{"type":"video","version":"1.0","html":"","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/private/b4c5c30f71d34c2a99e2b3f372fb580b-b56c153213c794b5.gif","duration":2577.03,"title":"Rovo for me - Forge agent for Sprint Health","description":"\n\n### Agent functionality and challenges 2:20\n\n- Sanjay Kulkarni and Ian Buchanan discussed the functionality of their agents and the challenges faced.\n- Ian mentioned issues with getting JSON output from Gemini, which often formats it in markdown code fences, complicating automation processes.\n- Ian expressed surprise at finally getting JSON output, suspecting a switch to LOMs.\n- Sanjay and Ian clarified that solution engineers (S-C's) are not supposed to be hands-on keyboard, which was a point of confusion during a call with Kroger.\n\n### Introduction and project overview 9:09\n\n- Sanjay Kulkarni introduced Ian Buchanan, highlighting his expertise in AI agent building and Forge.\n- Ian shared his background and the context of their project, which involves building a Rovo agent using Forge.\n- The project stemmed from a customer request for an agent to assess sprint health, aiming to assist Scrum Masters in focusing on process improvement rather than technical details.\n- Ian demonstrated the agent's functionality, which includes performing sprint health checks and providing detailed feedback on issues like missing descriptions and estimates.\n\n### Automation and business process improvement 15:32\n\n- Sanjay and Ian discussed potential automation scenarios for the sprint health check agent.\n- Ian suggested running health checks at the start of a sprint or when new stories are added, to ensure readiness and avoid delays.\n- They acknowledged that the customer is still in pilot mode, and the right information needs to be available to the LLM for effective use.\n- Sanjay emphasized the importance of leveraging the agent for business process improvement.\n\n### Sharing resources and community engagement 17:31\n\n- Sanjay and Ian planned to share the agent's instructions and repository with the community.\n- Ian mentioned the need to appeal to admins for installation within Atlassian.\n- Sanjay confirmed the video would be posted on the community platform, ensuring no customer names are mentioned for privacy reasons.\n- They discussed the importance of getting their names and faces out there to promote adoption.\n\n### Challenges with llms and adoption 20:08\n\n- Ian and Sanjay discussed the challenges of using LLMs, particularly the cost implications of deep reasoning and user preferences for expensive models.\n- They noted the low adoption rate of their software, with only 27 out of 300,000 customers using it, highlighting the need for better pitching and demonstration of use cases.\n- Sanjay expressed frustration with the lack of automatic adoption and the need for a clear demonstration of the software's capabilities.\n\n### Rovo adoption plan and data science support 28:06\n\n- Sanjay and Ian discussed the need for a Rovo adoption plan to manage customer engagement and governance requests effectively.\n- Ian suggested expecting large customers to want POC or pilot work before full adoption.\n- Sanjay expressed a desire for data science support to identify secondary dimensions for targeting potential customers, similar to the approach used by the Sackler family in targeting doctors.\n- They discussed the challenges of getting data science support and the potential benefits of a targeted approach.\n\n### Next steps and resource sharing 42:04\n\n- Sanjay and Ian concluded the meeting by discussing the next steps, including sharing the prompt and screenshots for the agent.\n- Ian planned to add the Loom video to the repository, creating a comprehensive resource for users.\n- They agreed to catch up later to continue their collaboration and ensure the successful deployment of the agent."}