SIX QUESTIONS / PRE-ANSWERED

The six questions I'd ask any AI team

— answered about my own work first. If I'd ask it of you, it's only fair I answer it about myself.

Q1

How do you evaluate agent and RAG quality in production — and who owns the eval suite?

Six layers, grown from shipping an AI judge. A golden dataset before trusting anything: 1,000+ tickets already rated by in-charges, compared dimension by dimension — nothing shipped until the system cleared 90%+ agreement with the human judgments. 500+ regression cases run before every release, with a staged rollout: a specific real-user group first, then the real world. Self-consistency as a tripwire: status and rating must correlate, so a broken correlation surfaces edge cases automatically, and errors alert the involved parties by email and Slack — failures announced themselves. Structural checks before quality checks: validate → ask → execute → notify caught malformed actions mechanically. Wrong outputs became permanent tests, never fixed-and-forgotten. And a live appeal loop as ongoing evaluation: challenged ratings turn into new parameters and rules — the users' pushback became the eval. The suite was mine as tech lead — if the person who owns the architecture doesn't own the definition of 'working', the two drift apart.

Q2

What's the worst failure your AI system has had in production, and what changed after it?

The retry storm. V1 let agents retry freely; one malformed input, one night, and retries multiplied into duplicated downstream business actions. Fixed within a week — Redis-backed idempotency keys on every action, plus a circuit breaker, because retries assume failure is transient and a malformed input is not. Changed permanently: every integration since starts with the failure path.

Q3

Where does the model boundary sit — fine-tuning, or prompting and retrieval over APIs?

At Wiffy: both, and settled — they solve different problems. RAG answers what the data says; fine-tuning answers what a question even means in our application, so domain interpretation lived in the weights of LLaMA and Mistral — a call that also tipped on practical grounds: data privacy, cost at volume, and latency. In my own products it's a live debate I re-argue per product, and the tiebreaker is unit economics — any answer that only works at API prices isn't an answer at consumer scale.

Q4

What does the AI layer look like in eighteen months — and what breaks first at 10x usage?

If things go right: VisionAI on real homes and schools, Kept at wedding scale, GameMind earning its first real-time commentary. What breaks first at 10x, in order: the human review loop, then inference cost, then retrieval quality — which degrades quietly, and quiet degradation is the dangerous kind. What doesn't break, by design: the event-driven backbone — 10x should be a provisioning problem, not an architecture problem.

Q5

What would my first ninety days own end to end — not contribute to, own?

Days 1–30: understand before touching — map the system, read the incidents, ship one small real improvement to earn trust. Days 31–60: own one outcome end to end with a number attached — the thinnest slice that touches production and carries real risk; I want the pager, not just the pull request. Days 61–90: make it repeatable — regression set, documented decisions, onboarding. One production outcome by day sixty, the system that keeps it healthy by day ninety.

Q6

How do you lead when things are on fire?

Three real fires, one playbook. The retry storm: stabilize first, blame never — the malformed input that caused it lives in the regression set forever, and the incident became a design principle: the failure path comes first. The 10-month mandate: pressure gets absorbed at the top, not passed down — the quality bar stayed up through design, code, and functional reviews with CI regression on every merge, and release velocity still rose 30%. Calm is a leadership deliverable. Growing six engineers into event-driven production under deadline: shrink the blast radius until mistakes are affordable — small services, replayable events, and at Classplus, validation in headless environments before every 50,000-viewer event. The through-line: build the system, human and technical, where mistakes are survivable and nobody is afraid to report breakage.

If you'd answer these six differently about your own systems — that's exactly the conversation I want to have.

START THAT CONVERSATION — BHAGAT99198@GMAIL.COM →