't been exposed before. My previous Linux background had been fifteen, twenty years ago. And then coming in and being like, wait. You mean to integrate with the kernel? I don't have to go through this arduous patch process and and kernel process. It was mind blowing. So, actually, let's maybe even start a little bit there. So how are you utilizing eBPF for ground cover? Yeah. So, as you said, after a few years with, kernel models, you kinda fall in love with the power of extending the kernel, which is very cool, but it's also very, very hard. The development cycle is so slow because any …

Get the full transcript (7,868 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all Software Engineering Daily transcripts →

You just read a 3-minute summary of a 47-minute episode.

Get Software Engineering Daily summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from Software Engineering Daily

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best Cybersecurity Podcasts (2026) — ranked and reviewed with AI summaries.

You're clearly into Software Engineering Daily.

Every Monday, we deliver AI summaries of the latest episodes from Software Engineering Daily and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime