Featured · AI · 6 min
Why most "AI features" should be a button
Most of the AI bolted into products in 2026 makes them worse, not better. Here is when to ship it and when to walk away.
Bharat Kabra ·
INSIGHTS / Field notes from the practice
Notes from the
workbench.
Engineering essays, AI breakdowns, product notes, and a few honest dispatches from inside the company. Written by the people doing the work.
-
Product · 3 min
When to start writing the runbook
Hint: not after launch.
Bharat Kabra · -
Company · 4 min
Hiring senior engineers in 2026
Where good engineers actually come from, and how we filter without breaking ourselves.
The UVTL Team · -
AI · 5 min
A short list of evals every LLM product should have
You don't need 1,000 examples. You need 30 well-chosen ones.
Bharat Kabra · -
Company · 3 min
How we run weekly demos that don't waste time
The industry cliché is "weekly demos." Most of them are bad. Here's the structure we use.
The UVTL Team · -
Engineering · 5 min
Django still wins for AI-first products
In 2026, Django is the unfashionable choice that keeps winning. Here is why we pick it for most AI products.
Bharat Kabra · -
Company · 4 min
Six-week projects beat six-month projects
Why we deliberately scope our engagements down to six weeks, and what we throw out to make it work.
The UVTL Team · -
Engineering · 7 min
The boring parts of an AI agent that actually matter
Tool-calling and prompts are the fun part. Evals, observability, and rate-limiting are the parts that decide whether the agent makes it past month two.
Bharat Kabra ·