Whiteboard AI agent
The design
I led the design of an AI-powered teammate that transforms whiteboarding into a dynamic, connected part of the Atlassian System of Work. By integrating real-time context and automating workflows, it helps teams turn ideas into action—fast. Built under tight timelines, it was showcased at the company summit Atlassian TEAM 25 to thousands, marking a major step in Atlassian’s competitive AI strategy.
The agent will search for relevant content across the organisation
Continue your train of thought by clicking on the ‘next step’ suggestions
We wanted to create more efficiency in the brainstorming space but providing a prompt box, but also an agent who can take context from across the ecosystem to suggest and action work. We had a few weeks to create a working demo for TEAM25 and a future vision for agentified experience within whiteboards. We worked across a total of 7 teams across the company to align and establish new platform patterns and
components and spearheaded the introduction of new logic and rules for AI, such as auto-generating content without previews or confirmation modals and inline next step suggestions so users can continue their thinking without needing to prompt. Due to the introduction of agents being a new industry trend, the work had many iterations as we gradually gained alignment across core teams within the company.
Select content on the whiteboard and ‘reference’ it in the new prompt
The process
-
I started by doing an audit on the current AI experiences across the company and connecting with key stakeholders from teams we knew we needed to get alignment on. As we were setting the standard for auto-populating agent actions, inline suggestions, and the concept of ‘referencing’ content within the org. I setup brainstorming sessions and joined other teams spikes to get involved in the space.
-
I setup regular rituals with the key stakeholders and began to visualise concepts. These concepts would go to weekly reviews and continue to be iterated as each team’s expectations and requirements were aligned on. There was a total of 21 iterations done on the agent model alone, from team requirements to marketing requirements to scope adjustments. We had core principles for the feature that we weren’t going to budge on e.g it must auto populate, there cannot be any confirmation buttons - so we used those principles to advocate against other teams requirements - even designing for those teams to show how our design can suit their needs as well. All in the aim to get alignment and quick - as we had a strict deadline to meet and not a lot of time.
-
The engineers were equally under the pump due to the deadlines, so I took the initiative to setup a UX debt backlog. We would blitz the feature every day and send it out to be dogfooded internally multiple times before we reached the deadline.
During this time, I also worked alongside content designers to set the prompting logic up for success by mapping adjectives and core words to content that could be created across Atlassian - as our prompting system can work across multiple tools (Image below)I also worked closely with the marketing team to co-create the slides for the TEAM25 presentation, where we would show the future state version of our demo.
The impact
The work got shared in the CEO keynote presentation at the company summit Atlassian TEAM 25 in front of thousands. This resulted in a positive reception from our users and higher investment in our team.
