Anuj

About

Founder of OsmO — an AI call assistant for your phone. It screens spam, answers when you can't pick up, and makes routine calls (appointment confirms, follow-ups) for you. getosmo.app We're launching OsmO on Product Hunt on August 19 — follow along here: producthunt.com/products/osmo-2

Badges

Gemologist
Gemologist
Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
View all badges

Maker History

  • OsmO
    OsmOPersonal assistants that answer and make calls for you
    Sep 2026
  • 🎉
    Joined Product HuntJuly 1st, 2022

Forums

California's companion chatbot law has no small-dev exemption

Three states passed laws this year about AI that acts like it cares. If your product does that on purpose - not as a joke, as the actual feature - you're not adjacent to this. You're the definition.

I build an app that helps people process their emotions with an AI that remembers what they told it last time. When I went looking for whether that puts Murror inside any of the new AI-companion laws, the honest answer was: probably, and I wouldn't have guessed that a year ago.

Five ways in, one participant boundary

AI-driven sessions can arrive through different client protocols. DungeonQ s self-hosted reference exposes the same bounded participant operations over HTTP, MCP, SSH, a PostgreSQL-profile interface, and a private Unix workload broker.

The transport and actor capability determine the context; the request payload cannot choose its own destination or authority. SSH provides no general shell, and the PostgreSQL profile is not a general SQL server.

These are real, bounded client paths into explicitly provisioned synthetic worlds. The reference does not automatically classify attacks or transparently intercept arbitrary host activity. The runtime guide documents the adapters and their limits: https://github.com/Ranopha/dunge...

•

3d ago

Shipping a feature got cheap. Deciding to delete one didn't.

We've got 111 one click apps in Arteza across six studios. Building them was the easy part. With an agent you can take a prompt template to a shipped, working app in an afternoon, so adding one feels free and you stop asking whether it earns its place.

The bill arrives later. A menu nobody can scan. Support load for things almost nobody opens. And every model swap underneath means retesting all of it, because 111 apps sitting on 30+ models is a test matrix, not a feature list.

The mistake wasn't building them. It was not writing the kill rule first. If I'd set a number up front, opened by this many distinct people in 30 days or it goes, removal would be a rule instead of an argument. Now every deletion is a conversation with someone who liked that one.

Vibe coding collapsed the build cost and did nothing to the maintenance cost, so the ratio is worse than it has ever been. Most of the feature bloat I see right now isn't ambition, it's just that saying no got expensive relative to saying yes.

View more