Challenge

As work scaled, too much time was being lost to fragmented communication, manual coordination, and repetitive setup tasks. Critical information was scattered across Slack threads, emails, calendar events, Jira planning, design files, and engineering workflows. The result was constant context switching, slower decisions, and unnecessary operational drag.

Several workflows stood out as especially inefficient:

• Jira epic and ticket creation required repeated manual setup
• daily Slack, email, and calendar synthesis took hours
• translating scattered conversations into actionable workstreams was slow
• moving from low-fidelity ideas to more developed wireframes involved too much repetition
• design-to-prototype workflows across Figma and GitLab were slower than they needed to be

What should have taken minutes often took hours. What should have taken hours often stretched into days. In some cases, concept-to-prototype cycles that could have moved within days were taking weeks.

This created an opportunity not only to improve efficiency, but to rethink how design and product teams could work through more intelligent, connected, and experimental systems.

My role

As part of an experimental tiger team, I helped explore how agentic AI could improve the way teams operate, create, and move work forward. My role focused on identifying high-friction operational moments, designing workflow orchestration across tools, and shaping how AI could be applied in a way that was useful, scalable, and grounded in real team needs.

I took initiate for:

• identifying the most time-consuming coordination and execution gaps
• designing the workflow architecture and orchestration logic
• connecting tools, signals, and outputs into a more unified system
• applying design judgment and systems thinking so outputs stayed clear, useful, and high quality
• testing new ways of working and sharing learnings to help others experiment and adopt similar approaches

This was not just about using AI tools. It was about designing a better operating model for modern product and design work, then helping others see how these methods could support their own workflows.

How I approached it

I approached this work as both an operational design problem and a cultural opportunity.

The first step was identifying where people were losing time, where coordination was breaking down, and which repetitive tasks were creating the most drag. From there, I designed orchestration flows that could reduce manual effort while still preserving quality, clarity, and human judgment.

Because this work was experimental, a major part of the value came from testing, learning, and sharing what worked. I used the tiger team environment not just to build solutions, but to demonstrate new possibilities for design and product teams. By making the workflows tangible and showing the before-and-after impact, I helped inspire others to experiment, adopt, and think more expansively about how AI could support their own practice.

Core components

• MCP servers for tool coordination and workflow context
• Cursor and Ask for synthesis, planning, and task generation
• Jira for epic and ticket creation
• Slack, email, calendar events, and relevant news for daily summaries and priority signals
• Figma plugins for faster low- to high-fidelity wireframing and design system outputs
• GitLab for faster prototyping and tighter design-engineering collaboration
• Momentum app for tracking and reviewing outcomes

What the system enabled

• Automated Jira epics and tickets from meeting inputs and discussions
• Summarized daily communication and surfaced what mattered most
• Turned fragmented conversations into structured action
• Accelerated wireframe creation and reusable design system patterns
• Shortened the path from design concept to prototype

More broadly, it showed how agentic AI could support both team operations and design execution when applied with clear intent and workflow structure.

view agentic ai outcomes 

Impact

• 30% increase in operational efficiency through AI-driven workflow orchestration
• 1–2 hours to 10–15 minutes: Jira epic and ticket setup: daily synthesis of Slack, email, calendar activity, and news
• Days to hours: low-fidelity to higher-fidelity design workflow acceleration
• Weeks to days: faster concept-to-prototype cycles through tighter Figma and GitLab integration

Reflection

This work showed that agentic AI is most powerful when it improves how teams think, coordinate, and execute. Beyond automation itself, the value came from reducing friction, creating better operating conditions, and helping others see how experimentation could lead to practical, scalable change.