Skip to main content
Software Engineering Daily

Engineering AI Systems for Autonomy and Resilience with Krishna Sai

53 min episode · 2 min read
·
Krishna Sai

Episode

53 min

Read time

2 min

Topics

Design & UX, Artificial Intelligence, Software Development

AI-Generated Summary

Key Takeaways

  • AI Coding Adoption Metrics: SolarWinds deployed AI-assisted coding across all engineers, measuring a 25-30% increase in pull request commit velocity and improved deployment frequency. The bottleneck has shifted from code generation to code review, which becomes the next target for AI tooling. Teams should measure lead time and change failure rate, not just lines generated.
  • Three-Plane Platform Architecture: Design AI-operational systems across three explicit planes — data (metrics, events, logs, traces ingestion and normalization), control (policies and actions), and reasoning (where agents operate). This separation mirrors Kubernetes-style design and ensures the reasoning plane can propose actions without having direct execution authority, enforcing least-privilege by default.
  • LLM Gateway as Foundation: Wiring raw logs directly to LLMs works in demos but fails in production through unpredictable cost spikes, PII exposure, and vendor lock-in. Centralizing model selection, PII masking, rate limiting, and auditability into a shared LLM gateway service before any downstream agent consumes data prevents these failure modes at scale.
  • Tiered Autonomy Levels: Avoid treating agent autonomy as a binary on/off switch. Structure it as progressive tiers — recommend only, execute with approval, then execute autonomously within defined constraints — tunable per action type, environment, service, or team. This allows safe production deployment while building organizational trust in agentic behavior incrementally over time.
  • Context Engineering Replaces Logic Authoring: The engineering role is shifting from writing deterministic business logic to designing the context that reasoning systems consume. Engineers who treat unexpected agent outputs as missing context rather than system failure iterate successfully. Teams with clear ownership and strong operational fundamentals use agents as force multipliers; those without struggle with unpredictability.

What It Covers

SolarWinds CTO Krishna Sai outlines how enterprise IT operations is shifting from reactive dashboards and copilot tools toward ambient agentic AI systems that autonomously detect, correlate, and remediate production issues — while engineering teams adapt their roles from writing business logic to designing context for AI reasoning systems.

Key Questions Answered

  • AI Coding Adoption Metrics: SolarWinds deployed AI-assisted coding across all engineers, measuring a 25-30% increase in pull request commit velocity and improved deployment frequency. The bottleneck has shifted from code generation to code review, which becomes the next target for AI tooling. Teams should measure lead time and change failure rate, not just lines generated.
  • Three-Plane Platform Architecture: Design AI-operational systems across three explicit planes — data (metrics, events, logs, traces ingestion and normalization), control (policies and actions), and reasoning (where agents operate). This separation mirrors Kubernetes-style design and ensures the reasoning plane can propose actions without having direct execution authority, enforcing least-privilege by default.
  • LLM Gateway as Foundation: Wiring raw logs directly to LLMs works in demos but fails in production through unpredictable cost spikes, PII exposure, and vendor lock-in. Centralizing model selection, PII masking, rate limiting, and auditability into a shared LLM gateway service before any downstream agent consumes data prevents these failure modes at scale.
  • Tiered Autonomy Levels: Avoid treating agent autonomy as a binary on/off switch. Structure it as progressive tiers — recommend only, execute with approval, then execute autonomously within defined constraints — tunable per action type, environment, service, or team. This allows safe production deployment while building organizational trust in agentic behavior incrementally over time.
  • Context Engineering Replaces Logic Authoring: The engineering role is shifting from writing deterministic business logic to designing the context that reasoning systems consume. Engineers who treat unexpected agent outputs as missing context rather than system failure iterate successfully. Teams with clear ownership and strong operational fundamentals use agents as force multipliers; those without struggle with unpredictability.

Notable Moment

Sai describes a ticket-routing agent in SolarWinds' ITSM product that reads full incident history, generates a contact summary, and drafts a suggested response before a human agent ever opens the ticket — reducing mean time to resolution by 30 to 50% with near-immediate user adoption upon release.

Know someone who'd find this useful?

Episode Transcript

Enterprise IT systems have grown into sprawling, highly distributed environments spanning cloud infrastructure, applications, data platforms, and increasingly AI driven workloads. Observability tools have made it easier to collect metrics, logs, and traces, but understanding why systems fail and responding quickly remains a persistent challenge. As complexity continues to rise, the industry is looking beyond dashboards and alerts towards agentic AI systems that can reason about operational data, reduce toil, and take action when things go wrong. SolarWinds offers solutions to monitor, understand, and remediate issues across complex distributed systems. The company began as a leader in network and infrastructure monitoring, and has evolved to support modern applications, cloud environments, containers, and AI workloads with a growing focus on reducing operational toil. Krishna Sai is the chief technology officer at SolarWinds. He joins the show with Sean Falconer to discuss how SolarWinds is rethinking observability in the age of AI, what it means to design agentic systems for mission critical environments, how AI assisted programming is reshaping engineering workflows, and why the future of operations depends on building platforms where humans and autonomous agents work together. This episode is hosted by Sean Falconer. Check the show notes for more information on Sean's work and where to find him. Sai, welcome to the show. Thanks, Sean. It's great to see you and me too. Big fan of the show, so thanks for having me here. Oh, well, thank you so much. That's nice to hear. Yeah. I'm looking forward to this as well. So I wanted to start off talking a little bit about, you know, SolarWinds and kind of set the stage there because I think a lot of people know SolarWinds. Maybe it's, like, a single tool that they used, you know, years ago, but you guys do a lot of different things. So given where you are today, like, how would you describe what SolarWinds actually is today to someone who hasn't looked at the space in a while? No. Absolutely. If you take a step back and say how IT and ops teams who typically use Solovance products have been using Solovance for the past, like, twenty five years or so, you know, our product portfolio broadly expands three domains, observability, incidence response and service management. And to put it simply, IT and ops teams use us to help detect and remediate issues across a variety of workloads and environments, Network and infrastructure, which is where we started and have been a leader for a very long time, but also applications, databases, containers, ML workloads, etcetera. And so our solutions cover this from a horizontal perspective, meaning give you the ability to look at the general basic health of the typical workloads, compute, storage, network, etcetera, but also vertical cross cutting concerns like performance, reliability, you know, cost, security, and so on. Right? And what happens is typically, IT and ops teams are accountable for SLAs and SLOs. Right? Like and that kinda drives your day to …

Get the full transcript (9,490 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 50-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.

Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.

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