Workflows let you chain together AI tasks into an automated sequence. Instead of running each step manually — extracting key terms, researching the relevant law, drafting a summary — you build a flow once and run it whenever you need it. Each step feeds its output into the next, so the whole process runs end to end without you switching between tools.
They’re built on a visual canvas where you lay out steps, connect them, and configure what each one does. The result is a reusable pipeline that can handle complex, multi-step work in a fraction of the time it would take to do manually.
Saga’s legal engineers can help you design workflows tailored to your firm’s specific processes — reach out to your account team if you’d like assistance.
How workflows are structured
A workflow is a linear sequence of steps. Each step is a node that does one thing — generate text, search legal sources, translate a document, run a grid review. You connect nodes in the order you want them to run, and data flows from one step to the next automatically.
There’s no branching or looping — every workflow is a straight line from start to finish. This keeps things predictable: you always know what runs when, and each step can reference the output of any earlier step.
What steps can do
Steps fall into two categories: inputs that collect information from you, and actions that do something with it.
| Step | What it does |
|---|
| Prompt input | Asks you to enter text — context, instructions, a question — that later steps can use |
| Files upload | Asks you to upload one or more documents for the workflow to process |
Actions
| Step | What it does |
|---|
| Run prompt | Sends a prompt to an AI assistant and returns the response |
| Drafting | Generates one or more documents based on earlier inputs |
| Legal research | Searches across selected legal sources and returns results with citations |
| Prompt library | Runs a saved prompt from your prompt library |
| Grid review | Creates a grid review with uploaded documents and AI-generated questions |
| Translate | Translates text or documents between languages via DeepL |
| Tasks | Runs a built-in task like /summarize, /anonymize, or /proofread |
| Logical thinking | Applies step-by-step reasoning to analyze or evaluate earlier outputs |
| Web search | Searches the web and returns relevant information |
| Code interpreter | Executes Python code for data processing, calculations, or analysis |
How data flows between steps
Each step can reference the output of any step that came before it. When you’re configuring a step’s instructions, type @ to mention a previous step by name. At runtime, that mention is replaced with the actual output from that step.
For example, a “Run prompt” step can @ a “Files upload” step to analyze the uploaded documents, and a “Drafting” step further down can @ both to produce a final report. The data threads through the workflow automatically. 
