From understanding work to getting work moved forward
Vibe devices could capture conversations and turn them into AI summaries, Vibe AI could access all summaries like a memory bank and understand work context. But understanding what happened in meetings wasn't the same as actually helping users move their work forward.
As Vibe prepared to introduce agentic capabilities to Vibe Dot, the team wanted to extend its AI value from summarizing conversations to executing work across connected apps like Slack, Notion, Google Drive...etc.
While the business direction and a general agent flow across Vibe devices were already defined, what remained unclear was what users would actually delegate, how they would discover these capabilities, and how the interaction should work.
My challenge: Turn a broad AI agent capability into a meaningful product experience that users could understand, discover, and confidently use.
01 — What work should users delegate to AI agent?
Finding an opportunity beyond AI summaries
I explored AI market trends in 2026, Vibe user feedback, and Vibe's advantaged domain in capturing and understanding conversations in the personal work or collaboration context.
While AI summaries were becoming increasingly common, fully autonomous agents still faced limitations like reliability, trust, and privacy in 2026.
I spotted an opportunity between the two: helping people move collaborative work forward after conversations instead of expecting AI to take over the rest in entire workflows.
For example, a salesperson could delegate customer follow-ups after calls and a product manager could update a PRD and notify teams after a meeting.
From technical AI skills to meaningful AI Jobs
Initially, I explored a wide range of AI skills and integrations. But the possibilities quickly became difficult to define what Vibe users needed and communicate with stakeholders. Most agent capabilities didn't have contexts to explain what they would actually help people accomplish.
Mental model: Users knew what outcome they want. But they wouldn’t know which AI skill could get them there.
I shifted toward AI Jobs—recognizable outcomes users could delegate, rather than individual skills they needed to understand.
One AI Job could combine several underlying capabilities, relevant meeting context, and app integrations to complete a meaningful task.
I developed a concept diagram and concrete scenarios to make that relationship understandable. This helped stakeholders move beyond discussing abstract capabilities toward identifying feasible jobs and defining the initial scope.
The turning point: AI Jobs gave the team a shared product concept to discuss what users could actually delegate.
02 — How should users discover and delegate AI Jobs?
With a clearer product concept, the next challenge was making AI Jobs relevant and usable within Vibe's existing experience.
I focused on two connected moments: helping users recognize a job worth delegating, then making it straightforward to review and authorize.
Make the next action recognizable through context
My early exploration included repositioning Vibe AI's homepage around agent capabilities, but the proposed change was too broad for the initial scope.
I returned to where users already encountered their work: meeting summaries and Ask AI.
Simply listing available jobs wouldn't necessarily help users imagine why they needed them.
I proposed surfacing AI Jobs close to the meeting information that made those actions meaningful.
In summaries, suggested jobs appeared alongside related discussions. In Ask AI, each suggestion carried essential context to help users recognize its relevance.
I also reduced the initial suggestions to three and developed criteria for when an AI Job should appear, rather than filling the experience with every possible action.
The intention was to help users recognize a useful next step without first having to discover and understand a new catalog of AI capabilities.
Make approval simpler than another conversation
Once users chose a job, they still needed to understand what the agent intended to execute.
Many conversational AI experiences rely on repeated exchanges to refine instructions and confirm actions. But Vibe's initial executable jobs were relatively simple, such as sending messages and updating documents.
Working with the development lead, I explored whether those actions really needed a conversational review process.
I designed a single review card that brought the proposed content, destination, and approval into one place.
My first design separated details into expandable items, but that weakened the visual hierarchy and obscured what users needed to review.
I refined the card to emphasize the content requiring attention while keeping recipients and destinations compact, allowing users to review, edit, and approve the proposed work without unnecessary back-and-forth.
The resulting interaction connected the two moments: discover a relevant job through context, then review and authorize its execution.
Outcome — From an ambiguous capability to a concrete direction
The final proposal brought together outcome-based AI Jobs, contextual discovery, a focused review-and-approval experience, and supporting cross-device flows.
The direction gained stakeholder buy-in and was handed off for continued development following an organizational reduction. Permissions, credit costs, and some implementation details remained unresolved during my involvement.
My contribution was helping the team move from asking what an AI agent could do to defining what people could meaningfully delegate—and how that experience should work.
You can also find me on 💁
- 👨🏻💻 Resume
- 🎨 Behance
- 📱 +886 909607406
- 📧 a870588@gmail.com