Slack is where the people you need, the information you share, and the tools you use come together to get things done. With Knowi's Slack integration, its powerful Search-based analytics (or Natural Language Processing) capabilities combine with Slack's intuitive messaging UI, allowing you to ask questions from your Knowi data directly from the Slack app and get answers back instantly. This allows you to obtain quick insights from your data, optimize by integrating it into your workflows, and enhance collaboration within your team.
Installing the Knowi bot
Step 1: To get started, add the Knowi bot to your workspace by clicking on the link below.
Step 2: After clicking the link, you will then be guided through the authentication flow to connect your Knowi and Slack accounts.
The previous authentication flow grants the Knowi app access to your Slack workspace. The following authentication flow will grant your Slack workspace access to your Knowi account.
Step 3: Back in your workspace, enter the command /knowi. You will then be prompted to connect to your Knowi account. Click the link and enter your Knowi credentials.
Step 4: In the following screen, click Allow to grant your workspace permission to access Knowi, then click Get Started in the next screen.
Step 5: Once redirected back to your Slack workspace, enter the command /knowi again. Now that your Slack workspace has been connected to your Knowi account, you will receive the following response:
This confirms a successful connection to your Knowi account and you are now ready to start asking questions from your Knowi data via Slack.
Enable/Disable Slack Integration
Knowi's NLP Slack Integration is enabled for each account by default. Admin users can enable/disable the feature by navigating to Settings > User Settings > NLP Slack Integration
Enable Slack File Sharing
Typically "On" by default, in some cases, you may need to manually enable file sharing for your Slack workspace to complete the integration. To enable it in your workspace, navigate to Settings & Permissions > Permissions Tab > Enable Public File Sharing. Or use the link format: https://<WORKSPACE_NAME>.http://slack.com/admin/settings#public_file_urls
Hands-on With Knowi’s Search-based Analytics
Fundamentally, Knowi’s Search-based analytics (NLP) capabilities with Slack integration function similarly to how it works when using NLP within the Knowi UI. It allows you to ask questions in plain English from your data and queries across all datasets within your account.
Once you type in a question, Knowi will detect and query the dataset that best matches the question asked and return a visualization most appropriate for the data being returned.
In the following examples, we’ll be using Knowi’s Search-based analytics via Slack to ask questions and retrieve data pertaining to an email marketing campaign.
Example 1:
We want to know the total emails delivered for each of the customers. So in Slack, we’ll type:
/knowi total emails delivered by customer
Knowi will briefly process your question, then return an answer in the form of a visualization.
Notice that the answer returned is in the form of a Pie Chart, so you can quickly visualize the proportion of delivered emails for each customer. Use the magnifying glass to zoom in to the visualization.
Data Preview
The results will also return a Data Preview table, right below the visualization. By default, it will include the first ten records of your query results.
Download Results
You have the option to download your query results as a CSV by clicking the Download results button:
Explore This Analysis
You’ll also notice the Explore this Analysis button below the results. Clicking on this will take you another screen that shows the visualization settings for the results. This interface will look familiar to what you see when working within the Knowi UI.
From here, you can do further analysis by clicking the Data tab to see how the results were initially aggregated and make any changes as needed. You can also change the type of visualization to display the results. Finally, you can use the NLP text bar to edit your question, or ask a brand new question all together.
Note: In the NLP text bar, hit the space bar following your question to see the dataset name displayed to the right.
Example 2:
Let’s ask another question from our data. This time, to find out the average converted emails by campaign name on a weekly basis. Back in Slack, type:
/knowi avg conversions by campaign name weekly
The results return an Area Chart visualization, with each line area representing the different email campaigns and their average conversions over the past several weeks. Exploring the analysis further shows that the “30% off Limited Sale” email campaign had the most conversions per email in the most recent week.
Example 3 - Select a Dataset:
Knowi’s Search-based analytics (NLP) also gives you the option to ask questions from a specific dataset in your connected account by specifying a flag (-d) at end of your query to return a matching dataset suggestion. You can then select the dataset from the list of suggestions to execute your query. Note that the first dataset listed is the default it will use, unless you choose another one.
Format:
/knowi <query/question> -d <dataset name>
Example:
/knowi total tickets this week -d zendesk
Example 4 - "All Details" Command:
A handy query for getting detailed results for a particular entity (i.e. customer, sales associate, email address, etc.) in your dataset is by including "all details for..." in your question. This will return all fields in the dataset for the given entity.
Format:
/knowi <"all details for.."> <entity> -d <dataset name>
Example:
/knowi all details for Wells Fargo -d sending activity
You can also add conditions (i.e. rolling date ranges) to the "all details for..." command to refine your results. Below are some examples:
/knowi all details for Wells Fargo since yesterday -d sending activity
/knowi all details since last 4 months for campaign like Newsletter -d sending activity
/knowi all details for Wells Fargo where message type is Marketing -d sending activity
Natural Language Processing Settings
Knowi’s Search-based Analytics can be figured by navigating to Settings > User Settings > Natural Language Processing Setting. You can toggle the settings below to disable/enable. By default, they are enabled.
NLP Across Datasets
When Enabled/ON, enables natural language interface across datasets and the NLP text bar appears at the top of dashboards. When Disabled/OFF, the NLP text bar will disappear from the top of the dashboards. Note, that you will still be able to use the NLP interface within individual widgets in the Analyze screen.
Index By Default
By default, all datasets will be automatically indexed. Turning this off will automatically exclude NEW datasets from being indexed. Datasets can be individually indexed from the Data Management section of the query listing Queries > Data Management > NLP . If you would like to turn off historical datasets for indexing as a one time operation, use the option in the pop up.
NLP Slack Integration
When Enabled/ON, enables natural language interface from Slack.
NLP Slack User Hints
When using search-based analytics on Slack, allows you to configure the message displayed when a user types in /knowi (make this a code block). Typically these would be the most commonly used questions. The message is in markdown format
Data Management for Natural Language Processing
To configure NLP settings at the dataset level, navigate to Queries > Data Management > NLP. It can also be accessed at the widget level via More Settings > Data Diagram > Edit Dataset (click on the pencil icon in the blue box representing the dataset).
NLP Indexer
Defaults to ON. Turning it off will exclude the dataset from Search-based Analytics/NLP queries. Note that it may take a few minutes for the change to take effect.
Synonyms
Synonyms are useful for adding context awareness to your Search-based Analytics/NLP queries. For example, if you have a field in your dataset named customer, you can add a synonym “tag” to this field such as “shopper”, “buyer”, “clent”, etc. So, when you type in a question like “total sent by client”, it will recognize the term “client” as equivalent to the field “customer”. Multiple synonyms can be added for each field.
