>>> [!note] Migrated issue <!-- Drupal.org comment --> <!-- Migrated from issue #3570444. --> Reported by: [kristen pol](https://www.drupal.org/user/8389) >>> <p>[Tracker]<br> <strong>Update Summary: </strong>[One-line status update for stakeholders]<br> <strong>Check-in Date: </strong>MM/DD/YYYY<br> <strong>Blocked by: </strong>[#XXXXXX] (New issues on new lines)<br> <strong>Additional Collaborators: </strong> @username1, @username2<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>Not all context is useful or may have flaws such as factual errors. We need a way to flag context that might not be "performing well" based on feedback when its used by agents, etc.</p> <p>We're not sure yet how such feedback would come in. One example could be a thumbs-up/down on a chatbot result which is noted in: <span class="drupalorg-gitlab-issue-link project-issue-status-info project-issue-status-8"><a href="https://www.drupal.org/project/ai_initiative/issues/3544476" title="Status: Needs review">#3544476: [META] Chatbot UX evolution ideas</a></span></p> <p>If we get this type of feedback, we'll need to be able to associate it with the right context and provide annotations with the feedback.</p> <h3 id="summary-proposed-resolution">Proposed resolution</h3> <p>Discuss the idea and create follow-up issues as needed</p> <h3 id="summary-remaining-tasks">Target date or deadline</h3> <p>February 2026</p> <h3 id="summary-remaining-tasks">Remaining tasks</h3> <ul> <li>Discuss</li> <li>Decide if this is a priority for soon or should be added to the roadmap for later (probably the latter because we need the upstream feedback mechanisms)</li> <li>Create follow-up issues as needed</li> </ul>