DocsGPT agents turn company documents into DOCX, PPTX, XLSX, PDF and HTML files: they analyse data in a sandbox, render the file and keep every version. File bytes stay on the server and never pass through the model.
pptx · docx · xlsx · pdf · html · files from this answer · versions · sandboxed python
Last updated:
An artifact is a file an agent produces: a presentation, a Word document, a spreadsheet, a PDF, an HTML page, an image or a data file. Each answer shows the files it made as cards, with Show all when there are more, and opens Files from this answer: the files grouped into Documents, Images, Data and Other files, each with a preview and its versions. Download a file or ask for changes; every edit adds a version, and any earlier version can be restored.
Word documents come out ready to send, with headings, numbered clauses and tables whose header row repeats on every page. API clients get a download link for every file an answer made. In workflows, artifacts appear in the run view and pass from one step to the next by reference. The model works with text and references, never the file bytes, and per-user quotas keep storage in check.
files from this answer · documents · images · data · versions · restore · api downloads
Your attached files and knowledge go to the agent, which reads them and plans the output. It analyses data with Python in the sandbox through the Code Executor, and the Artifact tool renders the file from a structured spec. Every edit adds a version that can be restored. File bytes stay on the server; the model sees text, run summaries and references.
The Code Executor runs Python in a sandbox session for the conversation or workflow run, about 60 seconds per run; longer jobs continue in the background and post the result to the chat. Every file it writes becomes an artifact.
The sandbox comes ready for office work: headless LibreOffice and Chromium, OCR, ffmpeg and Node.js, with fonts for Chinese, Japanese, Korean and Arabic. An agent can convert office files, print HTML to PDF and take screenshots of a page, and install any other package from the code.
Attach a spreadsheet and the agent can open it with pandas and chart it; the chart is shown back to vision models so they can read what they drew. Secrets are stripped from the sandbox environment, its network access can be locked down with the egress policy, and you can require approval before each run.
Code Executor
Three tools do the work: one writes, one runs and one reads. They are opt-in per agent, and an agent or a workflow step can use them alone or together. Answers can also draw Mermaid diagrams right in the chat.
artifact · code executor · read document · mermaid in chat
Write
Builds slide decks, Word documents, spreadsheets, PDFs and HTML pages from a structured spec, then edits or rewrites them on request, each change a new version. Word documents keep their structure: headings, numbered clauses and tables.
pptx · docx · xlsx · pdf · html · create · edit · rewrite
Run
Runs Python in the sandbox to clean data, compute and chart. Every file the code writes becomes a downloadable artifact.
python · pandas · matplotlib · files → artifacts
Read
Parses an uploaded or produced file into text, Markdown, structured JSON with tables, or chunks, so a workflow step can work on its contents.
pdf · docx · pptx · xlsx → text | markdown | json
Choose the self-hosted sandbox runner and code execution, file rendering and artifact storage all run inside your network. Daytona is a managed cloud sandbox for multi-tenant workloads; it is not for air-gapped estates.
Four deployment postures, one code base. Compare deployment options →
Inside your network
managed · on-premises · air-gapped
Cloud
Arc53 operates the sandbox and the artifact store.
Air-gapped
Self-hosted sandbox runner only, inside your network. No Daytona, no external network.
6+ h → under 5 min
IP application drafting: 6+ hours to under 5 minutes per application, with lawyer review as the final step.
Source: Balt Alnoor
Next: Code nodes in workflows · approval before a tool runs · how documents get in · legal drafting · deployment options · pricing
A 30-minute demo on your use case, or a free on-premises review with an engineer.
Can we use analytics cookies? They show us which pages lead people to sign up, and connect this visit to your DocsGPT account if you create one. If you say no, we still count page views, but store nothing on your device. Privacy Policy