How to use Compass

Overview of AI-powered Workflow Builder on SGP

Compass is an AI-powered low-code workflow builder that enables enterprise operators to import data, transform it, call LLMs or Agents, analyze or evaluate the output, & automate the whole workflow, all in one interface.

Getting started

You can access Compass in SGP (Scale GenAI Platform) through the Workflows tab. If you don’t see the tab on your SGP, please contact us. To start a workflow you must either import data or connect to a data source. Data sources available vary based on the connections set in the SGP instance you are running Compass on. You can set up new Data Sources in the under the Assets tab.

We have provided starter templates that you can Duplicate or take inspiration from that are based on the most common workflows engineers run on Compass. Just press the copy button on the top right to duplicate a workflow.

Compass cards

The basic building block in Compass is called a card. Cards can produce data, transform data, or perform actions on data. When you start a new Compass session, you can add cards to build your workflow.

Each card has its own interface appropriate for its function. Think of it like a form that you have to fill out to tell the card what you want it to do.

For example, the Python card appropriately has a code editor for you to write the code to transform the data you have imported in a previous step.

Cards stack upon each other, allowing you to perform rich transformations or analyses over the previous card’s data. As an example, we can take a CSV that has different LLM completions against a prompt and have an LLM judge it against ground truth for evals.

Compass sessions are long-lived, so you can run cards that take extended periods of time (for example, model evaluations using reasoning LLMs on thousands of rows) without losing your work. You can save cards while iterating, then run them later when you’re ready. Each session has a unique URL identifier that gives you persistent access to your session.

Finally, once you are done with a workflow, you can export the final output dataframe as an Evaluation that you can always access & monitor later, in cases you are running the evaluation on your agent traces periodically. You can also save it as an SGP Dataset that can be dowloaded and shared as a CSV as well.

In the event, that you need data from another Compass workflow in this one, you can use the Join Workflow card to bring the output of another Compass workflow (dataframe) and join it with the output here. Attached image is from an example workflow where we had to bring the mock PII from another workflow to perform an evaluation on whether our agent was correctly implementing PII anonimization.

Key features & associated cards

Compass offers a variety of cards for pulling, transforming, and performing actions on data. Additional cards will be added based on enterprise use case requirements. Some of the ways cards be used are:

• Importing data: Read data from sources like agent Traces tab, a CSV upload, or queryable sources like Postgres, Snowflake, Mongo, or MS SQL directly.
• Transforming data: Transform your data using custom Python code or simple cards like select columns, filter or aggregate. You can also use Join Data to join the output from another Compass workflow into this workflow’s output (dataframe).
• Call LLM or Agent: Generate output and traces against input from each row of your dataset via cards like Call LLM or Call Agent. Compass allows you to call your Agentex agents on SGP.
• Analyze data: Evaluate your outputs using LLM as Judge card and access the evaluation anytime in the SGP Evaluations tab
• Visualize data: Generate visualizations from your transformed dataset using the Chart card. For deeper dives, export the data as an Evaluation & open in the Dashboards tab.
• Export the data: Export the data as CSV or as a Dataset on SGP. This dataset can be referred to in the Evaluations tab anytime.
• Automate & monitor: Schedule the workflow to run hourly or daily. Monitor runs & get notified via Slack.

Most cards are available in SGP > Workflows > Playground. Compass instances deployed in customer VPCs may have a limited set of available cards based on customer requirements. You can chat with the Compass team to activate or disable certain cards depending on your customer’s needs.

Schedule & monitor workflows

If you have a sequence of Compass cards that you run over and over, you can save them as a Compass workflow so that you can easily load and re-run them again later.

If you have a sequence of Compass cards that you run repeatedly, you can save them as a workflow to easily load and re-run them later. You can also Share the workflow & add other editors for collaboration.

A powerful feature of Compass workflows is the ability to execute them on a schedule. Within the Save Workflow modal, toggle the Set a Schedule option and configure your desired schedule. Scheduled workflows allow you to automate repetitive tasks.

From the side menu, uou can view Execution logs anytime to monitor past runs. You can set up alerts to get notifications on Slack on failed automated runs. You can also check Workflow history to understand how the workflow changed across versions, the diffs, & the author responsible for each version.

What’s coming next in H1 2026

Here are core features planned on our roadmap.

• More data source support: Currently, Compass supports connection to queryable data sources. We plan on supporting file/artifact data sources.
• Document parsing & extraction on Compass: Utilize our Dex & Iris capabilities inside Compass to turn unstructured data across Docs or PDFs into structured data & extract the information you need for your workflows.
• Streaming data for workflows: Currently, Compass can import data for workflows in batches. We plan on supporting streaming data to empower real-time data processing use cases.

Creating a custom Compass card to support your specific enterprise use case on their VPC is also straightforward. If your organization has functionality requirements, please contact us.