# Dots by OpenAI

Hacker Approved page: https://hackerapproved.com/p/dots/

16 people recommended Dots by OpenAI in Hacker News comments, 11 had mixed feelings and 64 criticized it, November 2025 to October 2026. It was recommended in 4 of 12 months, in 9 threads. It does not meet the Hacker Approved badge rule.

**Verdict:** Criticized more than recommended: critics worry about giving a third party access to data; those who recommend it see it as an always-on agent that captures tasks on the go and runs projects.

Summary written by Claude from the comments below.

## What people warn about

- Marketing oversells what it does (4 comments in the sample): "They're probably over-selling there." ([source](https://news.ycombinator.com/item?id=49897989)) "it feels like a bit of theater" ([source](https://news.ycombinator.com/item?id=49904512)) "Are you sure? Based on their marketing video, usually you just have to tell it to swap one of the later slides" ([source](https://news.ycombinator.com/item?id=49905049))
- Gives third party access to data (3 comments in the sample): "A big negative is that you are giving access to even more of your services and data to a third party" ([source](https://news.ycombinator.com/item?id=49907437)) "normalizing surveillance/becoming wholly reliant on a single service by making it cute with big eyes" ([source](https://news.ycombinator.com/item?id=49897564)) "Always a sure sign to be wary if they can’t square the product with data protection" ([source](https://news.ycombinator.com/item?id=49905436))
- Not reliable enough yet (3 comments in the sample): "it still doesn't seem to be progressing well because it hasn't fully matched the quality I want or my context" ([source](https://news.ycombinator.com/item?id=50300576)) "all the evidence I've seen points to their models being nowhere near good enough to do this reliably, consistently and responsibly." ([source](https://news.ycombinator.com/item?id=49906176)) "They must have edited out the 1 in 5 times the agents crap the bed and mess up something important." ([source](https://news.ycombinator.com/item?id=49898433))

## Why people recommend it

- Handles tasks like a personal assistant (3 comments in the sample): "It truly acts as a personal assistant/executive assistant in every regard now" ([source](https://news.ycombinator.com/item?id=50187535)) "That's been about the most useful thing so far." ([source](https://news.ycombinator.com/item?id=50186410)) "Your dot can take a project and run with it..." ([source](https://news.ycombinator.com/item?id=49904760))
- Better than other tools (3 comments in the sample): "isn't done better using other tools (e.g. dots" ([source](https://news.ycombinator.com/item?id=49989048)) "Dots is the better product overall right now." ([source](https://news.ycombinator.com/item?id=50195426)) "dots is clearly more useful" ([source](https://news.ycombinator.com/item?id=49980415))
- Works without context switching (1 comment in the sample): "i'm just glad i can use my Dootle Dots™ without context switching" ([source](https://news.ycombinator.com/item?id=49897931))

## Other AI agents people recommend

- [OpenClaw](https://hackerapproved.com/p/openclaw/): 379 recommend, 248 mixed, 856 criticize
- [Muse by Meta](https://hackerapproved.com/p/muse/): 88 recommend, 46 mixed, 212 criticize
- [NanoClaw](https://hackerapproved.com/p/nanoclaw/): 31 recommend, 12 mixed, 31 criticize
- [Clawdbot](https://hackerapproved.com/p/clawdbot/): 30 recommend, 33 mixed, 87 criticize

## Where to get it

- [Visit the official site](https://unity.com/)

## The badge

A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged.

## Cite as

Hacker Approved, "Dots by OpenAI", https://hackerapproved.com/p/dots/ (16 recommend, 11 mixed, 64 criticize; Hacker News comments, November 2025 to October 2026).

Counts updated 2 Nov 2026, with data through October 31, 2026.
