# Cue (Manus)

Feedback Bench, personal agents, built 2026-10-26, window 2026-08-31 to 2026-10-25. Web page: https://feedbackbench.com/#/agent/cue

| Measure | Value |
|---|---|
| Rank | 10 of 12 (rank range 9–10) |
| Feedback Score | 42.3 (95% interval 41.1–43.4) |
| Popularity | 0.203 (share of voice 0.57%) |
| Customer love | 0.483 (95% interval 0.474–0.492) |
| Place | Popularity 9th of 12 × Customer love 9th of 12 |
| Top quadrant | no |
| Users | 778 |
| Posts counted | 865 |
| Posts that judge the agent | 306 |
| Criteria ranking high / low | 0 / 0 of 53 |

## The brief

Written by large language models from this page's numbers and the posts it quotes, then checked: every number in the text is in the build. Interpretation, not measurement.

For many users, the trouble with Cue by Manus starts before they can use it. Posts describe invite codes that fail, phone checks that break, and an app that stalls on its opening screen. Getting tasks done and working on its own draw more praise than complaints, but users mention them less often than for other agents. Setup makes up 15.0% of what its users rate, against 8.3% for other agents. Chat ranks 6th of 9, and some posts call it slower than Grokbot. Cue ranks 10th of 12 overall.

### Why people choose it


### Why people leave

- **Many users cannot get past sign-up** ([Getting it set up](https://feedbackbench.com/criteria/access.md)). 1.8×: 15% of what users rate, 1.8× the rate for other agents. Ranks 7th of 9 on “Getting it set up”. Posts describe invite codes that return errors, phone verification that fails even after an email login, and an app that freezes or closes at the entrance. One user says they lost their session after an update and could not link it back to their Manus account.
  Evidence:
  - 2026-10-18, App Store (App Store): “i have an invitation code, but after entering it, it shows an error, and i can't get in at all. it's really terrible.” [source](https://apps.apple.com/tw/app/cue-by-manus/id6808613358)
  - 2026-10-15, Play Store (Play Store): “it doesn't work, it doesn't let me authenticate my number, if i already logged in with my email account, why can't i continue with the activation, it's a shame.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- **Chat is slow, and the app crashes on open** ([Chatting with it](https://feedbackbench.com/criteria/ask.md)). 6th: of 9 on “Chatting with it”. 18% of what users rate. Users say its bots take a long time on simple tasks, and some say Grokbot does the same work faster. Others never reach a chat because the app crashes or sticks on its opening screen. One user says group chats do not show which bot answered or when it has finished.
  Evidence:
  - 2026-10-07, Play Store (Play Store): “at the moment terrible, very slow bots, they take even hours to do trivial tasks. useless.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
  - 2026-10-13, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “cue by manus is way slower and dumber than grokbot! i gave them the same tasks and cue is just taking ages to do that exact thing that grokbots did so fast.” [source](https://twitter.com/3059389886/status/2110038907014525118)

### What would move its score

Rule: For each area where an agent's customer love is below the category norm: the Feedback Score and rank it would have if that one area were at the norm (0.5) and everything else stayed the same, computed with the same formula as the ranking. An area's pull follows its weight, so an area many users of the category rate moves the score more than one they rarely mention.

| Area at the category norm | Feedback Score | Change | Position |
|---|---|---|---|
| Getting tasks done | 43.0 | +0.8 | 9th of 12 |
| Talking to the agent | 42.8 | +0.5 | 10th of 12 |
| Getting access and set up | 42.6 | +0.3 | 10th of 12 |
| Running on its own | 42.5 | +0.2 | 10th of 12 |
| Staying in control | 42.5 | +0.2 | 10th of 12 |
| Dealing with the vendor | 42.3 | +0.1 | 10th of 12 |
| Paying for the agent | 42.3 | +0.0 | 10th of 12 |
| Trusting it with data and safety | 42.3 | +0.0 | 10th of 12 |

No single area would move Cue far. Bringing getting tasks done up to the category norm would help most, lifting the Feedback Score from 42.3 to 43.0 and its rank from 10th to 9th. Bringing chat to the norm would add 0.5 and setup 0.3. Neither would change its rank.

### Six weeks

No users posted about Cue until the week of 28 September, when 434 did and it ranked 8th. Users fell each week after, to 86. Share of voice went from 1% to 0%. Rank reached 7th, then fell to 10th in the last week.

## Top requests

What users ask to add or change, most asked first. 47 user-weeks ask for something. Requests do not change the Feedback Score. Rule: A separate pass by a large language model reads every counted post and extracts what the user asks the agent or its vendor to add or change, with the criteria it maps to and a short normalised wording; it does not touch the labels or the Feedback Score. A large language model groups the wordings within each criterion (the first criterion the request maps to) into themes, and a second pass merges themes that ask for the same change under different criteria; a merged theme sits under the criterion most of its requests map to, and code counts it once. A theme counts distinct user-weeks that ask for it, per agent; across agents, one user-week per agent. Themes asked in fewer than 2 user-weeks, and requests that share no theme, are not shown. Examples: up to 3 posts per theme from different users, without slurs: whole posts of 60 to 450 characters with at least 8 words beyond handles and links, posts of at most 280 characters first, then the newest.

| Rank | Request | Criterion | User-weeks | Posts |
|---|---|---|---|---|
| 1 | Invite code to get access | [Country availability, waitlists and staged rollout](https://feedbackbench.com/criteria/access.availability.md) | 8 | 8 |
| 2 | Free tier or free access | [Free tier, trial or required plan to start](https://feedbackbench.com/criteria/billing.entry_plan.md) | 4 | 5 |
| 3 | Live view of agent's computer | [Seeing what the agent is doing and has done](https://feedbackbench.com/criteria/control.visibility.md) | 3 | 3 |
| 4 | Agent control of the phone | [Access to the user's own phone or computer](https://feedbackbench.com/criteria/connect.local_device.md) | 2 | 2 |
| 5 | Dedicated phone number for the agent | [Reaching the agent through messaging apps](https://feedbackbench.com/criteria/ask.channel.md) | 2 | 2 |
| 6 | More frequent feature updates | [Got better or worse over time, and update cadence](https://feedbackbench.com/criteria/vendor.updates.md) | 2 | 2 |
| 7 | Phone calls with the agent | [Speaking with the agent by voice or call](https://feedbackbench.com/criteria/ask.voice.md) | 2 | 2 |
| 8 | Single unified subscription across products | [Plan contents, bundles and usage meters unclear](https://feedbackbench.com/criteria/billing.plan_clarity.md) | 2 | 2 |

### 1. Invite code to get access

- Cue, 2026-10-11, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “anyone can share an invite code for cue by manus please? how was it anyway? thanks” [source](https://twitter.com/1851900159585849346/status/2109189605866234248)
- Cue, 2026-10-11, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “could someone please give me the invitation code for manus cue? 🙇” [source](https://twitter.com/1638814145104711682/status/2109076584695214433)
- Cue, 2026-10-10, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “looking for an invitation code for manus cue, is there a kind person?” [source](https://twitter.com/1557423223523774464/status/2108913617718665443)

### 2. Free tier or free access

- Cue, 2026-10-03, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “@thdxr i think you should make a free version of grok bot and manus cue” [source](https://twitter.com/2063217927055392768/status/2106416657736646978)
- Cue, 2026-09-30, Play Store (Play Store): “in the process of use, please consider that the subscription price is expensive.. please allow the free plan.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Cue, 2026-09-30, Play Store (Play Store): “i used manus from 15 august to 27august and honest review is that i enjoy it, this is my excellent experience with ai, now i have to use cue for free. can you gave it to me for free? kindly reply me if yes or not. i am waiting for your response 🙂” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### 3. Live view of agent's computer

- Cue, 2026-10-23, Play Store (Play Store): “overall good app but 1 major issue a person doesn't see clear in browser task what a agent can and wear ge clicked after fix this issue i edit my review and give full star” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### 4. Agent control of the phone

- Cue, 2026-10-09, Play Store (Play Store): “its work, its control pc but don't control phone. why that reason, if i said like( go my phone youtube and play song..) it cannot go but in pc work done properly” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Cue, 2026-09-30, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “thanks! but i am not concerned about answering phone call or making a phone call. i think manus cue agent is heavily promoting this feature. but is phone call really a thing nowadays? i don't remember when was the last time i have an important conversation over the phone. i think my point it let the bot operate a phone just like how it operates a computer.” [source](https://twitter.com/1976596760857559040/status/2105150740960604615)

### 5. Dedicated phone number for the agent

- Cue, 2026-10-19, Play Store (Play Store): “it is excellent for organizing your work or emails, drive documents, i would like it to be available to use the phone number and for them to integrate animated widgets for each of the assistants.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Cue, 2026-10-11, Play Store (Play Store): “more than wonderful, but we need more control over the computer and we need to purchase phone numbers.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### 6. More frequent feature updates

- Cue, 2026-10-11, Play Store (Play Store): “the app is very good and performs its purpose excellently, but i hope that future updates will add more features and improve responsiveness. good luck!” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### 7. Phone calls with the agent

- Cue, 2026-10-24, Play Store (Play Store): “just needs proactiveness and voice call features like openai dots and i'd rather use this any day. it has its own phone, email, computer, basically everything we would possibly need.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Cue, 2026-10-07, Play Store (Play Store): “cool, but make all functions available for ukraine and improve the ai and functionality, and add calls. also, please create a free plan with reasonably normal limits.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### 8. Single unified subscription across products

- Cue, 2026-09-29, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “@alanalyzing please offer a combined manus/cue/computer credits and resources pool plan. 🥲” [source](https://twitter.com/16124492/status/2104730772011954537)
- Cue, 2026-09-30, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “i tried using manus cue, but there are additional charges for everything... the regular monthly fee for cue is planned, and in addition, it's 1,700 yen for phone use in japan, and if you need computing, it's from 6,600 yen. it's not bad, but instead of just charging for this, a bundled package fee for coding and chat would be easier to use. [link]” [source](https://twitter.com/2656999148/status/2105393418952462789)

## Ranks highest on

No criterion where it sits clearly in the top half.

## Ranks lowest on

No criterion where it sits clearly in the bottom half.

Position on a criterion: its place among the agents with at least 30 rated user-weeks there, ordered by customer love. It ranks high when both its position and its 95% interval put it in the top half, low when both put it in the bottom half; neither otherwise, or when fewer than 4 agents qualify.

## All 53 criteria

Criterion love: 0.5 is the category norm. n: rated user-weeks.

### Paying for the agent: 5th of 8 (customer love 0.498, n 31)

Customer love for price and value is within the category norm. Complaints outnumber praise. One post says it used up credits quickly while making images. Some users ask for a free tier or free access.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Subscription price versus value received](https://feedbackbench.com/criteria/billing.price_level.md) | Too few posts | 0.481 | 0.468–0.494 | 16 | 3 | 13 |
| [Free tier, trial or required plan to start](https://feedbackbench.com/criteria/billing.entry_plan.md) | Too few posts | 0.506 | 0.498–0.515 | 7 | 6 | 1 |
| [Usage allowance size, exhaustion and reset wait](https://feedbackbench.com/criteria/billing.usage_cap.md) | Too few posts | 0.503 | 0.496–0.515 | 3 | 1 | 2 |
| [Plan contents, bundles and usage meters unclear](https://feedbackbench.com/criteria/billing.plan_clarity.md) | Too few posts | 0.497 | 0.494–0.500 | 3 | 0 | 3 |
| [Agent spends usage on overhead and costly choices](https://feedbackbench.com/criteria/billing.token_efficiency.md) | Too few posts | 0.498 | 0.495–0.500 | 2 | 0 | 2 |
| [Buying, upgrading, cancelling and refunding go wrong](https://feedbackbench.com/criteria/billing.purchase_flow.md) | Too few posts | 0.499 | 0.498–0.500 | 1 | 0 | 1 |

Most recent posts:

- Praise, 2026-10-23, Play Store (Play Store): “very good, it fulfills its function and is really free just like its other family of agents, i like the free stuff.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Praise, 2026-10-03, Play Store (Play Store): “this is best for me like those praopels who make their business team to grow their business without hiring employees this is like grokbot but in my opinion this is better because grokbot is not free but this is free and better work to han grokbot.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Praise, 2026-10-07, Play Store (Play Store): “this is free for now, and i love it. it's the best grok bot alternative. the agent has their own email, and you can call them. and create a group chat” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-09, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “i just activated manus's cue and haven't started using it yet. by the way, it can help answer calls, but i just saw it costs $9.99. it's more expensive than what was advertised before. #manus #cue [link]” [source](https://twitter.com/349966606/status/2108568835552952519)
- Complaint, 2026-09-29, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “manus’s cue is ridiculously stingy. plus users are still limited to 4 file uploads a day — worse than other apps’ free tiers. [link]” [source](https://twitter.com/2091099299262373888/status/2104869196001608142)
- Complaint, 2026-09-29, Play Store (Play Store): “everything need to pay from cue app token itself then the phone number cant use youre own so does the cloud computer need to pay i think the most cheapest setting 1 months will be 50+ usd to all services” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### Getting access and set up: 7th of 9 (customer love 0.470, n 41)

Setup is below the category norm. Invite codes, phone verification and an opening screen that will not load keep users out. Users talk about setup 1.8 times as often as for other agents. Invite codes are the most common request, at 8 user-weeks.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Account creation, sign-in and identity checks fail](https://feedbackbench.com/criteria/access.sign_in.md) | Too few posts | 0.477 | 0.468–0.485 | 23 | 0 | 23 |
| [Country availability, waitlists and staged rollout](https://feedbackbench.com/criteria/access.availability.md) | Too few posts | 0.491 | 0.484–0.497 | 7 | 0 | 7 |
| [Effort needed to set up and train the agent](https://feedbackbench.com/criteria/access.setup.md) | Too few posts | 0.506 | 0.497–0.515 | 7 | 5 | 2 |
| [Apps offered for phone, tablet and desktop](https://feedbackbench.com/criteria/access.platform.md) | Too few posts | 0.494 | 0.488–0.498 | 6 | 0 | 6 |

Most recent posts:

- Praise, 2026-10-14, App Store (App Store): “for anyone, like me, who is not so technical, i must say how easy it is to set up cue. it’s very intuitive and quick to do. i am now excited to test it but i already know it will be awesome!” [source](https://apps.apple.com/gb/app/cue-by-manus/id6808613358)
- Praise, 2026-10-19, App Store (App Store): “i have used manus heavily for the past 2 years. cue is the perfect evolution. simple to set up and easy to use this makes agent creation something anyone can do. i have already built commercial models from it in 2 weeks” [source](https://apps.apple.com/gb/app/cue-by-manus/id6808613358)
- Complaint, 2026-10-20, Play Store (Play Store): “i tried a lot to use it but i couldn't. i don't know if some integration code was given to me, so i had a very bad experience.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-18, App Store (App Store): “i have an invitation code, but after entering it, it shows an error, and i can't get in at all. it's really terrible.” [source](https://apps.apple.com/tw/app/cue-by-manus/id6808613358)
- Complaint, 2026-10-15, App Store (App Store): “when i try to sign with gmail i still need phone number and when i write it they say : phone service invaluable ???? why” [source](https://apps.apple.com/ma/app/cue-by-manus/id6808613358)

### Connecting accounts, sites and devices: Too few posts (customer love 0.503, n 14)

Users mention connecting apps and devices less often than for other agents, and there are too few posts to rank. One post says it cannot see events in Google Calendar.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Which services have a connector or integration](https://feedbackbench.com/criteria/connect.coverage.md) | Too few posts | 0.502 | 0.492–0.511 | 8 | 6 | 2 |
| [Access to the user's own phone or computer](https://feedbackbench.com/criteria/connect.local_device.md) | Too few posts | 0.498 | 0.491–0.504 | 4 | 2 | 2 |
| [Linking accounts and staying logged in](https://feedbackbench.com/criteria/connect.account_link.md) | Too few posts | 0.499 | 0.497–0.500 | 1 | 0 | 1 |
| [Moving files between agent, apps and user](https://feedbackbench.com/criteria/connect.file_transfer.md) | Too few posts | 0.498 | 0.495–0.500 | 1 | 0 | 1 |
| [Websites block the agent with captchas or IP bans](https://feedbackbench.com/criteria/connect.site_blocking.md) | Too few posts | 0.500 | 0.500–0.500 | 0 | 0 | 0 |

Most recent posts:

- Praise, 2026-10-16, Play Store (Play Store): “i am starting to use them and it is striking that it can connect to meta.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Praise, 2026-10-07, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “@connortalksai also you forgot about cue by manus it has some nice features like its own phone number and ofc its own computer and 100+ connectors @cueagents” [source](https://twitter.com/2099455241963925506/status/2107889865320731045)
- Praise, 2026-09-29, Play Store (Play Store): “unable to download muse, first try cue. i found that it can connect to oura, saving the trouble of dragging data to gpt for analysis! the experience is currently excellent!” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-09, Play Store (Play Store): “its work, its control pc but don't control phone. why that reason, if i said like( go my phone youtube and play song..) it cannot go but in pc work done properly” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-09-28, Play Store (Play Store): “the drive is connected but it doesn't recognize it, i haven't tested it anymore after that.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-13, Play Store (Play Store): “he does not have access to google's calendar, at least he nor the existence of an event , more color to choose from for agents” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### Talking to the agent: 6th of 9 (customer love 0.465, n 48)

Chat is below the category norm. Users describe slow replies and crashes on opening. One post says group chats do not show which bot answered or whether it has finished.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [App screens, layout, rendering, localisation and stability](https://feedbackbench.com/criteria/ask.app_client.md) | Too few posts | 0.485 | 0.475–0.496 | 21 | 2 | 19 |
| [Response and task completion speed](https://feedbackbench.com/criteria/ask.speed.md) | Too few posts | 0.487 | 0.473–0.501 | 16 | 4 | 12 |
| [Speaking with the agent by voice or call](https://feedbackbench.com/criteria/ask.voice.md) | Too few posts | 0.501 | 0.494–0.509 | 4 | 2 | 2 |
| [Avatar, personality and tone of replies](https://feedbackbench.com/criteria/ask.persona.md) | Too few posts | 0.491 | 0.473–0.504 | 4 | 2 | 2 |
| [Threads, chats and parallel tasks organisation](https://feedbackbench.com/criteria/ask.conversation.md) | Too few posts | 0.496 | 0.491–0.500 | 3 | 0 | 3 |
| [Reaching the agent through messaging apps](https://feedbackbench.com/criteria/ask.channel.md) | Too few posts | 0.502 | 0.500–0.506 | 2 | 2 | 0 |

Most recent posts:

- Praise, 2026-10-08, Play Store (Play Store): “what a wonderful and cute app, the ai sent me a :3, that was very cute, besides making wonderful images and not speaking in a generic way like the other 98 ais that i deleted.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Praise, 2026-10-02, Play Store (Play Store): “loving to use this app. its very minimal design and its user-friendly gesture are making me more attracted to using it and helping me to do my regular tasks. i like its best feature: creating a group of multiple bots and assigning them roles” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Praise, 2026-09-30, Play Store (Play Store): “the little cue i encountered is really too cute, can provide humorous emotional value, will help share and simplify content, very satisfied 😂😂” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-09-30, Play Store (Play Store): “the ai group chat does not make clear the response of each model or bot and does not indicate if it has finished responding” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-24, 六大 AI Agent 邊隻啱你？香港人揀 Agent 懶人包 - 附自己 host OpenClaw / Hermes 教學（廣東話） (YouTube): “the analysis is in place. i have used both grok bot and manus cue, but manus cue is slower than grok bot. so in the end, i still use grok bot. for analysis, documentation, or doing ad copy, grok bot's token consumption is acceptable, but for graphic requests, like asking a bot to help you with design, it's not good because it consumes tokens very quickly. similarly, manus cue allows you to pay for…” [source](https://www.youtube.com/watch?v=IBWvTPs_xFw&lc=UgzoKWllrYJ2kT9y3pd4AaABAg)

### Getting tasks done: 6th of 11 (customer love 0.475, n 45)

Users rate getting tasks done about half as often as for other agents. Praise outnumbers complaints, and customer love is within the category norm. Complaints describe slow work and results that miss what the user asked for.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Wrong facts, hallucinations and careless mistakes](https://feedbackbench.com/criteria/act.accuracy.md) | Too few posts | 0.503 | 0.491–0.515 | 10 | 4 | 6 |
| [Contacting other people and businesses for you](https://feedbackbench.com/criteria/act.outreach.md) | Too few posts | 0.489 | 0.470–0.504 | 6 | 3 | 3 |
| [Stops short, or hands the task back](https://feedbackbench.com/criteria/act.stops_short.md) | Too few posts | 0.496 | 0.487–0.504 | 6 | 2 | 4 |
| [Writing code and building apps or websites](https://feedbackbench.com/criteria/act.build.md) | Too few posts | 0.506 | 0.501–0.511 | 5 | 5 | 0 |
| [Creating writing, images, video and social posts](https://feedbackbench.com/criteria/act.content.md) | Too few posts | 0.493 | 0.476–0.504 | 5 | 3 | 2 |
| [Email triage, cleanup and drafting replies](https://feedbackbench.com/criteria/act.email.md) | Too few posts | 0.504 | 0.500–0.508 | 3 | 3 | 0 |
| [Booking appointments, reservations, travel and tickets](https://feedbackbench.com/criteria/act.reservations.md) | Too few posts | 0.503 | 0.500–0.507 | 3 | 3 | 0 |
| [Web research, monitoring and summarising information](https://feedbackbench.com/criteria/act.research.md) | Too few posts | 0.486 | 0.452–0.504 | 3 | 2 | 1 |
| [Forms, applications, claims and life admin paperwork](https://feedbackbench.com/criteria/act.admin.md) | Too few posts | 0.502 | 0.500–0.505 | 2 | 2 | 0 |
| [Budgets, transactions, bills and investments](https://feedbackbench.com/criteria/act.finance.md) | Too few posts | 0.502 | 0.500–0.506 | 2 | 2 | 0 |
| [Operating a browser or desktop by clicking](https://feedbackbench.com/criteria/act.computer_use.md) | Too few posts | 0.496 | 0.489–0.500 | 2 | 0 | 2 |
| [Calendar entries, conflicts and schedule changes](https://feedbackbench.com/criteria/act.calendar.md) | Too few posts | 0.501 | 0.500–0.504 | 1 | 1 | 0 |
| [Buying products, orders and purchase judgment](https://feedbackbench.com/criteria/act.shopping.md) | Too few posts | 0.502 | 0.500–0.505 | 1 | 1 | 0 |
| [Says it did something it did not do](https://feedbackbench.com/criteria/act.false_reports.md) | Too few posts | 0.499 | 0.498–0.500 | 1 | 0 | 1 |
| [Following instructions, rules and corrections](https://feedbackbench.com/criteria/act.instructions.md) | Too few posts | 0.502 | 0.500–0.508 | 1 | 1 | 0 |

Most recent posts:

- Praise, 2026-10-18, Play Store (Play Store): “it finds and corrects errors by itself very well, resulting in a perfect output. thank you, manus team, you did a great job!” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Praise, 2026-10-14, Play Store (Play Store): “that's insane level ai agent i gave a work to his and he complete it without errors” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Praise, 2026-10-07, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “you can make calls from an american phone number to a japanese number with manus cue! it's hard to convey in words, but it's amazing that a real call comes from the ai agent.” [source](https://twitter.com/822653421341802496/status/2107784768784089578)
- Complaint, 2026-10-21, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “and that’s the only most intuitive and amazing feature that seems only grokbot can achieve! i tried codex or manus cue, not fully working🙂↕️ [link]” [source](https://twitter.com/1511010620384378893/status/2112953370575249426)
- Complaint, 2026-10-10, App Store (App Store): “i just started using it, the old version was very useful and i spent 2800 for the monthly fee to use it. later, after switching to the new version, i couldn't complete the previous tasks for two or three hours. it's been going back and forth. is there any progress?” [source](https://apps.apple.com/hk/app/cue-by-manus/id6808613358)
- Complaint, 2026-10-08, Play Store (Play Store): “the design aesthetics are very good, and the experience is quite nice, but i don't know why the agent can't make videos for me, and it doesn't work with remotion or similar tools.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### Running on its own: Too few posts (customer love 0.488, n 25)

Working on its own draws more praise than complaints, but there are too few posts to rank. Some users ask for a live view of the agent's computer.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Where the agent runs: its own computer and always-on running](https://feedbackbench.com/criteria/auto.cloud_env.md) | Too few posts | 0.497 | 0.485–0.508 | 13 | 8 | 5 |
| [Multiple agents, teams and delegation between them](https://feedbackbench.com/criteria/auto.multi_agent.md) | Too few posts | 0.508 | 0.502–0.514 | 7 | 7 | 0 |
| [Scheduled recurring tasks and daily briefings run](https://feedbackbench.com/criteria/auto.routines.md) | Too few posts | 0.481 | 0.458–0.500 | 3 | 0 | 3 |
| [Remembering the user and context across sessions](https://feedbackbench.com/criteria/auto.memory.md) | Too few posts | 0.499 | 0.493–0.503 | 2 | 1 | 1 |
| [Unprompted suggestions, insights and check-ins](https://feedbackbench.com/criteria/auto.proactive.md) | Too few posts | 0.500 | 0.500–0.500 | 0 | 0 | 0 |
| [Reminders and notifications reach the user correctly](https://feedbackbench.com/criteria/auto.reminders.md) | Too few posts | 0.500 | 0.500–0.500 | 0 | 0 | 0 |

Most recent posts:

- Complaint, 2026-10-16, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “i used dots from chatgpt and felt it was very slow and often unresponsive, so i tried another one. the first one i tried was cue by manus, but i found that i couldn't set the routine i wanted; cue said it was not supported. so i tried grok bot, and it is truly amazing. it really changes the whole world, fast, accurate, and can check security for real. i wish i had known this earlier.” [source](https://twitter.com/1700717747473416192/status/2111208261831832047)
- Complaint, 2026-10-16, X search: Cue by Manus, Manus Cue, Manus's Cue, cue.im (X): “i used dots from chatgpt and felt it was very slow and often unresponsive, so i tried other options. the first one i tried was cue by manus, but i found that i couldn't set the routine i wanted; cue said it wasn't supported. so i tried grok @bot, and it's amazing! it really changes the whole world, fast, accurate, and can actually check security. i wish i had known this sooner.” [source](https://twitter.com/1700717747473416192/status/2111208370585915696)
- Complaint, 2026-09-29, Play Store (Play Store): “great ai agent. i used it for an hour, currently i would change 2 things - 1. i have a bug about the time zones, so it can't perform a automatic task for me. 2 - the text i send should be on the left and the agent messages should be on the right (especially right now when in every social media platform like whatsapp and insta, we see our text on the left and other peoples massages on the right, pl…” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### Staying in control: Too few posts (customer love 0.482, n 11)

Few posts cover control, too few to rank. Complaints outnumber praise, and customer love is within the category norm.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Seeing what the agent is doing and has done](https://feedbackbench.com/criteria/control.visibility.md) | Too few posts | 0.489 | 0.478–0.496 | 6 | 0 | 6 |
| [Configuring behaviour, skills and portability](https://feedbackbench.com/criteria/control.customize.md) | Too few posts | 0.492 | 0.480–0.501 | 4 | 1 | 3 |
| [Asks before acting: too little or too much](https://feedbackbench.com/criteria/control.approval.md) | Too few posts | 0.502 | 0.500–0.505 | 1 | 1 | 0 |
| [Which AI model runs, how good it is, and choosing it](https://feedbackbench.com/criteria/control.model.md) | Too few posts | 0.498 | 0.495–0.500 | 1 | 0 | 1 |

Most recent posts:

- Praise, 2026-10-07, Play Store (Play Store): “this is the king of all kings in matters of ai agents... it searches for jobs on my behalf, customise my resume/cv and cover letter to meet the job requirements. it opens my email and saves everything as a draft pending my approval and submission. then it gives me reports and next steps to take. it also save logs to eliminate duplication. no spray & pray! no guess work!” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-23, Play Store (Play Store): “overall good app but 1 major issue a person doesn't see clear in browser task what a agent can and wear ge clicked after fix this issue i edit my review and give full star” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-10, Play Store (Play Store): “i gthere is no information deletion or agent deletion function.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-09, Play Store (Play Store): “put an option for me to delete a task with an agent. i want to delete a conversation and it doesn't delete because it is the default agent.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)

### Trusting it with data and safety: Too few posts (customer love 0.499, n 1)

Privacy and safety barely come up: 0.4% of what users rate, against 4.3% for other agents. The area has one complaint and no praise.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Vulnerabilities, prompt injection and cross-user leaks](https://feedbackbench.com/criteria/trust.security.md) | Too few posts | 0.499 | 0.496–0.500 | 1 | 0 | 1 |
| [How the vendor collects, keeps and uses data](https://feedbackbench.com/criteria/trust.data_use.md) | Too few posts | 0.500 | 0.500–0.500 | 0 | 0 | 0 |
| [Permission scope requested and isolation between agents](https://feedbackbench.com/criteria/trust.access_scope.md) | Too few posts | 0.500 | 0.500–0.500 | 0 | 0 | 0 |
| [Refuses legitimate requests because of guardrails](https://feedbackbench.com/criteria/trust.refusals.md) | Too few posts | 0.500 | 0.500–0.500 | 0 | 0 | 0 |

### Dealing with the vendor: Too few posts (customer love 0.492, n 20)

Updates and support draw mostly complaints. Posts describe a session lost after an update and a help request that got no reply. Some users ask for more frequent feature updates.

| Criterion | Reading | Customer love | 95% interval | n | Praise | Complaint |
|---|---|---|---|---|---|---|
| [Got better or worse over time, and update cadence](https://feedbackbench.com/criteria/vendor.updates.md) | Too few posts | 0.497 | 0.487–0.509 | 10 | 3 | 7 |
| [Support responses and account bans or lockouts](https://feedbackbench.com/criteria/vendor.support.md) | Too few posts | 0.495 | 0.490–0.499 | 5 | 0 | 5 |
| [Outages, errors and agent going unresponsive](https://feedbackbench.com/criteria/vendor.uptime.md) | Too few posts | 0.495 | 0.491–0.499 | 5 | 0 | 5 |

Most recent posts:

- Praise, 2026-10-14, Play Store (Play Store): “wow...i recommend. manus has made a good leap forward. high-performing application...nothing to say.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-09-29, Play Store (Play Store): “since i installed this app, it has barely opened the login screen. most of the time, it just freezes on the loading screen, even after i updated the app to the latest version.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-09-29, Play Store (Play Store): “the user experience is extremely poor, the main phone feature was launched without being ready! i have given feedback several times and no one has addressed it!” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)
- Complaint, 2026-10-19, Play Store (Play Store): “the things are good things, but after the update, it is restricted domestically.” [source](https://play.google.com/store/apps/details?id=ai.manus.agents)