Goal
Fetch recent mentions, replies, and comments directed at the account to monitor and respond to community interactions.
Which Agents Use This
- engagement — Monitor for new mentions since last run, identify which need responses
- moderator — Check for complaints or urgent issues requiring human escalation
- custom — Any agent handling community engagement
Hard Rules
- MUST fetch mentions directed at the account (not general brand mentions)
- SHOULD calculate sentiment and priority for triage
- SHOULD flag has_response to avoid duplicate replies
- Priority levels help agents decide what to respond to first
Steps
1. Validate input
- Verify account_id exists and belongs to workspace
- Validate since timestamp if provided
- Apply limit (max 100)
2. Fetch mentions from platform
- Query platform API for mentions/replies/@mentions
- Filter by since timestamp
- Apply filter (all, unanswered, flagged)
3. Analyze mentions
- Determine sentiment (positive, neutral, negative)
- Calculate priority (normal, high, urgent) based on:
- Sentiment (complaints = higher priority)
- Keywords (refund, broken, help = urgent)
- Author influence/follower count
- Check has_response
4. Return mentions array
- Include mention metadata, author, content, timestamps
- Include analysis (sentiment, priority, has_response)
Output
{
"success": true,
"count": 12,
"mentions": [
{
"mention_id": "uuid",
"author": "@username",
"content": "Hey @brand, how do I reset my password?",
"platform": "twitter",
"created_at": "2026-02-20T09:15:00Z",
"sentiment": "neutral",
"has_response": false,
"priority": "high"
}
]
}
Failure Handling
- If account_id not found: return error "Account not found"
- If platform API fails: return cached mentions with warning
- If no mentions found: return empty array with count: 0
Example Usage
Scenario: Engagement agent checking for new mentions
{
"account_id": "uuid",
"since": "2026-02-20T08:00:00Z",
"filter": "unanswered"
}
Result: Receive list of unanswered mentions since 8am for response prioritization
1---2name: bolta-get-mentions3description: Fetch recent mentions, replies, and comments directed at the account for community engagement monitoring4---56## Goal7Fetch recent mentions, replies, and comments directed at the account to monitor and respond to community interactions.89## Which Agents Use This10- **engagement** — Monitor for new mentions since last run, identify which need responses11- **moderator** — Check for complaints or urgent issues requiring human escalation12- **custom** — Any agent handling community engagement1314## Hard Rules151. MUST fetch mentions directed at the account (not general brand mentions)162. SHOULD calculate sentiment and priority for triage173. SHOULD flag has_response to avoid duplicate replies184. Priority levels help agents decide what to respond to first1920## Steps2122### 1. Validate input23- Verify account_id exists and belongs to workspace24- Validate since timestamp if provided25- Apply limit (max 100)2627### 2. Fetch mentions from platform28- Query platform API for mentions/replies/@mentions29- Filter by since timestamp30- Apply filter (all, unanswered, flagged)3132### 3. Analyze mentions33- Determine sentiment (positive, neutral, negative)34- Calculate priority (normal, high, urgent) based on:35 - Sentiment (complaints = higher priority)36 - Keywords (refund, broken, help = urgent)37 - Author influence/follower count38- Check has_response3940### 4. Return mentions array41- Include mention metadata, author, content, timestamps42- Include analysis (sentiment, priority, has_response)4344## Output45```json46{47 "success": true,48 "count": 12,49 "mentions": [50 {51 "mention_id": "uuid",52 "author": "@username",53 "content": "Hey @brand, how do I reset my password?",54 "platform": "twitter",55 "created_at": "2026-02-20T09:15:00Z",56 "sentiment": "neutral",57 "has_response": false,58 "priority": "high"59 }60 ]61}62```6364## Failure Handling65- If account_id not found: return error "Account not found"66- If platform API fails: return cached mentions with warning67- If no mentions found: return empty array with count: 06869## Example Usage7071### Scenario: Engagement agent checking for new mentions72```json73{74 "account_id": "uuid",75 "since": "2026-02-20T08:00:00Z",76 "filter": "unanswered"77}78```79**Result:** Receive list of unanswered mentions since 8am for response prioritization