The 6 Pillars of an Agentic Harness for Production — Varun Krovvidi, Resolve AI
- Source
- youtube.com
- Author
- AI Engineer
- Date
Context
In an AI Engineer talk, Varun Krovvidi, product marketing lead at Resolve AI, argues that code is self-documenting, modular and a single domain, while production spans code, infrastructure, telemetry and many teams and needs one correct answer. The talk lists where agents break as they scale: anchoring on early guesses, too much or too little , answers that are coherent but not causal, missing , and no learning across investigations.
The six pillars of a answer these: model orchestration, , causal reasoning, governed actions, learning systems and evals. The description mentions a demo tracing a Grafana alert to a root cause. It reports no measured results, so treat the pillars as a design view from a company selling such an agent. Resolve AI also appears in another talk on always-on release checks.
- Krovvidi claims about 70% of engineering time goes to running and fixing software rather than writing it.
- His explanation for the gap: code is self-documenting, modular and one domain, while production spans code, infrastructure, telemetry and many teams and needs one correct answer.
- The five failure modes he lists: anchoring bias and the model treadmill, too much or too little context, answers that are coherent but not causal, missing guardrails, and no learning across investigations.
- Context and context window — Context is the information available for a generation; the context window is the capacity available to hold it.
- guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
- Harness — The software that sends a model its context, recognizes tool calls, runs or refuses them, returns results and keeps the record.
- context engineering — Deciding what an agent sees at each step — the discipline that replaced prompt engineering once context windows got large enough to fill badly.
Checking sign-in…
Loading comments…






