I have very mixed feelings about using Manus.
On one hand, I’m genuinely impressed by its high efficiency and task completion — it can quickly and accurately build product prototypes based on my needs.
On the other hand, when I invited my friends to try it, the system falsely flagged me for “fake referrals” and suspended my account — even though my friends actually subscribed.
I’ve reached out to their support team multiple times, but the issue has never been resolved.
I honestly don’t understand what their support team is doing. No matter how great a product is, poor customer service can easily ruin it.
The connector setup wall is one of the most mundane friction points in AI agent workflows, and this is a clean fix.
What it is: Manus Recommended Connectors is a feature that detects which third-party app connections a task requires and recommends them inline, without sending the user to settings to figure it out themselves.
The problem is familiar to anyone running multi-step tasks in Manus: you describe what you want done, and halfway through the agent hits a dead end because a connector is not enabled. You leave the conversation, find the right integration, authorize it, come back, and re-orient.
The new behaviour short-circuits that. Manus identifies the requirement during the task, surfaces the connector with a prompt, and enables it after you confirm. If the connector needs OAuth or additional authorization, you still complete that yourself no permissions are bypassed.
What makes it different is where the recommendation happens. It is not a setup wizard or an onboarding checklist. It is in-task, contextual, and based on what Manus infers from what you are actually trying to do. You describe the outcome, not the infrastructure.
Key features:
In-conversation connector detection based on task requirements
Recommendation appears inline without leaving the current task
User approval required before any connector is enabled
Works across all Manus plans, including mobile
Supports common connectors including Slack, Gmail, Notion, and Google Drive
Benefits:
No context-switching mid-task to configure settings
No need to know which connector a task requires in advance
Authorization and permission controls remain fully in user hands
Who it's for: Manus users running cross-app workflows, particularly those managing recurring tasks across tools like Notion, Gmail, Slack, or Google Drive.
My read is that the long-term value here is less about the individual connector recommendation and more about what it signals: the agent learning to manage its own setup requirements rather than offloading that to the user. Small feature, non-trivial direction.
I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified.