Dust and Perplexity Integration
Demonstration of how apps are integrated in WEXTL workflow builder[4]
Connect Dust and Perplexity to automate ai workflows. Trigger events from one app, run actions in the other and use AI to make smart decisions. Integrate apps in 3 simple steps - no code required.
- 3-day trial
- Cancel anytime
- Up to 10 minutes quick set up
- GDPR
- Data Encryption
- 2FA
- Local Data Region
Learn about Dust and Perplexity
Detailed info you need to know about Dust and Perplexity integrations in WEXTL. Explore which modules apps support and how you connect them.
Dust

Chat with Dust agents, keep your knowledge base up to date and manage agents, skills and analytics.[5]
Perplexity

AI answer engine for real-time web search, Sonar chat, and embeddings.[6]
How to connect Dust to Perplexity
Set up your Dust and Perplexity integration in 3 simple steps[2]. No coding required. Up to 10 minutes setup.
STEP 1
Connect Dust and Perplexity
Save credentials in WEXTL once. We store them encrypted and reuse the authorization across every workflow[3]. No coding or API skills required.
STEP 2
Build a workflow
Paste selected Dust and Perplexity nodes onto the canvas[4], or describe what you want and WEXTL wires the flow together with AI Builder.
STEP 3
Map your data
Choose which fields need to sync between Dust and Perplexity. Use filters or a JS custom code step in between. Everything is on the canvas.
How does the integration between Dust and Perplexity work in WEXTL?
WEXTL exposes actions and triggers for Dust and Perplexity that help you connect apps and automate repetitive tasks[1]. A trigger is an event that happens, and an action is a step that performs when the event has occurred.
Perplexity triggersDust actions
Perplexity modules
- Cancel an Agent Response Asks Perplexity to stop an agent run started in the background. The run reports the status cancelling and stops shortly after. A run that has already ended returns an error.
- Create a Background Agent Run Starts a Perplexity agent run that keeps going on Perplexity and returns at once with the run ID and a queued status. Read the finished answer with Get an Agent Response. Takes the same settings as Create an Agent Response.
- Create an Agent Response Sends Input to a Perplexity agent and returns its answer once it finishes, within 3 minutes. Use Effort to set how much work the agent does, or Model or Models to pick the model yourself. Use Tools to let it search the web.
- Create Contextualized Embeddings Turns the chunks of up to 512 documents into embeddings, with each document in its own inner array of Input. Use Dimensions to set a vector length from 128 to 1024 on the 0.6b Model.
- Create Embeddings Converts up to 512 texts, each up to 32K tokens, into vector embeddings with the 0.6b or 4b Model. Use Encoding Format to receive the vectors as Base64 Int8 or Base64 Binary.
- Get an Agent Response Reads one agent response by its ID. Use it to check a background run, which stays queued or in progress until it ends as completed, failed, cancelled or incomplete. A completed run carries the answer.
- Get Computer Usage Analytics Counts computer usage per time bucket for one Dataset, from Start Time on. Use Bucket Width for daily or hourly buckets and User Email to narrow results to one member. Uses the Organization Analytics API Key when the credential has one.
- List Models Returns the models offered by the Perplexity API, each with its ID, Created time and Owned by value.
- Make an API Call Makes an authorized free-form request to the Perplexity REST API with your saved credential.
- Run an Agent Sends an Input prompt to a Perplexity agent at a chosen effort and returns the answer with its Usage. Answers that take longer than 3 minutes fail. The simple version of Create an Agent Response.
- Search Looks up a Query with the Perplexity search API and returns the Results along with a Server Time.
- Sonar Chat Sends Messages to the Sonar model of your choice and returns the reply with its Citations, Search results and Related questions. Use Search Mode to draw on web, academic or SEC sources, and Disable Search to answer without any web search.
- Watch Models Checks the Perplexity model list on a schedule and starts the workflow once for each model not seen before. Use Limit to adjust how many results each cycle handles.
Dust modules
- Answer an Agent Question Replies to a question an agent asked during a conversation. Use Selected Options to give the numbers of the chosen options, or Custom Response when the question takes free text.
- Archive a Skill Archives a reusable skill in your Dust workspace.
- Archive an Agent Archives an agent in your Dust workspace.
- Cancel a Message Generation Stops agents that are still writing a reply in a conversation. Use Message IDs to say which agent messages to halt.
- Create a Content Fragment Attaches material to a conversation under a Title. The material is the Content text, a URL to read, or a File ID of an uploaded file. Turn on Skip File Processing to attach an uploaded file without reading it.
- Create a Conversation Opens a Dust conversation from a first Message. Name the Agents that should answer, and turn on Wait for the Answer to get their reply in the same step. Use Share With to give workspace members write access.
- Create a File Upload URL Prepares a file upload in Dust and returns the File record. Use File Name, Content Type, File Size (Bytes) and Use Case to describe the file.
- Create a Message Posts a Message into an existing conversation. Leave Agents blank and no agent runs. Use Model Provider and Model ID to answer with one specific model.
- Create an Agent Defines a new agent from its Handle, Description, Instructions and Toolset. Use Max Steps per Run to bound the work done per message and Editors to name who can change it.
- Create an App Run Starts a Dust app from a Space at the version fixed by Specification Hash. Turn on Wait for the Result to get the Results in the same step, and use Block Filter to keep only some blocks.
- Create or Update Document Writes a document into a data source under a Document ID, replacing it if it exists. Give either Text or a Section, and describe it with Tags and Timestamp.
- Create or Update Rows Adds or replaces Rows in a table, matched by Row ID. Turn on Delete Existing Rows First to empty the table beforehand.
- Create or Update Table Creates a table by Name, or updates an existing one through its Table ID. Add a Title, Description and Tags to document the table.
- Delete a Data Source View Deletes a data source view held in the chosen Space.
- Delete a Document Removes an indexed document from its Dust data source.
- Delete a Row Deletes a table row in Dust.
- Delete a Table Removes a table out of the chosen Dust data source.
- Delete Message Feedback Withdraws the thumb rating left on a message of a conversation.
- Download a Conversation File Fetches a file that an agent produced during a conversation, located at the File Path. Returns the File with its Size (Bytes) and Content Type.
- Edit a Message Rewrites the text of an earlier Message in a conversation. Choose Agents to run on the edited text, or leave them empty to run none.
- Export an Agent as YAML Exports the configuration of one agent from your Dust workspace as YAML text.
- Get a Conversation Opens a conversation with its Title, Visibility and Content. Page through long histories with Message Limit and Last Value.
- Get a Data Source View Reads one view of a data source, showing its Category, Kind and Parents In.
- Get a Document Fetches an indexed document by Document ID, showing its Title, Mime Type, Tags and Timestamp.
- Get a Row Reads a single row of a table by its Row ID.
- Get a Table Shows the Schema of a table together with its Table ID, Title and Tags.
- Get a Trigger Reads one trigger with its Kind, Status and Custom Prompt.
- Get an Agent Reads one agent configuration, with its Name, Description and Version. Set Variant to Full for the whole configuration instead of the light record.
- Get an App Run Checks on an earlier app run by its Run ID. Shows its Status, Results and Traces.
- Get Consumption Analytics Exports credit usage between a Start Date and an End Date, as CSV unless you change the Format. Use Filter to limit the rows. The export reports a Row Count.
- Get Conversation Feedback Collects the thumb ratings left on replies in a conversation, with their Thumb Direction, Content and Created At. Use Limit to set how many rows are read.
- Get Conversation Mention Suggestions Suggests agents or people to mention in a conversation, matching the Search Text against names or emails. Use Kinds to narrow the type of suggestion.
- Get Mention Suggestions Suggests agents or users to mention across the workspace for the Search Text. Turn on Current Conversation Only to restrict the list.
- Get the Consumption of a Conversation Reports what a conversation cost, as Billed Credits with a Details breakdown.
- Get the Sharing of a Conversation Shows who can reach a conversation, listing its Owner, Members and Groups.
- Get Workspace Analytics Exports one analytics Table between a Start Date and an End Date. Use Time Zone to decide where days start and Limit to set how many rows are read.
- Import Skills Uploads a skill File, or a ZIP holding several. Use If the Skill Exists to choose whether a duplicate fails, is skipped or is replaced, and read how many skills were Imported, Updated or Skipped.
- List Agents Shows the agents of your workspace, up to a Limit. Use View to restrict the list to a group such as Published or Workspace, and Include Authors to add each author.
- List Apps Retrieves the Dust apps stored in a Space, giving the Name, Description and Saved Run of each.
- List Data Source Views Browses the views defined inside a Space, with their Category and Kind.
- List Data Sources Finds the data sources attached to a Space, giving the Name and Connector Provider of each.
- List Documents Gathers documents in a data source with their Title and Tags. Use Document IDs to look at only some of them.
- List MCP Server Views Gathers the tool servers a Space exposes, giving the Server Type and Updated At of each.
- List Rows Reads the rows stored in a table of a data source, up to the Limit.
- List Skills Lists skills with their Name and Status. Filter on Availability or Status. Turn on Include Skills You Cannot Edit with an admin key to add skills whose editors did not share them.
- List Spaces Pulls spaces with their Kind and whether each Is Restricted. Use Kinds to keep only regular, global, system or public ones.
- List Tables Browses the tables of a data source with their Name and Schema.
- List Triggers Finds the triggers of your agents with their Kind and Status. Use Kind to see only one type.
- Make an API Call Calls the Dust REST API directly with a free-form request under your saved credential.
- Parse Mentions Converts the @mentions inside Markdown text into the mention syntax Dust understands.
Explore alternative integrations
There are other apps[9] supported by WEXTL that can be paired with Dust and Perplexity integrations. Pick any from the list below if the current combination isn't the one you need.
Frequently asked questions
Common questions about connecting Dust and Perplexity.
References
List of sources used to gather information about the Dust and Perplexity integration.
- Dust and Perplexity integration source code, module specs and credentials implementation.
- Our Dust and Perplexity integration documentation, structured input and output parameters, scopes, and authentication methods.
- Official vendor API documentation for Dust and Perplexity, used to verify field meanings, authentication flows, and anything our own specs don't fully capture.
- WEXTL® visual workflow builder, anonymized data from our technical support team.
- Dust integration information
- Perplexity integration information
- WEXTL® Scheduling
- WEXTL® Pricing and Trial
- WEXTL® Apps Library
How we write our apps documentation
Explore how WEXTL® crafted Dust and Perplexity integration page documentation. Used sources, the role of AI, and how the team validates the result.