For underwriting work where the documents are sensitive (rent rolls, P&Ls, OMs under NDA), this page documents the infrastructure path your uploads travel.
At upload
When you drag a document into a property's Documents section:
- Your browser uploads the file straight to Relm's servers over TLS 1.2+.
- The file is streamed directly to encrypted object storage in our US region. It's encrypted at rest with AES-256-GCM.
- A reference (URL + metadata) is written to our application database.
The file does not transit a third-party-hosted intermediate during upload — it goes from your browser to our object storage via our servers.
During indexing
After the upload completes, the indexing pipeline:
- Reads the file from object storage.
- Extracts text — scanned PDFs go through OCR (text recognition), which runs on our own processing servers.
- Chunks the text into searchable passages.
- Embeds each chunk via a production embedding API (no training, contractual).
- Writes the embeddings into our vector index, scoped to your organization.
The original file stays in object storage.
During chat / agent work
When a chat query or agent run needs a document's content:
- The agent retrieves relevant chunks from the vector index.
- Chunks are passed to a frontier model provider along with your query.
- The model's response is streamed back to your browser.
The provider sees only the chunks needed to answer the query, not your entire document corpus.
At deletion
When you delete a document:
- It's removed from the property's Documents section.
- Its chunks are removed from the vector index, so chat and agents can no longer retrieve it.
- The stored file and its metadata are archived, not erased — they stay in our systems.
To have an archived document permanently erased, email legal@relm.ai.
Cross-organization isolation
- Object-storage paths are organization-scoped.
- Vector-index namespaces are per-organization.
- Application DB queries are scoped via the org-id filter at the API layer.
There's no path for one organization's chat / agent run to retrieve another organization's document chunks.
What we don't do
- We don't ship your documents to any third-party indexer or search provider beyond our own vector index.
- We don't allow contractor / personal use of your data.
- We don't add your documents to any shared dataset or benchmark. Our privacy policy does allow aggregated, de-identified information that can't identify you to be used for research, benchmarking, and industry reporting.