Suggestions

- Scheduled trigger: We send out suggestions at specific time intervals. On such an interval cycle, we trigger the TechWolf Skill Assistant. The interval can be changed depending on your needs.
- Fetch suggestions: To get those suggestions, we fetch them from our own API. More specifically, from the Suggestions Skill Profile endpoint, for all employees.
-
Format suggestions:
The Skill Assistant first determines which users should receive suggestions
or reminders. The system determines this by checking when each user last
received a suggestion and comparing it against the configured timing
parameters for suggestions and reminders.
The suggestions are then formatted based on the configurations for the
message content. See how the message looks like in the
How It Looks
section. - Send suggestions: We send out the suggestions to the messaging platform.
- Users receive the message: The messaging platform delivers the message to the correct user.
Validations

- The user clicks submit on a card, which informs the messaging platform that it should send an update to the TechWolf Skill Assistant.
- The message is received by the Skill Assistant, which receives a list of confirmed and rejected skills.
- The TechWolf Skill Assistant stores this information, such as which skills, but also when and by whom.
- The feedback is sent to the TechWolf API, using the
Employee Skill Profile feedback endpoint
and can be tracked with the
source
field as“tw--bot”
. To access feedback provided by an employee through the Skill Assistant, use the Employee List Skill Event endpoint withskill_profile_feedback
asevent_type
. The resulting Skill Events withsource
field as“tw--bot”
are the feedback events given using the Skill Assistant.
Linking users through Custom Properties
An important step for the Skill Assistant to work is linking employee profiles in TechWolf to users in the messaging platform. This can be done by setting a Custom Property on the employee profile in TechWolf. The Skill Assistant will then use this Custom Property to link the employee profile to the user in the messaging platform.Data flows
General overview

Components
Slack The Slack environment used by the customer. AWS infrastructure TechWolf utilizes AWS infrastructure to facilitate communication between Slack and the Skill Assistant. This infrastructure comprises:- CloudFront: Processes and routes incoming requests at edge locations, minimizing latency by handling traffic close to its source.
- Lambda at Edge: Processes incoming requests by extracting the Enterprise or Workspace ID and uses DynamoDB to determine the correct Skill Assistant deployment region (EU or US) for routing.
- Global DynamoDB: Maintains a mapping between Enterprise/Workspace IDs and their corresponding deployment regions (EU or US).
Data processing
Types of data that is processed- Skill Suggestions: Automatically inferred skills for an employee, retrieved from the Skill Engine API.
- Skill Feedback: Employee feedback on their suggested skills. Either validating that they have the skills, or rejecting the skills.
- Slack User Data: Employee details retrieved from Slack systems, including name.
Managed by | Suggestions | Feedback | Slack User Data | |
---|---|---|---|---|
Slack | Customer | X | X | X |
AWS: CloudFront | TechWolf | |||
AWS: Lambda at Edge | TechWolf | X | X | |
AWS: Global DynamoDB | TechWolf | |||
Skill Assistant | TechWolf | X | X | X |
Data storage
Overview of Data Storage LocationsManaged by | Suggestions | Feedback | Slack User Data | |
---|---|---|---|---|
Slack | Customer | X | X | X |
AWS | TechWolf | |||
Skill Assistant | TechWolf | X | X | X (No personal identifiable information stored) |
Communication Protocols
All data exchanges occur over REST APIs secured by TLS 1.2 or higher.Suggesting Skills

- Fetch suggestions: On a regular basis, the Skill Assistant will fetch suggestions generated by the API.
- Sending the suggestion: The suggestion is sent by the Skill Assistant to the customer Slack tenant.
- Slack ID, Internal ID, Suggestion
- Slack ID, Suggestion
User Input
User input entails button clicks and messages.
- User input request: When a user interacts with a suggestion, it is sent to CloudFront in the TechWolf AWS instance.
- Routing to Skill Assistant: The request is processed and routed by CloudFront to the Skill Assistant. Only necessary information is retained, and names and email addresses are dropped.
- Execution of request: The Skill Assistant directs the request in proper format to the API, where the request is executed on the customer’s data.
- Response to user: A response, based on the request’s proper execution, is sent back to the concerning Slack user.
- Event Data or Interactivity Data, Feedback, Slack User Data (Contains the name of the user which cannot be dropped from the request.)
- Event Data or Interactivity Data, Feedback, Slack User Data (Contains the name of the user which cannot be dropped from the request.)
- Internal ID, Slack ID, Depending on the event: Feedback or Request suggestions
- Slack ID, Custom response, Suggestion