diff --git a/docs/openapi/schemas.yaml b/docs/openapi/schemas.yaml
index 4b17f06e6..e3d785c87 100644
--- a/docs/openapi/schemas.yaml
+++ b/docs/openapi/schemas.yaml
@@ -12188,12 +12188,23 @@ SuggestionReview:
     tier:
       type: string
       enum: [paid, free]
+    feedbackSubjectId:
+      type: [string, 'null']
+      description: >-
+        SpaceCat-internal id of the sub-item this review is about within the
+        suggestion (e.g. a CWV issue id), used to group per-issue feedback. Null
+        for whole-suggestion reviews.
     previousFix:
       type: object
-      description: Patch snapshot at review time (only when ?include=...,patches).
+      description: AI-generated patch snapshot at review time (only when ?include=...,patches).
     editedFix:
       type: object
       description: ESE-edited patch (only when ?include=...,patches).
+    guidanceMarkdown:
+      type: [string, 'null']
+      description: >-
+        AI-generated issue context (title + description) for the reviewed issue
+        (only when ?include=...,patches). Null when not set.
   required:
     - eventId
     - eventTime
diff --git a/docs/openapi/site-opportunities.yaml b/docs/openapi/site-opportunities.yaml
index 7d88f2572..68c6d0d94 100644
--- a/docs/openapi/site-opportunities.yaml
+++ b/docs/openapi/site-opportunities.yaml
@@ -1264,6 +1264,21 @@ site-opportunity-suggestion-backoffice-reviews:
                 type: string
                 maxLength: 8192
                 description: Optional ESE rationale (markdown). Required on reject by the UI; sanitised + 8 KB cap server-side.
+              guidanceMarkdown:
+                type: string
+                maxLength: 65536
+                description: >-
+                  AI-generated issue context (title + description) for the reviewed issue.
+                  Gives the Learning Agent "what the issue was" alongside the generated
+                  patch (previousFix) and the review. Sanitised + 64 KB cap server-side.
+              feedbackSubjectId:
+                type: string
+                maxLength: 200
+                description: >-
+                  Optional SpaceCat-internal id of the sub-item this review is about
+                  within the suggestion (e.g. a CWV issue id), so the Backoffice can group
+                  per-issue "previous feedback" when issues share one suggestionId.
+                  Independent of the Fix-entity issue id. Not exported to S3.
               rejectionCategory:
                 type: string
                 enum: [product_bug, bad_recommendation, other]
diff --git a/package-lock.json b/package-lock.json
index ce7cb6655..7f8d3533a 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -23,7 +23,7 @@
         "@adobe/spacecat-shared-brand-client": "1.4.0",
         "@adobe/spacecat-shared-cloudflare-client": "1.2.1",
         "@adobe/spacecat-shared-content-client": "1.8.24",
-        "@adobe/spacecat-shared-data-access": "4.8.0",
+        "@adobe/spacecat-shared-data-access": "4.9.0",
         "@adobe/spacecat-shared-drs-client": "1.13.0",
         "@adobe/spacecat-shared-gpt-client": "1.6.23",
         "@adobe/spacecat-shared-http-utils": "1.34.0",
@@ -3811,9 +3811,9 @@
       }
     },
     "node_modules/@adobe/spacecat-shared-data-access": {
-      "version": "4.8.0",
-      "resolved": "https://registry.npmjs.org/@adobe/spacecat-shared-data-access/-/spacecat-shared-data-access-4.8.0.tgz",
-      "integrity": "sha512-FUUIfrnOIG36Jnm+byG91MJPioTZJGLfKxO3zODangn3Dt+ZCr+2DpppqkazcUdxj24N6EFApRSPC2NE0I1e6Q==",
+      "version": "4.9.0",
+      "resolved": "https://registry.npmjs.org/@adobe/spacecat-shared-data-access/-/spacecat-shared-data-access-4.9.0.tgz",
+      "integrity": "sha512-yZPVZAUsMNOCmhGPFUK5822u8UGO4VpF8TTmYoAbhlCAqJiOJmxCBY+2cDunAMS1aS1P2dhjcp3btGcJrGxh1Q==",
       "license": "Apache-2.0",
       "dependencies": {
         "@adobe/fetch": "^4.2.3",
diff --git a/package.json b/package.json
index ce40c57ff..f48d1d724 100644
--- a/package.json
+++ b/package.json
@@ -88,7 +88,7 @@
     "@adobe/spacecat-shared-brand-client": "1.4.0",
     "@adobe/spacecat-shared-cloudflare-client": "1.2.1",
     "@adobe/spacecat-shared-content-client": "1.8.24",
-    "@adobe/spacecat-shared-data-access": "4.8.0",
+    "@adobe/spacecat-shared-data-access": "4.9.0",
     "@adobe/spacecat-shared-drs-client": "1.13.0",
     "@adobe/spacecat-shared-gpt-client": "1.6.23",
     "@adobe/spacecat-shared-http-utils": "1.34.0",
diff --git a/src/controllers/suggestions.js b/src/controllers/suggestions.js
index df30c8faf..78576511d 100644
--- a/src/controllers/suggestions.js
+++ b/src/controllers/suggestions.js
@@ -2872,8 +2872,8 @@ function SuggestionsController(ctx, sqs, env) {
 
     const body = isNonEmptyObject(context.data) ? context.data : {};
     const {
-      eventId, verdict, detailMarkdown, rejectionCategory,
-      stateTransition, previousFix, editedFix,
+      eventId, verdict, detailMarkdown, guidanceMarkdown, rejectionCategory,
+      stateTransition, previousFix, editedFix, feedbackSubjectId,
     } = body;
 
     // FR-09: event_id is MANDATORY and client-supplied (no server fallback).
@@ -2902,6 +2902,24 @@ function SuggestionsController(ctx, sqs, env) {
         return createResponse({ message: 'detail_markdown exceeds the 8 KB limit' }, 413);
       }
     }
+    // guidance_markdown is the AI-generated issue context (title + description).
+    // Larger cap than detail_markdown (64 KB) because issue descriptions +
+    // implementation guidance run long.
+    if (guidanceMarkdown != null) {
+      if (typeof guidanceMarkdown !== 'string') {
+        return badRequest('guidance_markdown must be a string');
+      }
+      if (Buffer.byteLength(guidanceMarkdown, 'utf8') > 65536) {
+        return createResponse({ message: 'guidance_markdown exceeds the 64 KB limit' }, 413);
+      }
+    }
+    // feedback_subject_id is an opaque grouping id (e.g. a CWV issue id) — a short
+    // string, not free text. Bounded to guard against abuse.
+    if (feedbackSubjectId != null) {
+      if (typeof feedbackSubjectId !== 'string' || feedbackSubjectId.length > 200) {
+        return badRequest('feedback_subject_id must be a string of at most 200 characters');
+      }
+    }
 
     const site = await Site.findById(siteId);
     if (!site) {
@@ -2939,10 +2957,13 @@ function SuggestionsController(ctx, sqs, env) {
 
     const {
       detailMarkdown: cleanMarkdown,
+      guidanceMarkdown: cleanGuidance,
       previousFix: cleanPreviousFix,
       editedFix: cleanEditedFix,
       scrubHits,
-    } = redactFeedbackContent({ detailMarkdown, previousFix, editedFix });
+    } = redactFeedbackContent({
+      detailMarkdown, guidanceMarkdown, previousFix, editedFix,
+    });
 
     const scrubbed = Object.entries(scrubHits);
     if (scrubbed.length > 0) {
@@ -2959,6 +2980,8 @@ function SuggestionsController(ctx, sqs, env) {
       signal,
       reviewer_id: reviewerId,
       detail_markdown: cleanMarkdown ?? null,
+      guidance_markdown: cleanGuidance ?? null,
+      feedback_subject_id: feedbackSubjectId ?? null,
       previous_fix: cleanPreviousFix ?? null,
       edited_fix: cleanEditedFix ?? null,
       state_transition: hasText(stateTransition) ? stateTransition : null,
diff --git a/src/support/feedback-redaction.js b/src/support/feedback-redaction.js
index 5ba45a08d..f79e9a399 100644
--- a/src/support/feedback-redaction.js
+++ b/src/support/feedback-redaction.js
@@ -129,12 +129,16 @@ export function scrubDeep(value, hits) {
  *
  * @param {object} input
  * @param {string} [input.detailMarkdown]
+ * @param {string} [input.guidanceMarkdown]
  * @param {*} [input.previousFix]
  * @param {*} [input.editedFix]
- * @returns {{ detailMarkdown: (string|undefined), previousFix: *, editedFix: *,
+ * @returns {{ detailMarkdown: (string|undefined),
+ *   guidanceMarkdown: (string|undefined), previousFix: *, editedFix: *,
  *   scrubHits: Record<string, number> }}
  */
-export function redactFeedbackContent({ detailMarkdown, previousFix, editedFix } = {}) {
+export function redactFeedbackContent({
+  detailMarkdown, guidanceMarkdown, previousFix, editedFix,
+} = {}) {
   const scrubHits = {};
 
   let cleanMarkdown = detailMarkdown;
@@ -142,8 +146,17 @@ export function redactFeedbackContent({ detailMarkdown, previousFix, editedFix }
     cleanMarkdown = scrubString(sanitizeMarkdown(detailMarkdown), scrubHits);
   }
 
+  // guidance_markdown is AI-generated issue context, but we secret-scrub it too
+  // (defence in depth — it can quote customer HTML/config). Sanitised like the
+  // reviewer's rationale.
+  let cleanGuidance = guidanceMarkdown;
+  if (typeof guidanceMarkdown === 'string') {
+    cleanGuidance = scrubString(sanitizeMarkdown(guidanceMarkdown), scrubHits);
+  }
+
   return {
     detailMarkdown: cleanMarkdown,
+    guidanceMarkdown: cleanGuidance,
     previousFix: previousFix === undefined ? undefined : scrubDeep(previousFix, scrubHits),
     editedFix: editedFix === undefined ? undefined : scrubDeep(editedFix, scrubHits),
     scrubHits,
diff --git a/test/controllers/suggestions-reviews.test.js b/test/controllers/suggestions-reviews.test.js
index 3f026d420..7a2ca10a5 100644
--- a/test/controllers/suggestions-reviews.test.js
+++ b/test/controllers/suggestions-reviews.test.js
@@ -249,6 +249,58 @@ describe('Suggestions Controller - backoffice reviews', () => {
     expect(response.status).to.equal(413);
   });
 
+  it('captures guidance_markdown (issue context) alongside the generated patch', async () => {
+    const context = makeContext({
+      postgrest: { onInsert: () => ({ data: { event_id: EVENT_ID, signal: 'negative', tier: 'free' }, error: null }) },
+    });
+    context.data.guidanceMarkdown = '# Slow hero image\n\nLCP element is a 1.2 MB PNG.';
+    const response = await controller.createBackofficeReview(context);
+    expect(response.status).to.equal(201);
+    const inserted = context.dataAccess.services.postgrestClient.capturedInserts[0];
+    expect(inserted.guidance_markdown).to.equal('# Slow hero image\n\nLCP element is a 1.2 MB PNG.');
+    // the generated patch is stored too (the LA maps the review to it)
+    expect(inserted.previous_fix).to.deep.equal({ patch: 'before' });
+  });
+
+  it('rejects oversize guidance_markdown with 413 (64 KB cap)', async () => {
+    const context = makeContext();
+    context.data.guidanceMarkdown = 'x'.repeat(65537);
+    const response = await controller.createBackofficeReview(context);
+    expect(response.status).to.equal(413);
+  });
+
+  it('rejects a non-string guidance_markdown with 400', async () => {
+    const context = makeContext();
+    context.data.guidanceMarkdown = { not: 'a string' };
+    const response = await controller.createBackofficeReview(context);
+    expect(response.status).to.equal(400);
+  });
+
+  it('stores feedback_subject_id (per-issue grouping key) on the row', async () => {
+    const context = makeContext({
+      postgrest: { onInsert: () => ({ data: { event_id: EVENT_ID, signal: 'negative', tier: 'free' }, error: null }) },
+    });
+    context.data.feedbackSubjectId = 'issue-42';
+    const response = await controller.createBackofficeReview(context);
+    expect(response.status).to.equal(201);
+    const inserted = context.dataAccess.services.postgrestClient.capturedInserts[0];
+    expect(inserted.feedback_subject_id).to.equal('issue-42');
+  });
+
+  it('rejects a non-string feedback_subject_id with 400', async () => {
+    const context = makeContext();
+    context.data.feedbackSubjectId = { not: 'a string' };
+    const response = await controller.createBackofficeReview(context);
+    expect(response.status).to.equal(400);
+  });
+
+  it('rejects an over-long feedback_subject_id with 400', async () => {
+    const context = makeContext();
+    context.data.feedbackSubjectId = 'x'.repeat(201);
+    const response = await controller.createBackofficeReview(context);
+    expect(response.status).to.equal(400);
+  });
+
   it('returns 404 when the site is not found', async () => {
     mockDataAccess.Site.findById.resolves(null);
     const response = await controller.createBackofficeReview(makeContext());
diff --git a/test/support/feedback-redaction.test.js b/test/support/feedback-redaction.test.js
index 9f1b566f9..838f0547c 100644
--- a/test/support/feedback-redaction.test.js
+++ b/test/support/feedback-redaction.test.js
@@ -129,12 +129,16 @@ describe('feedback-redaction', () => {
     it('sanitises + scrubs markdown and scrubs both patches, aggregating hits', () => {
       const result = redactFeedbackContent({
         detailMarkdown: '<script>x</script> key AKIAABCDEFGHIJKLMNOP me@adobe.com',
+        guidanceMarkdown: '<style>y</style> issue at foo.corp.adobe.com',
         previousFix: { code: 'Bearer abcdefghijklmnop' },
         editedFix: { code: `ghp_${'z'.repeat(25)}` },
       });
       expect(result.detailMarkdown).to.not.contain('<script>');
       expect(result.detailMarkdown).to.contain('[[REDACTED:aws_access_key]]');
       expect(result.detailMarkdown).to.contain('[[REDACTED:adobe_email]]');
+      // guidance_markdown is sanitised + scrubbed the same way (defence in depth)
+      expect(result.guidanceMarkdown).to.not.contain('<style>');
+      expect(result.guidanceMarkdown).to.contain('[[REDACTED:adobe_internal_host]]');
       expect(result.previousFix.code).to.contain('[[REDACTED:bearer_token]]');
       expect(result.editedFix.code).to.contain('[[REDACTED:github_pat]]');
       expect(result.scrubHits.aws_access_key).to.be.greaterThan(0);