Skip to navigation
Agentic Orchestrator

Code Execution

The Agentic Orchestrator runs Python in a sandbox to compute exact results over data and files, or to generate a file for the user.
View as Markdown
Controlled Availability

The Agentic Orchestrator is in Controlled Availability and comes to your Enterprise Assistant in Q1 2027. Capabilities, limits, and interface labels described here may change before general availability. To request access, contact your Moveworks account team.

When a request needs exact math, a data transformation, or a generated file, the Orchestrator writes Python and runs it in an isolated sandbox. File contents are never pasted into the prompt: the model names the files a run needs, and the sandbox stages them as inputs.

alt [Result is data] [Result is a file] Message with an uploaded file Code, values, and named input files JSON-serializable result Answer in the conversation One file from OUTPUT_DIR Artifact card Inputs staged in INPUT_DIR User Orchestrator Python sandbox

How It Works

  • Two outcomes. The code defines main(variables) and either returns JSON-serializable data to the conversation or writes exactly one file to OUTPUT_DIR, which becomes an artifact.
  • Explicit inputs. Code sees only the values and files the model passes in: user uploads, earlier artifacts, or Skill resources. Skill resources reach only file-producing runs.
  • Uploads. Users attach files in the EmployeeWorks web app. The model sees a list of them and picks a method: code for exact computation, or the File Processor plugin for what a document says (enabled per organization).
  • Fixed libraries. The Python standard library plus Beautiful Soup, NLTK, NumPy, OpenPyXL, pandas, Pillow, Plotly, PyCryptodomeX, python-docx, python-gnupg, python-pptx, ReportLab, scikit-learn, and seaborn. Code can’t install packages.
  • Stateless and offline. No network access, and nothing carries over between runs. To chain steps, the Orchestrator saves an intermediate artifact and passes it to the next run.

Limits

LimitValue
LanguagePython only
Run timeAbout 90 seconds per run
Input files5 per run, up to 100 MB each
OutputOne file per file-producing run, up to 25 MiB
Uploads5 files per message, 25 MiB each
Upload typespptx, xlsx, docx, pdf, csv, png, jpg, jpeg, txt, md, json, html
Upload retention1 day

Configure

Code execution needs no setup. File-producing runs require artifacts, which are enabled per organization. To steer the model, say so in the instructions, for example: “Compute any totals from an uploaded spreadsheet in code.”