Book a demo
Home
Platform
Platform Browser Agent How It Works Supported Platforms AI & Analytics Security & Governance
Solutions
Solutions Procurement Finance & operations Sales & CRM IT & admin Business process automation
Industries
Industries Ports & logistics Manufacturing Banking & financial services Healthcare Government & public sector Energy & utilities E-commerce Industrial surveillance Border surveillance Supply chain
Agents
Agent Library SAP agents Salesforce agents Odoo agents Zoho agents Custom website agents Procurement agents Finance agents Operations agents IT & admin agents
Customers
Resources
Documentation Guides FAQ Why Choose Us
About Book a demo
Documentation

Technical reference

Every engagement ships with connection diagrams, endpoint specifications, validation rules and full flow documents. This is what that documentation covers.

What is documented

Delivered with every engagement

Detailed technical documentation is produced as part of delivery and handed over with the build. Contact us for access to the current set for your environment.

Connection diagrams

How agents reach each connected system, and through which interface.

Endpoint specifications

The REST, OData and Service Layer endpoints each integration uses.

Validation rules

The checks applied before any transaction is committed to a system of record.

Flow documents

End-to-end process flows for every automated workflow in scope.

Security architecture

Isolation model, authorisation rules and deployment gateways.

Audit and logging

What is written to the audit trail, where it lives and how to query it.

Architecture

The stack the documentation describes

  1. Presentation

    Side panel UI with chat interface, live state updates and conversation history; an agent launcher for new tasks, sessions and templates; an options page for model settings and configuration.

  2. Extension infrastructure

    A background service worker acts as the central orchestrator, handling message routing, task management, tab management, event handling and connection management.

  3. Agent runtime

    The core multi-agent system. An executor orchestrates agents and manages the task lifecycle; a planner agent understands the task, creates the plan, self-corrects and breaks down steps; a navigator agent executes it against live pages.

  4. Model providers

    Multi-model support across Anthropic Claude, OpenAI, Google Gemini, Ollama local models and any OpenAI-compatible endpoint.

  5. Browser APIs

    Tabs, DOM, cookies, storage and navigation, the browser capabilities the agent uses to act on a page the way a person would.

  6. Target applications

    SAP Fiori, ERP systems, websites, internal portals and any other URL-based application your teams already work in.

Shared services

Cross-cutting services: storage and settings sync, action caching, LLM observability and tracing, usage analytics, resource monitoring and RPA integration for hybrid automation.

Book a session

Need the technical detail?

Tell us what your architecture or security team needs and we will send the relevant documentation.