Decagon
Enterprise CX agent platform built around Agent Operating Procedures (AOPs) — natural-language workflow definitions that the AI agent executes across chat, email and voice with selective routing to human agents.
Description
Decagon ships an AI Agent Engine for customer support. The Core AI Agent is the primary contact point across chat, email and voice. AOPs let non-technical CX teams define agent workflows in natural language with enterprise guardrails. A Routing module decides when a request should escalate, and Agent Assist becomes a copilot for the human handler. Evaluation, observability and experimentation tooling sit around the agent for iteration.
Solution
Multi-channel agent: chat / email / voice converge on a single Core AI Agent governed by AOPs (natural-language workflows). The agent consults knowledge and executes multi-step workflows; the Routing module escalates to human handlers when an inquiry should not be handled by the AI, at which point Agent Assist gives the human copilot suggestions. An evaluation engine and Watchtower observability layer monitor behaviour.
Primary use cases
- enterprise CX agent across chat, email and voice on one logic layer
- natural-language workflow authoring via AOPs
- AI-to-human routing with copilot for human agents
- continuous evaluation and iteration on agent behaviour
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.