Skip to main content
AI built into the platform

Your studio, augmented

Studio Manager handles the conversational ops; four specialist agents handle the cross-cutting work; the MCP server lets external AI clients read your venue's data with the same scope enforcement.
188+
Studio Manager tools

Read / write / analytics / vision / partner / client / public / onboarding / migration surfaces

4
Specialist agents

Operations · Marketing · Financial · Retention

8 + 6
MCP resources + tools

Approved MCP clients can read venue-scoped data via /api/mcp

Studio Manager

The single AI surface across every admin page. Ask in plain language — “What’s our bounce rate?”, “How much did we spend on SMS?”, “Schedule maintenance for room 2”, “Find duplicate clients”. Studio Manager has typed access to 188+ tools across the platform and respects every permission gate the venue admin uses by hand.

  • Per-venue capability awareness — only suggests features the venue can actually use
  • Permission and confirmation gates remain authoritative for write-capable tools
  • Write tools carry reversal data or an explicit irreversible marker
  • Tool calls record audit evidence, timing and outcome

Specialist agents

Operations

Front-of-house huddle generator, staff scheduling, equipment + maintenance, room conflicts, walk-in queue.

Marketing

Campaign planning, sequence drafting, segment building, churn-risk scoring, re-engagement triggers.

Financial

Revenue recognition, deferred-revenue waterfall, accountant exports, reconciliation, tax-period close.

Retention

Lifecycle stage classification, win-back triggers, lifetime-value cohorts, partner-network referrals.

The seeded baseline is registry-driven. Availability varies with venue capabilities, permissions and platform rollout.

MCP server

Booking Bible exposes itself as a Model Context Protocol server at POST /api/mcp so approved MCP clients can read venue data with API-key authentication and scope enforcement. 8 resources + 6 tools today; writes intentionally out of scope (read-only v1).

MCP integration guide

AI safety

Input screening, per-tool row caps, scope checks, permission gates and audit evidence reduce the AI blast radius. They do not make a model infallible, so consequential writes remain bounded by confirmation and reversal policy. Tool calls land in ai_tool_audit_log for operational review.

  • Suspicious tool input is screened and sensitive audit fields are reduced
  • Read tools have bounded result sizes, with narrower caps where appropriate
  • MCP resources and tools require the matching API scope
  • System behavior contracts prohibit cross-tenant access and hidden side effects

See the operating model

Open the guided product preview for an illustrative Studio Manager workflow, then scope live access for your venue.