Engineering AI Systems for Autonomy and Resilience with Krishna Sai

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.