Docs
A folder tree the agent reads, and a config file it obeys.
What it does
Documents live in a folder tree with real uploads: PDFs, CSVs and video transcripts are extracted, scrubbed of personal data and staged before they become part of what an agent can see. Each folder carries a plain-text config file whose settings cascade down the tree, so behaviour and grounding are defined next to the material they apply to rather than in a distant admin screen.
Why it matters
Configuration that lives in a database is configuration nobody can review. Putting an agent's scope, tone and grounding in a file inside the folder it governs makes the whole setup diff-able, explainable and reversible.
How it works
Config cascades down the folder tree
A setting on a parent folder applies to everything beneath it unless a child overrides it, the same model as directory-scoped config in a codebase.
Uploads are staged before they are live
Extracted content goes through a draft and test stage, so publishing new grounding material is a deliberate step rather than a side effect of a file drop.
Personal data is scrubbed on extraction
Extraction runs a sanitisation pass, so a CV dropped into a folder does not silently become retrievable in full.
Questions
- What file types can it read?
- PDFs, CSVs and spreadsheet exports, plain text and markdown, and video transcripts. Anything outside that is stored but not extracted.
- Where does an agent's behaviour get configured?
- In a config file inside the folder itself, with settings cascading down the tree. It is editable in the product and it is plain text.
The rest of the bag
Your agent has its own inbox, not a share of yours.
Inbound arrives by webhook from an email provider. We do not run our own MX or SMTP servers.
Package
Export, share and install agents as portable archives.
Export, import, handoff links and showcase all work. There is no marketplace, no package versioning, and no signed packages.
Memory
Grounded retrieval over your own material, with receipts.
This is retrieval, not persistent agent memory. Vector grounding is code-complete; the vector deployment is still pending.
That was step 5 of 6: the agent consults its bag. Next, tasks, delegation edges, decisions and artifacts persist as rows you can replay, and the spend is already accounted for.