viraldi.
Video details
How it works
Back to discovery
20:20
Technology & Computing / VIDEO

How to Build Agents That Improve Over Time: Model, Harness, Context | Interrupt London

LangChain· 209K subscribers

1d ago · English audio

Harrison Chase, Co-Founder and CEO of LangChain, splits an agent into three parts, the model, the harness, and the context, and explains how each one can improve over time: the model's weights through supervised fine-tuning with LangSmith Fine-Tuning and its smithtune CLI, or through RL for more complex tasks; the harness through LangSmith Engine, a deep agent that runs over traces, clusters issues, and proposes…

Watch on YouTube
5.0×Score at discovery
24.9KViews
4.4KMedian · 42 videos

Outlier score

This score was measured on Wed, 28 Oct 2026 19:03:22 GMT. Current view counts may differ.

22.3K views ÷ a 4.4K baseline = 5.0×. Compared with 42 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: Wed, 28 Oct 2026 23:29:34 GMT. Counters may have changed.

Read the methodology

Artificial Intelligence & Data

Channel-balanced percentile: 60

Comparison details

20 videos from 19 other channels, with each channel weighted equally. Same format and language, with 100,000–999,999 subscribers. Observed at 31 hours after publication, within ±6 hours.

The comparison uses this broader topic because the specific niche has too few examples. This describes the collected sample, not all of YouTube. Updated Wed, 28 Oct 2026 23:42:06 GMT.

Niches & tags

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

Breakouts from other channels