Skip to main content
An EigenPal project usually moves through five steps: build a workflow, evaluate it, deploy it, inspect real runs, and add failures back to the dataset. The example below extracts a bank statement, but the same process applies to other document and data workflows.

​
Build

Create a workflow: a directed graph of typed steps that parse, extract, transform, and act on data. For open-ended tasks that do not fit a fixed graph, use a Git-backed agent. In both cases, the definition is stored in files you can read, diff, and version.

​
Evaluate

Attach a dataset of example documents with their expected output, and evaluators that define what correct means for this document type. Run an experiment across the whole dataset and tune the workflow until it clears a pass threshold.

​
Deploy

Run the workflow from the dashboard, CLI, SDKs, or API. A request returns a run id; workers execute the run asynchronously and store inputs, outputs, traces, and model versions. Experiments store evaluator scores.

​
Observe

Use the run trace to inspect each step, its inputs, and its output. This is where you debug unexpected results and find gaps in the dataset.

​
Improve

When a real document exposes a wrong answer, add that input and the corrected output to the evaluation dataset. Re-run the experiment and compare the new version before shipping. That turns production issues into regression tests. The full flow is covered in Eval-first development.