In this guide, we will show you how to integrate SnapCall Flow into your Messaging Widget, allowing you to automate and simplify the process based on videos uploaded by customers.
This approach offers significant advantages over traditional check-in/check-out methods:
Customers will be forced to take live videos of the delivery, meaning your company will receive a direct proof of the issue from their side.
SnapCall will automatically populate all the necessary custom fields, meaning your agents can focus on solving the issue instead of manually adding data on the ticket.
Powered by AI, the system ensures that customer-submitted videos contain all the necessary information for agents to verify the process manually. Customers will only be able to complete the flow once all steps and criteria are fully met, meaning we will partially eliminate any back and forth between the customer and the agent.
For the configuration we will use mainly the following tools:
SnapCall with a Flow Subscription: This will enable the creation of three distinct flows: two for the check-in and check-out processes, and one for customers to report any damage.
Zendesk Messaging Widget: This is where customers can record a video or take a snapshot. Once the media is collected, it will be organized either into a ticket or a conversation, allowing agents to review it offline at their convenience.
Ultimate Bot: While the standard Zendesk Flow Builder is sufficient for basic automation, the Ultimate Bot offers enhanced capabilities. It allows you to create advanced workflows based on the outcomes of the videos recorded by customers. For instance, if SnapCall is unable to detect any damage on the video uploaded by the customer, they will be asked to upload it again.
Configuring your SnapCall Flow - step by step guide
To configure the first Flow for gathering data from a package's shipping label, start by navigating to the Flow section in your SnapCall Dashboard and clicking the "New" button. Assign a name to your Flow and select Snapshot as the media type. On the next screen, provide clear instructions for customers to follow when capturing their media. Then proceed to the following screen and enable 'Data Extract' at the bottom. Add the fields you want SnapCall to populate, specifying a Name for each and selecting the corresponding field from the drop-down list. Ensure that each defined name matches the information visible in the snapshot provided by the customer.
Repeat the same process for the other two Flows (or as many as you'd like to use for this configuration). Instead of 'Snapshot', select 'Video' as a type of media your customers will be able to record. If you're creating the Flow for the 'Damaged delivery' scenario, use a prompt that will produce different outputs according to the damage customer is showing. You can do so in the 'Content Recognition' AI skill and this would be a good example for such purpose:
You will be given some media related to a damaged item delivered:
- If you detect the damage in the package, please provide as an output: ''Damage in the package detected''
- If you detect the damage in both the package itself as well as in the product inside it, please provide as an output ''both''
- If you detect the damage in the item or product inside the package itself, please provide as an output: ''Damaged product detected''
- If none of the above applies, type ''None''
Save changes and create a Flow to list all items inside the delivery as well. While editing the prompt of Content Recognition, let the AI know it will have to list all items in bullet points. A prompt like the one below should do the job:
You will be given a few media related to a delivery package, where client states some of the items purchased are missing.
Please indicate in bullet points each item you see inside the box. Each bullet point is an item that you detect.
Please do not any other information on the output if not the bullet points requested earlier.
Adding your Flow to your Ultimate bot
Now that the SnapCall configuration is complete, we can proceed with adding these flows to a brand-new Ultimate flow configuration. You can define the process in a way that best suits your organization, but here is the approach we used to streamline and simplify the check-in/check-out process:
Begin by requesting the customer to capture a snapshot of the shipping label. This provides valuable information for your agent, such as the order number, tracking number, sender, recipient, and more. SnapCall can also populate these details into custom fields, making it easier to generate reports in Zendesk or set up advanced automations.
To enable the customer to take a snapshot, add a 'Bot message' step to the Flow, and include an Action to open a webview. Click here to learn more about opening a webview with Ultimate.
On this step, make sure to save the conversation id as a parameter, so that SnapCall can use it to add the media directly in the conversation. Learn more here
Once the two bot messages are configured, add a 'visitor message' step. When the customer uploads a video using the Flow, SnapCall will post a new message within the chat using the related conversation ID. This message will appear as a visitor message, ensuring that the flow continues only once the media has been received. In the same step, make sure to save all conversation metadata from SnapCall, as it includes the AI output. You should configure it similarly to the example in the screenshot below, but feel free to refer to this FAQ article for additional guidance if needed.
Next, we prompt a Carousel to the customer. The first option will allow the customer to flag an issue with a damaged package, while the second one will allow them to report a missing article inside the package itself. For both use cases, we will ask the customer to record a video and SnapCall will be opened into a webview using the same instructions shared above.
The AI will be used differently according to the scenario selected by the customer: while in the first one we want the AI to assess how urgent the issue is (by defining the damage of the package), in the second scenario we use AI to list all items visible, allowing the customer to just film the problem instead of writing a long message, and at the same time giving the full list to the agent as well so that they can check this internally.
Same as done earlier, add a 'visitor message' step so that the flow can continue as soon as the customer upload anything.
Building conditions on your Ultimate bot
On the 'Damaged package' scenario, we now want to build conditions according to the AI output provided by SnapCall, so that if the product itself is damage we can reassure the fastest reaction from support. To do so, let's use a Condition (green) step from the Ultimate Flow Builder.
If you're using the exact prompt I shared earlier in the article, you can set up the first condition as 'description' (which is the variable where we stored the AI output from SnapCall) IS 'none', so that the first thing Ultimate will check is whether the video shows a damaged item at all. In the ELSE part, we then build a cascade where Ultimate checks each possible value of the 'description' variable, as shown in the screenshot below.
In the example above, we use SnapCall AI to determine if the video uploaded by the customer includes all the necessary details and information. If it doesn’t, we ask the customer to record a new video, eliminating the need for an agent to request the same at a later stage. This significantly reduces resolution time, as it ensures the customer cannot complete the check-in or check-out process until all criteria are met.
Submit the ticket to an agent for manual review
The final step is submitting all the information to an agent so they can finalize the process offline on behalf of the customer. For this, we recommend using the 'Escalation' > 'Forward to an agent' step. This approach is beneficial for the following reasons:
The agent will have access to the full conversation history between the customer and the bot.
All media recorded by SnapCall will be available on the right side of the Zendesk interface, along with a summary, transcript, and additional details.
Agents can handle the case either offline or live, depending on your company’s processes.
Have any questions? Feel free to reach out via our chat widget or email us at support@snapcall.io!