--- title: Claude Duet is the first personal-assistant-type harness... description: A developer reviews Duet, an Anthropic chatbot assistant, calling it more useful than rivals like Muse, Dot, and NanoClaw. Duet is supposedly powered by Opus... canonical: https://daily.dev/posts/claude-duet-is-the-first-personal-assistant-type-harness-that-feels-useful-xezaurczu twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Claude Duet is the first personal-assistant-type harness that feels useful | daily.dev og:description: A developer reviews Duet, an Anthropic chatbot assistant, calling it more useful than rivals like Muse, Dot, and NanoClaw. Duet is supposedly powered by Opus... og:url: https://daily.dev/posts/claude-duet-is-the-first-personal-assistant-type-harness-that-feels-useful-xezaurczu og:image: https://api.daily.dev/og/posts/xeZauRCzu.png og:image:alt: Claude Duet is the first personal-assistant-type harness that feels useful og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Claude Duet is the first personal-assistant-type harness that feels useful **[Hacker News](https://daily.dev/sources/hn)** · 5 min read · 0 upvotes · 0 comments ## Summary A developer reviews Duet, an Anthropic chatbot assistant, calling it more useful than rivals like Muse, Dot, and NanoClaw. Duet is supposedly powered by Opus 5.5 and feels faster than other Claude interfaces. It organizes work into channels, with access to GitHub repos restricted per channel, stores no credentials, and keeps responses short. The reviewer notes it's still in beta with glitches, like repo access sometimes failing to attach, and says Dot still reigns on voice interaction. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What model powers Anthropic's Duet assistant? Duet is supposedly powered by Opus 5.5, according to a hands-on reviewer who noted it feels faster than Opus has felt in other Claude interfaces, suggesting Anthropic applied additional performance tuning specifically for Duet's response speed. _Developers evaluating Claude-based agent tools can track model and tooling changes like this on daily.dev._ ### How does Duet handle access to GitHub repos and credentials? Duet restricts GitHub repo access per channel, so repos added to one channel do not mix with other projects, and it stores no credentials at all, actively discouraging users from providing them. At most it may use a Chrome session on the user's behalf, preferring Claude's existing connector ecosystem instead. _Anyone weighing agent tools against credential-sharing risk can follow these security-conscious design choices on daily.dev._ ### What problems does Duet currently have in beta? Duet has glitches in beta, including threads that run but are not visible in the interface, and delegated repo access that sometimes fails to attach correctly, possibly due to a race condition between agent start and access attachment. _Developers deciding whether to adopt a beta agent tool can watch for rough edges like these on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 98 comments across hackernews (as of 2026-10-30). **TL;DR:** Reactions are split between enthusiasm for Duet's channels, speed, and Opus 5.5 backing, and heavy skepticism about agentic assistants generally—especially around credential handling, prompt injection, and whether purchases/actions are truly safe—with many preferring rival tools like Grokbot or self-built harnesses. **Sentiment:** 30% positive · 40% mixed · 30% skeptical **The case for** - Channels and per-channel repo access are seen as genuinely useful features. - Several found it noticeably faster and less error-prone than other Claude interfaces, attributing it to Opus 5.5. - Some report real productivity wins from similar agent setups, like running multi-day coding projects unattended. - One long-time user found research/filtering use cases (deals, events, schedules) to be the most compelling application. **The pushback** - Many are wary of granting agents credentials, payment info, or broad access given prompt-injection and 'lethal trifecta' risks. - Several say purchase/approval safeguards are not as foolproof as advertised, since 'purchase' is hard to define in software. - Multiple commenters report the underlying models still make basic mistakes or lie about completing tasks. - Some testers found it missing features compared to rivals (no phone calls, no VM shell access, flaky repo attachment) and not clearly faster than competitors. - A number of people argue these harnesses are easy to replicate with a custom-built agent, reducing the value of proprietary products. - Many prefer competing products (notably Grokbot) for overall usefulness, voice interaction, or simplicity. **By community** - hackernews (mixed): Discussion splits between genuine interest in Duet's channel/speed improvements and broader skepticism about agent security, credential handling, and whether it beats established rivals like Grokbot and Dot. **Hottest debate:** Whether giving these assistants access to credentials, payments, and personal data is a reasonable trade-off or an unacceptable security/privacy risk. **Open questions** - Can prompt injection and 'lethal trifecta' risks actually be solved, and how would that be proven? - How exactly do harness-enforced purchase limits distinguish a 'purchase' from other actions, and how reliable are they? - Does Duet integrate with existing credential managers like 1Password, and how well does it handle sensitive data compared to competitors? **Highlights** > Yeah, that's the core of the issue: https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/ The "lethal trifecta": To be useful, an agent needs internet access, untrusted inputs, and your private information. So it can get prompt injected and exfiltrate your data. (Indeed I read that Claude Code puts your email address into HTTP requests it makes to random servers?) My solution here was to just not give it anything, but that does preclude the "my claw bought a car!" result everyone's excited about. My way of thinking here is "blast radius". Assume it will get prompt injected. What goes wrong? Then design the setup so that scenario is not bad. e.g. it has my keys but they've got $5 of credit on them. It has access to the filesystem, but only on its own Linux account. (Ok I set this up last year before they could communicate thru the bloody CPU cache, might need an update :) > — [andai on hackernews · 3 comments](https://news.ycombinator.com/item?id=50296416) > I've recently talked to people at Anthropic who are very confident that they have effectively solved the prompt injection risks that cause lethal trifecta attacks with their latest models. The open challenge is how to prove it! > — [simonw on hackernews · 7 comments](https://news.ycombinator.com/item?id=50297369) > The problem is how do you define a "purchase"? The agent crawls some websites and reads some stuff and pushes some buttons. It's my limited understanding that you have 1. Hard limits like "file system permissions" (* never mind it going around for sake of this conversation) 3. On other hand of spectrum, fundamentally soft limits like a prompt "and ask me before you purchase " 2. And then in the middle you have harness enforced limits like "it won't do X with approval"... Those are being sold as hard limits but frequently they have classifiers and heuristics that essentially try to figure out which button on some third party website constitutes a "purchase" and triggers the harness limit. Bottom line - I don't think such limits are as 100% fool proof as they are advertised / interpreted. Very happy to be explained wrong :). > — [NikolaNovak on hackernews](https://news.ycombinator.com/item?id=50298997) > I have to agree. I've been using it for a few days now after coming from GrokBot, then Muse, then Dots. None really clicked for me within the first day. Duet seems different. I haven't quite pegged it, but off the top of my hand: 1. Yes, channels really are useful 2. It does seem to be using Opus 5.5 behind the scenes because, shockingly, it's not screwing everything up like the others usually did 3. Agree that the answers are short and to the point. If you want more info, you just pop open whatever task (separate from channels) it started and you can see what it's doing. Seems like more time in the oven might have paid off here. Also, to be clear, this is purely used as a personal assistant by me. I still use omp+Paseo for all of my day to day work. I find the separation of concerns kind of nice. > — [aliasxneo on hackernews · 2 comments](https://news.ycombinator.com/item?id=50295126) > I started using Grok Bot a few days ago and I have seen zero screwups. I don't know what I'd need a channel for, creating bots/personas seems more natural. Adding credentials is essential, contrary to what the author of the article said. I gave it my library login and it can fetch newspapers for me instead of me clicking through the app every day. When I had to provide a GitLab token, it nicely spawned a box for me to save the credential. - What did not work well - Voice calls. The quick responses are often dumb while the proper model does the thinking, and in the middle of talking to me it would stop to do work or searches. It did not feel realtime. Permission settings. There is a form where you can automatically allow actions you describe in natural language. I tried to allow it to run Claude on my computer or Send certain emails automatically, but the settings achieved nothing. Coding. I wasn't able to make it use Claude, and its own work is worse than me using Opus 5.5 in Claude Code. - What worked well - Planning flights, accessing newspapers from my online library, checking stock in online stores, sending regular summaries of events and weather to plan activities. > — [user43928 on hackernews · 1 comments](https://news.ycombinator.com/item?id=50295795) > Just got access today. I like the channels, but I'm actually finding a few things frustrating compared to Dots: no phone calls (convenient to braindump and have it clean up later) and I don't have shell access to its underlying VM like with Dots. It's also weirdly hard / impossible to spawn Claude Code for Web workers and I can't connect the agent to a desktop and have it spawn jobs there. It doesn't seem all that faster than Dots. It's early and obviously they'll keep iterating. It definitely feels less "make it yours" than Dots and that does feel intentional. > — [dovin on hackernews](https://news.ycombinator.com/item?id=50296823) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50292727) · 99 points · 98 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#claude](https://daily.dev/tags/claude), [#anthropic](https://daily.dev/tags/anthropic) [View this post on daily.dev](https://daily.dev/posts/claude-duet-is-the-first-personal-assistant-type-harness-that-feels-useful-xezaurczu) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Claude Duet is the first personal-assistant-type harness that feels useful","url":"https://daily.dev/posts/claude-duet-is-the-first-personal-assistant-type-harness-that-feels-useful-xezaurczu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/claude-duet-is-the-first-personal-assistant-type-harness-that-feels-useful-xezaurczu"},"datePublished":"2026-10-29T22:01:37.424Z","dateModified":"2026-10-30T02:52:48.710Z","description":"A developer reviews Duet, an Anthropic chatbot assistant, calling it more useful than rivals like Muse, Dot, and NanoClaw. Duet is supposedly powered by Opus...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9160443e746bcb0ae05f086c0b4e9b7b?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9160443e746bcb0ae05f086c0b4e9b7b?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/claude-duet-is-the-first-personal-assistant-type-harness-that-feels-useful-xezaurczu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,claude,anthropic","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Claude Duet is the first personal-assistant-type harness that feels useful"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/claude-duet-is-the-first-personal-assistant-type-harness-that-feels-useful-xezaurczu#faq","mainEntity":[{"@type":"Question","name":"What model powers Anthropic's Duet assistant?","acceptedAnswer":{"@type":"Answer","text":"Duet is supposedly powered by Opus 5.5, according to a hands-on reviewer who noted it feels faster than Opus has felt in other Claude interfaces, suggesting Anthropic applied additional performance tuning specifically for Duet's response speed. Developers evaluating Claude-based agent tools can track model and tooling changes like this on daily.dev."}},{"@type":"Question","name":"How does Duet handle access to GitHub repos and credentials?","acceptedAnswer":{"@type":"Answer","text":"Duet restricts GitHub repo access per channel, so repos added to one channel do not mix with other projects, and it stores no credentials at all, actively discouraging users from providing them. At most it may use a Chrome session on the user's behalf, preferring Claude's existing connector ecosystem instead. Anyone weighing agent tools against credential-sharing risk can follow these security-conscious design choices on daily.dev."}},{"@type":"Question","name":"What problems does Duet currently have in beta?","acceptedAnswer":{"@type":"Answer","text":"Duet has glitches in beta, including threads that run but are not visible in the interface, and delegated repo access that sometimes fails to attach correctly, possibly due to a race condition between agent start and access attachment. Developers deciding whether to adopt a beta agent tool can watch for rough edges like these on daily.dev."}}]} ```