viraldi.
Back to discovery
17:33
Technology & Computing / VIDEO

How to Know When an AI Agent Can Work Unsupervised — Evan Kormos, Coinbase

AI Engineer· 864K subscribers

5d ago · English audio

Evan Kormos, a player-coach at Coinbase with 15 years in enterprise financial services, lays out a practical way to bring agents into policy-driven, regulated workflows. He models processes as DAGs and loops, explains why a loop is only as trustworthy as its check, and shows how evals and traces become a new confidence mechanism. Agents then move through three stages: fully supervised, then sampled, then humans…

3.3×Score at discovery
17.1KViews
5.2KMedian · 38 videos

Outlier score

This score was measured on Sun, 25 Oct 2026 12:13:19 GMT. Current view counts may differ.

17.1K views ÷ a 5.2K baseline = 3.3×. Compared with 38 earlier videos from the same channel, matching the format recorded at scoring time. Older-upload baseline: reference videos had at least as long to gain views. This comparison is not age-matched.

YouTube snapshot: Sun, 25 Oct 2026 15:30:44 GMT. Counters may have changed.

Read the methodology

Generative AI & Agents

Channel-balanced percentile: 45

Comparison details

43 videos from 32 other channels, with each channel weighted equally. Same format and language, with 100,000–999,999 subscribers. Observed at 137 hours after publication, within ±27 hours.

This describes the collected sample, not all of YouTube. Updated Sun, 25 Oct 2026 15:44:36 GMT.

Niches & tags

Transcripts and detailed analytics are available for recent outlier Shorts up to three minutes. Research tools