{"id":243,"date":"2026-01-19T10:32:45","date_gmt":"2026-01-19T13:32:45","guid":{"rendered":"https:\/\/brunopavani.com\/?page_id=243"},"modified":"2026-04-27T07:36:13","modified_gmt":"2026-04-27T10:36:13","slug":"poker-tournament-optimization","status":"publish","type":"page","link":"https:\/\/brunopavani.com\/?page_id=243","title":{"rendered":"Poker Tournament Optimization – Evoke"},"content":{"rendered":"\n

Transforming AI-generated insights into a decision-driven system that reduced manual effort and improved operational speed<\/p>\n\n\n\n

Project Snapshot<\/h3>\n\n\n\n

Company \/ Product:<\/strong> Evoke \u2014 Poker Ops, tournament optimization workflow (iterating an Excel-based tool)<\/p>\n\n\n\n

Timeline:<\/strong> Oct 2025 \u2013 Dec 2025<\/p>\n\n\n\n

Role:<\/strong> Senior UI\/UX Designer<\/p>\n\n\n\n

Stakeholders:<\/strong> Poker Ops + Business stakeholders<\/p>\n\n\n\n

Platform \/ Tools:<\/strong> Excel-based ops tool (iteration-focused approach)<\/p>\n\n\n\n

Scope (What I designed):<\/strong> prioritization aligned to weekly cadence, decision context, safe bulk actions with guardrails, integrated auditability\/traceability<\/p>\n\n\n\n

Outcomes (pilot):<\/strong> overlay -15\u201320%, profit\/tournament +8\u201310%, weekly time -50\u201360%<\/p>\n\n\n\n

Confidentiality:<\/strong> Pilot results are rounded \/ scoped.<\/p>\n\n\n\n

\n\n\n\n

Summary<\/h3>\n\n\n\n

This project focused on improving how tournament optimization decisions were made based on AI-generated insights.<\/p>\n\n\n\n

Before this work, the system produced recommendations through a periodically generated spreadsheet. Users had to manually search for tournaments, interpret the data, and then apply changes in a separate platform. This process was time-consuming, error-prone, and highly dependent on individual interpretation.<\/p>\n\n\n\n

I redesigned this workflow by transforming the spreadsheet-based output into a structured product experience. The new system automatically matched AI insights with real tournaments and allowed users to review, apply, or reject recommendations directly within the platform.<\/p>\n\n\n\n

This shifted the workflow from manual interpretation to fast, decision-driven actions, while also creating a feedback loop to continuously improve the AI model.<\/p>\n\n\n\n

Context<\/h3>\n\n\n\n

The AI system was already generating valuable insights, but the way those insights were consumed created friction.<\/p>\n\n\n\n

Users had to move between tools, manually reconcile data, and decide what actions to take without a clear or structured interface. This introduced delays, inconsistencies, and limited the overall impact of the AI.<\/p>\n\n\n\n

My Role<\/h3>\n\n\n\n

I led the UX\/UI design, focusing on transforming a data-heavy, spreadsheet-based workflow into a usable and scalable product experience.<\/p>\n\n\n\n

A key part of my work was understanding how users interpreted the data, what decisions they needed to make, and where errors or inefficiencies occurred.<\/p>\n\n\n\n

From this, I designed a system that connected insights directly to real entities (tournaments) and supported fast, confident decision-making.<\/p>\n\n\n\n

Problem<\/h3>\n\n\n\n

The core issue was not the quality of the AI insights, but how they were delivered and used.<\/p>\n\n\n\n

Users had to manually:<\/p>\n\n\n\n

    \n
  • find relevant tournaments<\/li>\n\n\n\n
  • interpret AI-generated data<\/li>\n\n\n\n
  • apply changes in a separate system<\/li>\n<\/ul>\n\n\n\n

    This created high cognitive load, increased the risk of errors, and slowed down decision-making.<\/p>\n\n\n\n

    Approach<\/h3>\n\n\n\n

    Instead of improving the spreadsheet, I focused on redesigning the entire interaction model.<\/p>\n\n\n\n

    The goal was to eliminate manual reconciliation and turn insights into direct actions.<\/p>\n\n\n\n

    This involved:<\/p>\n\n\n\n

      \n
    • designing a decision interface instead of a data interface<\/li>\n\n\n\n
    • connecting AI output to real tournament data<\/li>\n\n\n\n
    • structuring insights in a clear and actionable format<\/li>\n<\/ul>\n\n\n\n

      Key Product Improvements<\/h3>\n\n\n\n

      The workflow was transformed from manual interpretation into a structured decision system.<\/h4>\n\n\n\n

      AI-generated insights were automatically matched with real tournaments, removing the need for users to manually search and reconcile data.<\/p>\n\n\n\n

      Users could review each recommendation directly in context and either apply it instantly or reject it, providing a reason for their decision.<\/p>\n\n\n\n

      This created a clear decision flow while also generating structured feedback that could be used to improve the AI model over time.<\/p>\n\n\n\n

      The system reduced context switching, lowered cognitive load, and significantly improved the speed and consistency of decision-making.ile supporting operational confidence.<\/p>\n\n\n\n

      Approved Layout<\/h3>\n\n\n\n

      Final layout designed and iterated by me, reviewed and approved jointly with Poker Ops and Business stakeholders.<\/p>\n\n\n\n