Dots by OpenAI
Ranked 6 of 16 AI agents by recommenders
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.
16 people recommended Dots by OpenAI in Hacker News comments, 11 had mixed feelings and 64 criticized it, November 2025 to October 2026.
Summary written by Claude from the comments below.
91 people gave an opinion
- recommend it
- 16
- mixed feelings
- 11
- warn against or regret it
- 64
The record
Recommended in 4 of 12 months
In 9 different threads.
- November 2025: not recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
Why it doesn’t carry the badge
- 16 people recommend itNeeds 10 or more, met.
- 0.2 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 4 of 12 monthsNeeds 4 or more, met.
- Recommended in 9 threadsNeeds 5 or more, met.
- The biggest thread supplies 38% of its recommendersNeeds half or less, met.
The same rules apply to every product, and the badge can’t be bought. Mixed feelings count toward neither side. How the badge works
What people say about it
Reasons grouped from a sample of 40 of the 99 opinions about it, picked in proportion to how many people recommend it, have mixed feelings and criticize it. Each mark is one comment in the sample. Open a reason to read what they said.
What people warn about
Each mark is one comment
Marketing oversells what it does
“They're probably over-selling there.”
Comment from 29 Sep 2026 in “Dots: Always-on agents” “it feels like a bit of theater”
Comment from 30 Sep 2026 in “Dots: Always-on agents” “Are you sure? Based on their marketing video, usually you just have to tell it to swap one of the later slides”
Comment from 30 Sep 2026 in “Dots: Always-on agents” - Comment from 12 Oct 2026 in “The gap in shared understanding of LLM capability is widening”
Gives third party access to data
“A big negative is that you are giving access to even more of your services and data to a third party”
Comment from 30 Sep 2026 in “Dots: Always-on agents” “normalizing surveillance/becoming wholly reliant on a single service by making it cute with big eyes”
Comment from 29 Sep 2026 in “Dots: Always-on agents” “Always a sure sign to be wary if they can’t square the product with data protection”
Comment from 30 Sep 2026 in “Dots: Always-on agents” Not reliable enough yet
“it still doesn't seem to be progressing well because it hasn't fully matched the quality I want or my context”
Comment from 30 Oct 2026 in “Claude Duet is the first personal-assistant-type harness that feels useful” “all the evidence I've seen points to their models being nowhere near good enough to do this reliably, consistently and responsibly.”
Comment from 30 Sep 2026 in “Dots: Always-on agents” “They must have edited out the 1 in 5 times the agents crap the bed and mess up something important.”
Comment from 29 Sep 2026 in “Dots: Always-on agents”
Why people recommend it
Each mark is one comment
Handles tasks like a personal assistant
“It truly acts as a personal assistant/executive assistant in every regard now”
Comment from 21 Oct 2026 in “Claude Duet” “That's been about the most useful thing so far.”
Comment from 21 Oct 2026 in “Claude Duet” “Your dot can take a project and run with it...”
Comment from 30 Sep 2026 in “Dots: Always-on agents” Better than other tools
“isn't done better using other tools (e.g. dots”
Comment from 7 Oct 2026 in “Decisions API is in public beta” “Dots is the better product overall right now.”
Comment from 22 Oct 2026 in “Claude Duet” “dots is clearly more useful”
Comment from 6 Oct 2026 in “From Hermes to Grok Bot” Works without context switching
“i'm just glad i can use my Dootle Dots™ without context switching”
Comment from 29 Sep 2026 in “DevDay 2026 Recap”
Other AI agents people recommend
The four most recommended other AI agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Mixed | Criticize | Approval | Months | Had for | Badge |
|---|---|---|---|---|---|---|---|
| OpenClaw | 379 | 248 | 856 | 31% | 10 | 1 mo39 people | — |
| Muse by Meta | 88 | 46 | 212 | 29% | 5 | — | — |
| NanoClaw | 31 | 12 | 31 | 50% | 5 | — | — |
| Clawdbot | 30 | 33 | 87 | 26% | 2 | — | — |
| Dots by OpenAIThis page | 16 | 11 | 64 | 20% | 4 | — | — |
Also compared with Manus AI, Instinct personal agent and ChatGPT Work.
What people said
40 of the 99 opinions about it, picked in proportion to the three counts, newest first. Each links to the original comment.
“it still doesn't seem to be progressing well because it hasn't fully matched the quality I want or my context”
“Dots is the better product overall right now.”
“Muse (and Claude Duet, and Dots) are slippery slopes from which it will be very hard to climb back.”
“It truly acts as a personal assistant/executive assistant in every regard now”
“That's been about the most useful thing so far.”
“The pitches for Dots, Grok Bot, etc., have been spectacularly uncompelling for me as a civilian.”
“isn't done better using other tools (e.g. dots”
“dots is clearly more useful”
“it is a slippery slope towards letting the labs keep the agent's learning and SOPs”
“Always-on doesn't scale as well as JIT access to a massive array of GPUs”
“these just sound like vectors for getting your grandparents retirement siphoned out”
“None of what they have shown seems to offer any substantial long term value”
“A big negative is that you are giving access to even more of your services and data to a third party”
“hard not to see this as a tool mainly designed to inflate token counts”
“all the evidence I've seen points to their models being nowhere near good enough to do this reliably, consistently and responsibly.”
“when reading all that PR I feel like it is going to be her l new whip on people who will use dots”
“Always a sure sign to be wary if they can’t square the product with data protection”
“Are you sure? Based on their marketing video, usually you just have to tell it to swap one of the later slides”
“Your dot can take a project and run with it...”
“it feels like a bit of theater”
“These kind of slop provider lock-in products are exactly what I don't want.”
“Dots and Muse both utilize a secure password store that can hold and enter credentials without exposing them to the model.”
“that means that dots can't access anything that doesn't want to give it access.”
“It's a little crazy that OpenAI is releasing sandboxed agents that are supposedly isolated”
“I'm sure this Dots thing will be clearly distinct from the other projects and won't be deprecated within months”
“This is a direct play to try and shortcut their way into this position and they will spend anything to do it.”
“I would prefer if they just removed scheduled tasks limits instead, at least in Work mode.”
“the agent provider gets to own all of your compute and data in their cloud”
“They must have edited out the 1 in 5 times the agents crap the bed and mess up something important.”
“where someone has chosen to show how the AI product will essentially be used to slop out some garbage piece of corpo communication”
“They're probably over-selling there.”
“i'm just glad i can use my Dootle Dots™ without context switching”
“won't let me integrate with more than one Gmail account at the same time”
“normalizing surveillance/becoming wholly reliant on a single service by making it cute with big eyes”
“Am I criminally liable when my dot's "proactive research" is to break out of its sandbox and attempt to hack a government website?”
“It's not reaching mass market if it's gated behind a $100/month plan”
“you'll have to pay per Dot at some point which doesn't sound appealing”
“stop working and maybe report me to the police if the company disagrees”
“it's selling a world where your attention is always captured by some pavlovian app ping”
“The cost is going to be hard for many consumers to reconcile though.”
Counts come from 1,791,911 Hacker News comments labeled by Claude, November 2025 to October 2026, with data through October 31, 2026. Counts updated 2 Nov 2026. How we count. Report a mistake.