Santosh Savel

Santosh Savel

Creator of Neural Gains Weekly, a free newsletter on using AI in everyday work, and co-host of Explore AI Out Loud, the video podcast with Brandon Ratay. A non-technical professional building with AI in public.
04
Aug

Volume 45: Your Words Need Somewhere to Land

A 4K screenshot does not reach the model at 4K. It is scaled to a resolution cap, cut into squares, and converted into visual tokens, which is why small text and exact numbers get lost, and why cropping tight before you upload changes the answer you get back.
15 min read
04
Aug

The Work Starts Before You Talk to AI

I tested both July voice upgrades on real tasks from my own life. One session stopped at a plan because the file sat outside the workflow I had built, and the other finished the job because my inbox and calendar were already connected.
5 min read
04
Aug

Steal My Prompt Vol. 45: The Coverage Brief

Most handoffs fail because they list projects instead of decisions. This prompt takes a two minute spoken brain dump and returns a coverage brief sorted into what your backup can decide alone, what waits for you, and what gets escalated.
4 min read
28
Jul

Volume 44: Nobody Is Coming to Hand You a Use Case

A model does not read text. It processes tokens, and images, scans, and screenshots become tokens too, which is why you can hand it a photo of a page instead of retyping the whole thing.
15 min read
28
Jul

The Build Waiting in Your Living Room

I did not go looking for an AI use case. A problem in my own living room handed me one, and the system I built around it in a single night is the whole distance from user to builder.
6 min read
28
Jul

Steal My Prompt Vol. 44: The Conflict De-Escalation

A copy-paste prompt for the conversations that ambush you. It interviews you about the outcome you actually want, then returns three responses ordered from cooler to warmer, names which one to lead with, and lists the phrases that would pour fuel on the fire.
5 min read
21
Jul

Volume 43: The Terminal Teaches Faster Than the Tutorial Does

Copilot, Claude, and NotebookLM all search by matching meaning instead of keywords, turning your files into a map of related ideas. That same shortcut can also return the nearest answer instead of the correct one, especially with messy data, mixed-up jargon, or oversharing permissions.
14 min read
21
Jul

The Future of Work Is Here, Waiting to Be Claimed

I approve terminal commands at home without thinking. At work, one request to change files on someone else's machine stopped me cold and taught me more than months of easy reps: claiming the future of work means choosing discomfort before anyone hands you permission.
5 min read

Before you go: one email every Tuesday.

A full Neural Gains Weekly issue one week, the best lesson from the new podcast episode the next. Free, plain English, no hype.

Subscribe for free