Neuron Workflows
Neuron

Documentation

Get Started

Documents

Tables, docs and slides that belong to a workflow. Neurons read tables in GET and write to them from SEND.

Documents are the tables, docs and slides that belong to a workflow. They live in the Docs section of the canvas's left rail. Neurons can read a table in GET and write rows to a table from SEND, so one table can carry data from neuron to neuron and from run to run.

Create a document

  1. Open Docs in the canvas's left rail.
  2. Click New document.
  3. Choose Table, Doc or Slides.

The new document appears in the Docs list, for example as "Untitled table", and opens in its editor in a new browser tab: a spreadsheet for a table, a page for a doc, or a slide deck for slides.

Import a CSV as a table

  1. Open Docs in the canvas's left rail.
  2. Click Import.
  3. Pick a CSV file. It becomes a new table in this workflow.

Open, duplicate or delete a document

In the Docs section, open a document's Document options menu (the three dots) and choose Open, Duplicate or Delete. Delete asks you to confirm with Delete again.

Read a table in a neuron

  1. In the neuron's GET, add an input and set its type to Table.
  2. Click Pick a table and choose the table, or Upload a CSV to create a new one.
  3. Click Open editor to view or change the table.

On each run, the AI reads the table's rows along with the neuron's other inputs.

Run once per row

With Run once per row on for a table input, the neuron runs once for each row of the table, from Start row for Number of rows, instead of reading the table in one go.

  • A run carries on if the server restarts. A row that was cut off by a restart is undone and run again once.
  • Rows run a few at a time. The run bar shows how many rows have finished.
  • A row that fails doesn't stop the others. When the run ends, a message tells you which rows ran and how many were done or failed.
  • The next step starts once, when all the rows are done. Neurons connected after this one don't start for each row.
  • Click Stop to end the run. Rows already in progress finish, and the message says which row to start from to carry on. If the account runs out of credits, the neuron shows the error "Stopped: not enough credits" and the run ends.

While rows are running, starting the neuron again is refused, with a message saying that it is still running.

Write rows to a table from a neuron

  1. In the neuron's MAKE, choose Table.
  2. In SEND, turn on Document.
  3. Under Write to table, choose the table. With no table picked, a new table is created on the first run.
  4. Under Columns to fill, tick the columns the neuron should fill, or click All.

Each run adds one row into the chosen columns.

Changes a run makes can't be undone. History lists your own edits.

Replace the rows on every run

By default each run adds its rows to the ones already in the table, so a table that is filled on a schedule keeps growing. To keep only the latest result, set Write mode to Replace all rows on the table's Document row in SEND. Write mode shows for a table you pick or one that is made on the first run, not for a table made new on every run.

  • When the run finishes, the table's rows are swapped for the rows the run wrote. The table's columns stay, and any column the run adds is kept.
  • A failed or stopped run leaves the table as it was. A run that wrote no rows leaves it as it was too.
  • With Run once per row, the swap happens when the whole pass ends, and it uses the rows of the rows that succeeded. If none succeeded, the table is left as it was.
  • A neuron that replaces rows can only add rows. Changing or deleting existing rows in that table is refused with a message.
  • The old rows aren't kept anywhere, so they can't be brought back afterwards.

Fixed table columns

When SEND writes to a table you made, the result uses that table's column names, so a later neuron or your own systems can read the columns by a known name. Set up the table first: create it in Docs, name its columns, then pick it under Write to table. With no table picked, the AI chooses the column names itself on the first run.

Column names and lists in a table result

A table result shows its column names and cells exactly as the neuron produced them. The app doesn't rename columns or reformat cells, so total_amount stays total_amount, and a cell that holds a list shows as a list in brackets, for example ["Pasta","Broccoli"].

To make a table easier to read:

  • Name the columns yourself. Create a table in Docs with the column names you want people to see, such as "Total Amount", and pick it under Write to table. Every run then uses those names, and so does every User of your Agent.
  • Or ask in DO. With no table picked, say in the DO instructions which column names to use and how to write each cell, for example "one ingredient list per cell, separated by commas".

Users of your Agent can't change the column names. They see the names you set up.

Documents and Memory

Docs hold tables, docs and slides. A PDF, image or audio file that several runs should read belongs in Memory: use Add document in the Memory section. A table, doc or slides can also be added to Memory with From Documents, and stays in sync. See Memory.

Limits

  • CSV import: up to 25 MB per file.
  • Rows the AI reads: the first 500 rows of a table on each run.

Common problems

Only CSV files can be imported

Docs Import and table inputs take CSV files only. Excel files aren't supported: save the sheet as CSV first.

Save the workflow before uploading a table

A CSV upload in GET needs a saved workflow. Wait for the top bar to show Saved, then upload again.

Document is not available in SEND

The Document destination needs a table result. In MAKE, choose Table first.

The AI ignores rows at the end of a large table

The AI reads only the first rows of a large table on each run (see Limits). Split the table, or filter it down before the neuron reads it.