Decagon Product Foundations
Start learning now
Fill out the form to get started on your AI CX Specialist Certification
Start learning now
Fill out the password to get started on your AI CX Architect Certification (customers only).
Building your AOPs
Top takeaways from this module:
- Entry conditions tell agent when to select an AOP
- Tools tell an agent to take action and connect to real systems
- Nodes ensure reliable execution of each step of your AOP
Enabling an AI agent to take action, like processing refunds, updating account details, or troubleshooting issues, requires structured workflows. That’s where Agent Operating Procedures (AOPs) come in. They’re the playbooks that allow Decagon agents to resolve complex, multi-turn conversations reliably at scale.
An AOP is a step-by-step set of natural language instructions backed by code. This design combines human-like adaptability with the control needed for production systems. Decagon built AOPs on three principles: they’re fast to create and iterate on, flexible yet durable, and equipped with guardrails to keep sensitive operations safe.
Creating an AOP starts with a descriptive name and entry conditions, the triggers that tell the agent when to use that workflow. From there, AOP Copilot can generate a first draft from plain English or an existing standard operating procedure, saving time and letting teams iterate quickly. Each workflow is structured as a series of nodes, moving step by step until the process is complete.
AOPs become even more powerful when extended with tools and metadata. Tools are custom logic like API calls, data lookups, or calculations that the AI agent can run in real time. Metadata provides extra context, such as location, role, or product tier, allowing workflows to adapt based on customer profile. Together, they connect the agent to live systems and personalize responses.
Nodes (represented by gear icons) combine tools, metadata, and natural language instructions in your AOP. They serve as critical decision points that trigger actions and provide checkpoints for reliable workflow execution and detailed observability.
In summary, AOPs give CX teams both control and flexibility: structured enough to be reliable, but open enough for natural, conversational AI.
