[Discuss] Analyze Cognizant MAKER approach for CCC context granularity, selection, and flagging
>>> [!note] Migrated issue <!-- Drupal.org comment --> <!-- Migrated from issue #3564629. --> Reported by: [kristen pol](https://www.drupal.org/user/8389) >>> <p>[Tracker]<br> <strong>Update Summary: </strong>Analyze Cognizant MAKER approach for CCC context selection<br> <strong>Additional Collaborators: </strong> @kristen pol @kurtfoster<br> <em>Metadata is used by the <a href="https://www.drupalstarforge.ai/" title="AI Tracker">AI Tracker.</a> Docs and additional fields <a href="https://www.drupalstarforge.ai/ai-dashboard/docs" title="AI Issue Tracker Documentation">here</a>.</em><br> [/Tracker]</p> <h3 id="summary-problem-motivation">Problem/Motivation</h3> <p>Kurt shared this:</p> <p><a href="https://www.cognizant.com/us/en/ai-lab/blog/maker">https://www.cognizant.com/us/en/ai-lab/blog/maker</a></p> <p>which talks about solving complex problems with no errors by:</p> <ol> <li>Breaking down problems into tiny pieces</li> <li>Adding voting to determine the solution of the tiny piece to reduce errors</li> <li>Filtering out risky outputs</li> </ol> <p>This can have implications for context, as providing too much context can worsen outcomes compared to providing too little context.</p> <h3 id="summary-proposed-resolution">Proposed resolution</h3> <p>Things to think about for context granularity and selection:</p> <ul> <li>How can more granular and relevant context items be provided based on the AI task?</li> <li>How can voting be used to select the best context items?</li> <li>How can risky context items be flagged and filtered?</li> </ul> <h3 id="summary-remaining-tasks">Target date or deadline</h3> <h3 id="summary-remaining-tasks">Remaining tasks</h3> <ul> <li>Discuss</li> <li>Create follow-up issues as needed</li> </ul> <h3 id="summary-ai-usage">AI usage (if applicable)</h3> <p>[x] AI Assisted Issue<br> This issue was generated with AI assistance, but was reviewed and refined by the creator.</p> <p>[ ] AI Assisted Code<br> This code was mainly generated by a human, with AI autocompleting or parts AI generated, but under full human supervision.</p> <p>[x] AI Generated Code<br> This code was mainly generated by an AI with human guidance, and reviewed, tested, and refined by a human.</p> <p>[ ] Vibe Coded<br> This code was generated by an AI and has only been functionally tested.</p>
issue