Daily Dose of Data Science

Daily Dose of Data Science

Why Multi-turn Agents Need More Than a Task Graph
What production agents must preserve between turns, and what they must reset.
 • Avi Chawla
Your Agent Harness Needs Runtime Security
A 100% local, open-source guide to recording what AI agents actually do at runtime.
 • Avi Chawla
Momentum in ML, Explained Visually and Intuitively!
(a popular ML interview question)
 • Avi Chawla
LLM Routing Can Cost More Than Not Routing
...covered with a production-grade router for LLM apps.
 • Avi Chawla
KV Cache Engineering for LLM Serving
12 techniques to manage KV cache in production.
 • Avi Chawla
5 Embedding Compression Techniques
...explained visually.
 • Avi Chawla
Attention Mechanisms in LLMs, clearly explained
Everything you need to understand how attention works, why the KV cache is the bottleneck, and what every attention variant is actually solving.
 • Avi Chawla
Stop Guessing Which Local Model To Run
A practitioner's guide to local AI.
 • Avi Chawla
Static vs. Dynamic vs. Continuous Batching in LLMs, clearly explained!
+ a popular LLM interview question.
 • Avi Chawla

August 2026

© 2026 Avi Chawla · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture