Designing the Response Layer for AI Agents

A system for how AI agents present answers, actions and progress.

Xyne Spaces is a collaborative workspace where teams and AI agents work together across chats, tickets, and other tools. But in developers’ day-to-day workflows, bug reports, suggested fixes, and pull requests often got buried in long chat threads, making it difficult to track progress and review the agent’s work.

To solve this, we designed more structured, interactive responses that made plans easier to review, task progress easier to track, and code changes easier to understand.

Role
Product Designer
Team
Harshvardhan Agarwal and Prakhar Kothari (Designer)
Read the full case study

Some project snapshots

An agent's reply in a Xyne thread: it found the cause of an export bug, opened a pull request, and shows the patch with its additions and removals.
Agent replies in a thread with a table of reviewers, their roles and next sessions, a task table, and a booked review meeting.
The agent says staging is ready and lists the code changes and the staging preview as two items to open, below the booked review.
The agent shares staging walkthrough recordings with the QA notes, as video previews in the thread.