Documentation

Have natural conversations with AI about your ServiceNow environment. Ask questions about tables, records, scripts, and best practices. The assistant understands ServiceNow concepts and can provide contextual guidance based on your connected instance.

• Natural language queries about your instance
• Context-aware responses using your instance metadata
• Support for multiple AI models via OpenRouter (Claude, GPT-4, Gemini, Llama, and more)
• Streaming responses with real-time token and cost tracking
• Conversation history stored locally in your browser

Go beyond chat. The agent can execute multi-step operations on your ServiceNow instance autonomously, with your approval at each step. It plans actions, explains what it will do, and waits for confirmation before proceeding.

• Multi-step task planning and execution
• Approval workflow before any changes are made
• Support for creating, updating, and querying records
• Script generation and deployment
• Automated workflow and business rule creation

Enable Code Mode to let Snolly execute server-side JavaScript directly on your ServiceNow instance via a Scripted REST API. This powers advanced operations like running GlideRecord queries, executing scripts, and automating complex workflows.

• Server-side script execution via Scripted REST API
• Must be explicitly enabled per instance (admin access required)
• All executions are logged and rate-limited
• Supports GlideRecord operations, script includes, and more
• One-click setup with guided configuration wizard

Connect and manage multiple ServiceNow instances from a single interface. Quickly switch between DEV, TEST, and PROD environments, or work across instances simultaneously with Cross-Instance Mode.

• Add unlimited instances (PDI, dev, test, production)
• Quick-switch between instances in the chat interface
• Cross-Instance Mode for operations spanning multiple environments
• Independent credentials and configuration per instance
• Connection testing to verify instance accessibility

Snolly uses a BYOK model. You provide your own API key from OpenRouter (or Anthropic directly), giving you full control over costs, model selection, and usage. We never mark up AI costs.

• Use OpenRouter for access to 100+ AI models with a single key
• Or use an Anthropic API key directly for Claude models
• Pay the AI provider directly at their published rates
• Real-time cost tracking per conversation
• No subscription fees, no hidden costs during beta

Snolly is designed with security as a priority. Your credentials are encrypted, your conversations stay in your browser, and we collect only minimal anonymized analytics.

• AES-256-GCM encryption for ServiceNow credentials
• OAuth 2.0 support with automatic token refresh
• Conversation history stored locally (never sent to our servers)
• Per-user data isolation in browser storage
• GDPR-compliant data handling with export and deletion support
• Content Security Policy (CSP) and security headers enforced