Conversation context

Before advancing to the APIs and integrations, there is an important concept used across the platform: the conversation context. Each conversation can have multiple messages from the user and the virtual agent. Those messages might generate data important to maintain the conversation, understand the user and update information about the current process.

Channels and webhooks can manage the context to add information relevant for the virtual agent execution. Any information fetched by services can be added to the context for later use, while other webhooks might use data stored in the context to call other services and change the execution flow of the dialogue, and so on. The context of the conversation is one of the most powerful tools in eva.

There are three types of context:

Open context

This context is the least secure. It is shared in all integrations and can be modified by anyone. Channels that integrate with eva are considered insecure and this is the only place where they can manage information in eva’s context.

Don’t store sensitive data in this context. This information is visible and modifiable by external agents, such as channels.

Visible context

The visible context is available for everyone, but channels are not able to change its content. For the conversation service this is a read-only context. Information that might be used by the channels but that impact the conversation flow, service calls and overall functioning of the virtual agent must be added here.

Important: don’t store sensitive data in this context. This information is visible – but not modifiable – by external agents, such as the channels.

Hidden context

The most secure of the three. This context is only visible by eva’s platform and services called through webhooks.

If any sensitive data must be managed in eva, this is where it must be stored.

​