SocialHub.AI
Platform · AI Frontier

Callable by agents. Governed by you.

A Loyalty Concierge is a conversational assistant that answers a member about their own points, tier, and rewards from real program data, and does not invent a balance.

When a member wants to redeem, Loyalty Concierge only proposes a confirmation card. Points are redeemed after the member confirms. The assistant does not redeem them on its own.

The AI Frontier extension layer turns the platform from something people use into a governed capability surface that agents can call, external AI ecosystems can reuse, and your teams can trust — built on governed MCP and signed Skills, with SoCode, SoTag and SoClaw on top.

What is an AI Loyalty Concierge?

A Loyalty Concierge is a conversational assistant that answers a member about their own points, tier, and rewards from real program data, and does not invent a balance.

When a member wants to redeem, Loyalty Concierge only proposes a confirmation card. Points are redeemed after the member confirms. The assistant does not redeem them on its own.

Can AI identify the best rewards strategy for a member? Loyalty Concierge answers from that member's real points, tier, coupons, and redeemable rewards. It does not invent a balance or a reward. Connect your own assistant is the same governed surface: a read-only, member-bound key for an assistant such as Claude or Cursor.

FAQ

What is an AI Loyalty Concierge?

A Loyalty Concierge is a conversational assistant that answers a member about their own points, tier, and rewards from real program data, and does not invent a balance. When a member wants to redeem, Loyalty Concierge only proposes a confirmation card. Points are redeemed after the member confirms. The assistant does not redeem them on its own.

Is Loyalty Concierge available?

Yes. Loyalty Concierge is Available. Connect your own assistant is Available too.

Can Loyalty Concierge spend points by itself?

When a member wants to redeem, Loyalty Concierge only proposes a confirmation card. Points are redeemed after the member confirms. The assistant does not redeem them on its own.

Can AI identify the best rewards strategy for me?

An AI Loyalty Concierge answers from that member's real points, tier, coupons, and redeemable rewards. It does not invent a balance or a reward. It can show rewards that member can afford. It does not invent a balance to make a reward look available.

Can a member connect Claude or Cursor to a loyalty program?

Yes. Connect your own assistant is Available. A member creates a read-only key tied to their own account and can connect an assistant such as Claude or Cursor. The key reads only that member's loyalty data.

Can an assistant limit answers to that member's tier?

It answers from that member's own record, including their tier. A member-bound key cannot reach anyone else's data.

Is an AI Loyalty Concierge the same as a hotel concierge?

No. This Loyalty Concierge answers a member about their own loyalty program — points, tier, and rewards — from real program data. It is not a hotel or travel concierge.

Operate it from where you already work.

The same governed agent — same MCP server, same scopes, same audit trail — wherever you work: in your editor, in Slack, or running on its own. Not a chatbot bolted onto a dashboard; the platform itself, callable.

SoCode

Available
Claude Code · Claude Desktop · Cursor

A downloadable skill plus the governed MCP server, so an agent can operate the platform and answer questions about your data in plain language — without leaving the editor.

  • ›Ask about your data in plain language, in-editor
  • ›Run governed operations without leaving Claude Code or Cursor
  • ›Backed by the same MCP server and scopes as everything else

SoTag

Available
Slack

The same governed agent in the channel where your team already coordinates: ask for a metric or run an approved operation — the answer, and the audit trail, live right next to the decision.

  • ›Pull a metric or run an approved action inside Slack
  • ›The answer and its audit trail sit next to the decision
  • ›No dashboard-hopping just to get a number

SoClaw

Early Access
Autonomous · win-back

The autonomous one. It doesn't wait to be asked — it works your high-value, at-risk customers one by one, picks a personal way to win each back or holds off, and proves the real lift against a control group it never touches. Win-back is on by default once it's set up for your workspace; you can pause it or turn it off at any time. Spend caps and an instant pause stay in place.

  • ›Works high-value, at-risk customers one at a time
  • ›Chooses a personal win-back or a deliberate hold
  • ›Proves real lift vs an untouched control — capped, pausable
Run in Agent

Or run it inside the agent your enterprise already uses.

Because it's a standard, governed MCP server, the platform doesn't only run in our agents — it plugs into the enterprise assistants your teams already have. Same tenant key, same scopes, same audit trail.

Claude Desktop

Available
Anthropic

Connect the governed MCP server straight into Claude Desktop and ask about your members, campaigns and metrics — or run an approved operation — in an ordinary chat.

How it works →

Microsoft Copilot

Available
Microsoft 365 · Teams

A declarative agent for Microsoft 365 Copilot: your team queries members, campaigns and metrics inside the Copilot they already use — with the same tenant key, scopes and audit trail as every other call.

How it works →

SAP Joule

Planned
SAP

Bring the same governed tools into SAP's Joule assistant, so operations and merchandising teams reach loyalty and campaign data without leaving SAP.

Learn more →
Facing your members

Now the AI faces your members, too.

The same governed surface doesn't only serve your team — it serves your members. A concierge lives in their portal, and they can plug in their own assistant. Grounded in real data, read-only, and only ever a member's own account.

Loyalty Concierge

Available
In your member portal

A conversational assistant inside your member portal. Members ask, in plain language, about their own points, tier progress, coupons, redeemable rewards and how the program works — answered from their real data, never fabricated. It's read-only, on by default, and stays in your brand's voice.

  • ›Answers from real data — the AI never invents a balance or a reward
  • ›Read-only: it explains status, it never spends points or changes anything
  • ›On by default, brand-controlled, cost-capped

Connect your own assistant

Available
The member's AI · via MCP

A member mints a read-only, member-bound key from their portal and plugs their own AI assistant (Claude, Cursor…) into the same governed MCP server — pinned to their account and unable to reach anyone else's data. Your loyalty program shows up inside the AI they already use.

  • ›Member-bound key: reads only that member's own loyalty data
  • ›Same governed MCP surface — read-only, scoped, audited
  • ›Your program, inside the assistant the customer already lives in

What it's built on: MCP and Skills.

Two building blocks make the platform callable without giving up control — the interface an agent talks through, and the capabilities it's allowed to invoke.

MCP
The governed interface

A standard, authenticated way for any agent — Claude, Copilot, M365 — to call the platform's tools. Every call carries a tenant key, is authorized per tool, metered against a budget, and written to the audit trail.

Skills
The reusable capabilities

Packaged business tasks with their conditions, validation and boundaries built in — the units an agent actually invokes. Each one is cryptographically signed and integrity-checked before it runs, and sandboxed while it does.

What do those skills actually contain? 31 built-in expert plays across the consumer lifecycle, each one a governed, versioned SOP — Explore the Enterprise Skill Library →

Under it all

One certified semantic layer.

MCP and Skills are only as trustworthy as the numbers underneath them. Both read through one governed semantic layer — every business metric defined and certified once, computed one way. So the figure an agent returns is the figure on your dashboard, and the AI never invents a number.

One certified semantic layer

Defined once · computed one way

read through by

MCP

same number

Skills

same number

Dashboards

same number

Safe by design

Autonomy you can govern.

AI-generated commands are validated against a static command tree before they run; third-party Skills are signed, integrity-checked and sandboxed; and every MCP call is authenticated by a tenant key, authorized per tool, metered against a budget, and audited. Metric numbers come from the semantic layer — the AI never invents figures.

Tenant isolation · least privilege · full auditability · SOC 2 Type II · CCPA/CPRA-ready · Azure-native

Concierge support

Search help, open a ticket, or hand off to a person.

Loyalty Concierge can search the knowledge base. It can also offer to open a support ticket or hand the conversation to a person, and that happens after the member confirms.

Reward redemption

The assistant proposes. The member confirms.

When a member wants to redeem a reward, Loyalty Concierge only proposes a confirmation card. Points are redeemed after the member confirms. The assistant does not redeem them on its own.

Brand controls

On or off, a rollout percentage, and capped cost.

For each brand, an admin can turn Loyalty Concierge on or off and set a rollout percentage. Cost is capped by rate limits and a daily usage budget.

Make the platform callable by your agents.

400M+
50+
12+