Aissist.io
  • Aissistant
  • Tutorial
    • Quick Start
    • Turn assets into AI
      • Domain/Subdomain
      • Web Page
      • Google Drive Doc
      • Documents
      • Asset Debugger
    • Create Sub Agents
    • Deploy Gateway
    • Tune Instructions
      • Tweak global instructions
      • Enhance with Sub Agents
      • Refine assets
    • Teach AI with Examples
    • Streamline with human team
    • Auto-Pilot, Auto-Draft, Co-Pilot
    • Managing Points
    • Instructions, Assets, and Sub Agents
    • Simulator
  • Integrations
    • Shopify
    • Woocommerce
    • Adobe Commerce (Magento 2)
    • Restful API
    • AWS Lambda
    • Action Debugger
  • Gateways
    • Front
    • Gorgias
    • Intercom
    • Zendesk
      • Zendesk Conversation (messaging)
    • Hubspot
    • Salesforce
    • Kustomer
  • Use cases
    • Sales
    • Service
  • Success Metrics
  • FAQ
  • Release notes
Powered by GitBook
On this page
  • Method 1. Suspend the Sub Agent
  • Method 2. Notification/Assignment on tag
  • Method 3. Dedicated inbox
  • Method 4. Shared view
  1. Tutorial

Streamline with human team

PreviousTeach AI with ExamplesNextAuto-Pilot, Auto-Draft, Co-Pilot

Last updated 14 days ago

While we strive for full automation, there are instances where Aissistant may not be able to address every customer query. This could be due to the complexity of the queries, limited access to your internal systems, or the preference to have certain sensitive tasks, like refunds, handled by human agents. In these situations, smart tags can be used to seamlessly transition tasks from Aissistant to your human team. Below are couple different methods to do so.

Method 1. Suspend the Sub Agent

A straightforward approach to handing off tasks to the human team involves employing the post-action feature in the sub agent. For instance, the return_or_refund sub agent comes with contextual instructions that prompt the user to provide their order number, shipping address, reason for return, and a photo showing the product's current state. This sub agent is set up with the post-action 'suspend afterwards,' ensuring that Aissistant halts any further responses. Once the user submits the requested information, a human agent can step in to handle the return process.

Method 2. Notification/Assignment on tag

An alternative straightforward approach involves setting up a rule within your agent platform. This rule would trigger a notification or an assignment to a human agent whenever a message is sent that includes either the sys_human_follow_up or sys_human_help tag.

Method 3. Dedicated inbox

Alternatively, utilizing predefined tags like sys_human_help and sys_human_follow_up is another effective method for alerting human agents to take action. We recommend our users to take this method.

Step 1: Create an empty inbox

Initially, it's essential to establish a shared, empty inbox. This inbox won't be linked to any message channels; instead, it will exclusively house messages that Aissistant has tagged as requiring follow-up by a human agent.

Step 2: Create a rule to move tagged conversation

Aissistant includes predefined tags such as sys_human_help and sys_human_follow_up for immediate notifications, but you also have the flexibility to create custom tags tailored to your specific requirements. The sys_human_help tag is used when Aissistant lacks the information needed to respond to a query, while sys_human_follow_up is employed when Aissistant recognizes a user's request but cannot execute the related task, necessitating human intervention.

In FrontApp, you have the ability to set up a rule that relocates messages to the inbox you previously established. This happens whenever a message is tagged with sys_human_help, sys_human_follow_up, or any other custom tags you've designated as indicators for the necessity of human intervention.

Step 3: Human team follow up from the inbox

Once the previous rule is in motion, all messages flagged for human attention will be redirected to the specified inbox. The human team can then address these messages directly from that inbox. The image below illustrates a message that has been transferred to an inbox, awaiting follow-up by the human team.

Method 4. Shared view

Certain agent platforms, such as Gorgias, do not feature inboxes but instead offer views. In such scenarios, we can establish a shared view for tags that may necessitate assistance from a human agent. Then, the human agent can review this shared view and proceed to engage with customers.

In the following example, we'll use as a sample gateway to illustrate the development of an efficient handoff procedure and the method for receiving explicit notifications from Aissistant about tasks necessitating human intervention. Other gateways may have similar mechanism.

FrontApp