Social Media Care Agent
Moderates the bank's social channels and community and moves account help to secure channels.
- Industry
- Banking
- Department
- Customer
- Team
- Customer Lifecycle
- Kind
- Assistant
- Approver
- Head of Retail Banking
- Code
- CUS-11
It moderates the bank's social channels and community forum against the house rules, hiding posts that expose account or card details, removing scam links and impersonator accounts, and answering general questions from the knowledge base. It moves anyone who needs account help into a secure channel and never discusses a customer's account in public.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the CRM: the posts, reports and the authors' customer records where linked..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Prepares the draft, match, recommendation or reply, with its sources.
- 05Asks a person
Hands the work to Head of Retail Banking with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the CRM: it applies the moderation actions and logs complaints and private hand-offs. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The social and community guidelines: house rules, the impersonation and scam-account playbook, what may and may not be said in public, the secure hand-off to private channels, complaint recognition on social, and crisis escalation.
Reads from
the CRM: the posts, reports and the authors' customer records where linked.
Acts in
the CRM: it applies the moderation actions and logs complaints and private hand-offs.
Hands back
A list with one entry per post, each with post_id, action (keep, hide, remove, reply or move_private), reason, reply (or null), is_complaint (true or false) and escalation (or null).
Asks a person when
It proposes a ban, a post reports a threat, self-harm or harassment, a post is a public complaint likely to escalate or reach the media, or a reply would speak about rates, a product launch or a security incident.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Answer posts unanswered after (hours) | 4 | Questions left this long get an answer. |
| Hide after reports | 3 | A post with this many reports is hidden pending review. |
| Hide posts showing account or card details | On | When on, such posts are hidden at once and the customer told privately. |
| Report impersonator accounts | On | When on, accounts posing as the bank are reported to the platform. |
| May ban members | Off | When off, bans go to the approver. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- When on is true, hide any post showing a card number, account number or balance and tell the customer privately.
- Never discuss a customer's account in public; invite them to a secure channel.
- Remove scam links, and when on is true, report accounts posing as the bank and warn followers.
- A public complaint is acknowledged and logged as a complaint.
- Hide a post with 3 reports; answer questions unanswered after 4 hours.
- When off is false, propose bans to the Head of Retail Banking.
See the Social Media Care Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.