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.
Manus can now turn a completed task into an approved update to your Project's instructions, files, or skills.
What it is: A self-updating capability for Manus Projects that reviews conversation output and proposes context changes, with approval required before anything takes effect.
The workflow is straightforward: work in a Project as usual, ask Manus to review the conversation when something useful was produced, review the proposed updates, and approve what you want carried forward. Future tasks start with that updated context already in place.
What makes it different: The key architectural choice here is approval-gating. Manus proposes but does not apply. That is the right call for team workspaces where one bad context update could affect multiple people and future tasks. The control surface stays with the user.
Key features:
Conversation-driven instruction updates
Project file refresh from updated source material or examples
Skill creation and refinement from repeatable workflows
Per-update approval before any context change takes effect
Works across launch planning, research, PRD writing, feedback analysis, and onboarding use cases
Benefits:
Removes manual maintenance from recurring AI workflows
Keeps team Projects aligned without a dedicated context manager
Reusable patterns get captured without anyone having to write documentation
Context quality compounds over time rather than degrading
Who it's for: PMs, researchers, and team leads managing Manus Projects across multiple contributors who need shared context to stay accurate without constant manual editing.
The interesting design question here is what the ceiling is on approval fatigue. If Manus proposes good updates consistently, teams will build a habit of reviewing them. If the proposals are noisy, the feature will get ignored. Worth watching how the community uses it in practice.
I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified.