How It Works
A step-by-step guide to building workflows, configuring nodes, and wiring up variables in AutoPilot.
AutoPilot turns data work into a flowchart. You drag blocks — called nodes — onto a canvas, connect them in order, and click Run. Each node does one job and passes its result to the next. It's the visual version of a command-line pipeline:
cat data.csv | filter "age > 30" | sort by "name" > output.csvEverything runs inside your browser tab. Nothing is uploaded, no account is needed, and it keeps working with no internet connection.
100% private
Files never leave your machine.
Works offline
Runs fully in the browser, no server.
Handles huge files
Streams to disk so large data won't crash the tab.
The big idea
A workflow is a left-to-right chain of nodes. The output handle of one node connects to the input handle of the next — "send your result onward." A typical CSV pipeline looks like this:
Bring data in → reshape it → export any node's result straight from the execution panel. Mix and match the nodes below to build anything from "dedupe this contact list" to "merge ten PDFs and pull out the tables."
Create a workflow
- Open Workflows from the sidebar.
- Click New Workflow. Give it a unique name. If you already have workflows, you'll also see a Copy existing option — pick any workflow to use as a starting point, with its full canvas copied over. Otherwise just click Start blank.
- The canvas opens with a single Start node already placed. Click the tile below it to add your first real block.
- Workflows auto-save to your browser as you build — click Save in the editor toolbar any time to commit changes explicitly.
Screenshot placeholder
Screenshot placeholder
Add & connect nodes
- Click the + button on any node (or the large + tile on the empty canvas) to open the node picker.
- The very first picker asks "What triggers this workflow?" — pick Manual Trigger (starts when you click Run) or go straight to Upload File.
- Search or scroll the list, then click a node. It drops onto the canvas already wired to the previous one.
- Connections run handle-to-handle: the dot on a node's right edge (output) connects to the dot on the next node's left edge (input). Drag between handles to rewire manually.
- Each node shows a status indicator after a run — no icon when idle, blue spinner while running, green on success, red on error. Use the gear icon to configure or the trash icon to delete a node.
Screenshot placeholder
Screenshot placeholder
Configure a node
- Click a node's gear to open its configuration dialog.
- Most dialogs share the same three-part structure: an input variable (which upstream result to use), the node options (has header, delimiter, sort column, filter conditions, etc.), and an output variable name.
- Fields are validated with Zod. If something required is missing you'll see an inline message and the Save Configuration button stays disabled until the form is valid.
- Click Save Configuration — settings are persisted automatically in your browser's IndexedDB.
Screenshot placeholder
Screenshot placeholder
Variables
Variables are how data travels between nodes. Every node that produces data writes its result to a named variable. The next node picks that name from a dropdown as its input. Think of it as a shared bag of results that grows as the workflow runs.
- When you configure Upload File, you give the file a name like
data. Downstream nodes can reference it by selectingdatain their input-variable dropdown. - CSV Parse reads
dataand writes a new variable, e.g.parsedData. - CSV Filter reads
parsedDataand writesfilteredData, and so on down the chain. - The output variable name is suggested automatically — when you open the dialog you'll see an auto badge next to the field, showing the suggested name. Simply leave it or type over it to rename. The suggestion is pre-filled — no button needed.
- The description below the output name field shows a live preview:
{{filteredData}}updates as you type so you can see exactly what downstream nodes will reference. - Column fields (those asking for a header name) autocomplete from the upstream file's schema — once a file is parsed you'll see the real column names as suggestions.
| Field | What it means | Example |
|---|---|---|
| Input variable | Which upstream result this node should read | parsedData |
| Output variable name | Names this node's result for nodes further down | filteredData |
| {{ variable }} | A live preview hint shown in dialog descriptions | {{filteredData}} |
| Column field | A column header from the upstream file (autocompletes) | email, age |
Name variables for what they hold (cleanContacts, over30) rather than the node type. When a workflow has ten nodes, descriptive names make the input dropdowns far easier to read.
Screenshot placeholder
Screenshot placeholder
Run & read results
- Click Run in the editor toolbar. AutoPilot calculates the correct execution order automatically (topological sort) and runs each node in sequence.
- A progress panel opens on the right. Node indicators turn blue while running and green when done; large files show a live progress bar.
- If a node fails it turns red with an error message, and the run stops there so you can fix the configuration and re-run.
- When the run finishes, open the execution panel and click any node's output row to preview it. Hit Export to download the data as CSV, Excel (.xlsx), TXT, or PDF. Toggle "Download in segments" to split very large results into multiple files — either by specifying the number of files or the target rows per file.
- Every run is saved under Executions in the sidebar — open any past run to see per-node timing, a paginated dataset preview, and to re-download results at any time.
Screenshot placeholder
Screenshot placeholder
Worked example
Filter a contact list down to people over 30 and export it. Three nodes, end to end.
Upload File
- Drop in
- your contacts.csv file
- Output variable
- data
CSV Parse
- Input variable
- data
- Has header
- on
- Delimiter
- auto-detect
- Output variable
- parsedData
CSV Filter
- Input variable
- parsedData
- Condition
- age > 30
- Logic
- AND
- Output variable
- filteredData
filteredData from the execution panel — pick CSV or Excel and optionally split into segments.Node reference
All 21 nodes available in the canvas, grouped by category. Derived from the live node registry — no phantom nodes.
Triggers & input
Manual Trigger
Start the workflow when you click Run.
Upload File
Select a local .csv, .txt, or PDF file and bring it into the workflow.
CSV transforms
CSV Parse
Read a raw file into structured rows and columns, with schema inference.
CSV Filter
Keep only rows matching one or more conditions (12 operators, AND/OR logic).
CSV Sort
Order rows by one or more columns. Uses external merge sort for huge files.
CSV Join
Merge two datasets on a shared key (inner, left, right, full, or cross join).
CSV Aggregate
Group rows by columns and compute totals, counts, averages, min/max.
Detect Duplicates
Find duplicate rows by a key — outputs unique rows and duplicates separately.
CSV Compare
Diff two datasets: produces added, removed, changed, common, and schema_diff sets.
Consecutive Sequence Analyzer
Detect gaps or runs in a numeric or date column (e.g. missing IDs, time gaps).
CSV Transform
Apply conditional find-and-replace rules: replace, clear, delete, or set values.
Column Transform
Apply unconditional ops to a column: trim, case change, regex replace, math.
CSV Restructure
Reorder, drop, or add computed columns to rebuild the output schema.
CSV Generate
Produce a synthetic dataset for testing workflows without real data.
PDF operations
PDF Extract Text
Pull all text from a PDF, page by page.
PDF Extract Tables
Detect tables in a PDF and convert them into structured rows.
PDF Split
Split a multi-page PDF into separate page documents.
PDF Merge
Combine multiple PDFs into one document.
PDF Fill Form
Write values into PDF AcroForm fields.
PDF Generate
Build a new PDF document from text and data.
PDF Sign
Apply a digital signature to a PDF.
Exporting results. There is no export node — run the workflow, then export any node's output straight from the execution panel as CSV, Excel, TXT, or PDF, with segment options for large datasets.
Build your first workflow
It takes about a minute. Add a trigger, drop in a file, chain a couple of nodes, and hit Run.
Open the editor