Danvas
Danvas
DashboardSupportWelcome

👤 USER DOCS

User Guides

Getting Started

Getting StartedDashboard & OnboardingApp Settings

Tutorials

Tutorial: Setting Up Shift Tasks & ClosersTutorial: Managing Incidents in the InboxTutorial: Tracking Compliance & Sync StatusTutorial: Operational Workflows with the AI AssistantTutorial: Building & Deploying Custom Checklists

Daily Operations (Staff)

Shift Workspace & TasksService Day SetupDaily Line-UpStaff Service Day ReportsForms

Communication & Chat

Messages & AnnouncementsUnified Operations InboxAI Assistant

Manager & Admin Guides

Daily Line-Up SetupStaff SchedulingManaging LocationsNPS and Guest FeedbackCouponsContacts and Guest HistoryManager CloseoutsDaily Line-Up & ComplianceAnalyticsIncident ReportingWhistleblower Concerns & FeedbackAdmin Tools

⚙️ DEVELOPER DOCS

Getting Started

Getting StartedDevelopmentDeployment Guide

Architecture

Architecture OverviewExplanation: AI Integration & Tenant SecurityExplanation: Dynamic Forms Engine DesignExplanation: Compliance Ledger DesignExplanation: Live Sync & Data FreshnessData FlowArchitecture Decision Records

Core Domain

Core DomainDatabase ReferenceLocations DomainAuth & RBACScheduling DomainReports DomainIncidents DomainUnified Operations InboxLive Sync Data FreshnessToast Sync PipelineNotifications DomainCoupons and Guest NPSAudit Log & Compliance ArchitectureDesign Audit FindingsAI Chat IntegrationAnalytics & Tips Integration

Frontend

Frontend ArchitectureFormsLoading SkeletonsComponentsPWA & Offline ShellScreenshots

API Reference

API Reference

Endpoints

POS Sales APIOptimization Data APISchedule Shifts APIEmployee Export APIReports APIIncidents APIAI Chat APIPush Notifications APIWebhooks APICron API

Contributing

ContributingCode Examples

Security

Security & Compliance

Release Notes

What's New

AI Assistant

Ask plain-English questions about your operational and location data

Danvas features an AI Assistant powered by DeepSeek V4.1 Flash through the Vercel AI Gateway and the Vercel AI SDK. The assistant acts as an on-demand operational copilot, helping managers and team members navigate standard operating procedures, formulate policies, and prepare drafted content for reviews and announcements.

How to Chat with the AI

The AI Assistant is accessible directly across desktop and mobile:

  1. Desktop: Press Cmd+K (or Ctrl+K) to open the Command Menu and select Ask Danvas, or navigate directly to /ask.
  2. Mobile: Tap More in the bottom navigation dock and select Ask.
  3. Type your question or drafting request in the chat composer. For example:
    • "What is our opening procedure checklist for the front-of-house?"
    • "Draft a pre-shift announcement for the dinner team about tonight's private dining event."
    • "Help me structure a manager handover note for the closing manager."

Operational Modes & Capabilities

The assistant has three modes:

  1. Guidance (general): Answers operational, SOP, compliance, and application help questions concisely and directly, grounded in verified company documents. Guidance is not connected to company policies, schedules, or live restaurant data.
  2. Draft (actions): Prepares workflow drafts (shift handoffs, team announcements, general drafts). Draft mode is non-mutating and performs no operational writes, so every operational workflow is draft-first — the assistant produces structured, editable drafts that managers review, refine, and hand off to team messages. Retirement records (closeout, incident) use a dedicated form instead.
  3. Data (data): Answers questions from live restaurant data. Available to admins and managers with a location scope, across a bounded range of at most 31 completed service days; the range defaults to the last completed day, not today. The mode is hidden when the workspace has no data tools configured.

Switching modes in a conversation that already has messages starts a new conversation and preserves the current one.

Safety & Privacy: The assistant enforces strict tenant and role boundaries. It minimizes staff and guest PII in responses and will not fabricate policy when authoritative context is unavailable. An admin with no explicit location assignments has team-wide location scope; admins with explicit assignments, managers, and members remain limited to their authorized locations.

Rate Limits

To maintain service stability, chat queries are rate-limited to 20 requests per minute per user.

Related

Team Messages

Shift Reports

Technical: AI Integration

Unified Operations Inbox

How to use the consolidated Master-Detail operations inbox and messaging feed

Daily Line-Up Setup

Use a daypart panel inside the Service Day Workspace

On this page

How to Chat with the AIOperational Modes & CapabilitiesRate LimitsRelated