watasu
Agent-native encrypted intake rail

Publish a machine-readable request contract, receive encrypted submissions, and keep payload custody outside watasu.

Start here

Give this to your service-side agent.

Paste this as-is into your coding or operations agent. The agent should ask one compact four-slot question, then summarize and wait for confirmation before it publishes anything.

I want to use watasu to collect information from people through encrypted intake.
Use https://docs.watasu.ai/llms.txt and
https://docs.watasu.ai/operator-prompts.md only as watasu reference docs.
Do not plan web research, SEO, or llms.txt setup for my site.
Ask one compact setup question that covers exactly these slots: what to collect
and from whom, destination, purpose, and retention.
Agent-mediated handoffmetadata-only
01Human asks

A person starts from a natural-language request, not developer setup.

02Agent reads

Docs, llms files, schemas, and Agent Cards ground the workflow.

03watasu relays

Encrypted submissions are validated without plaintext custody.

04Receiver acts

The receiver owns decryption, destination writes, and obligations.

Machine-readable intake

Request definitions, JSON Schema, Agent Cards, and A2A-compatible submit routes describe what is needed before a user-side agent sends data.

No payload custody

watasu validates and forwards encrypted envelopes without receiving, decrypting, logging, or retaining plaintext payload values.

AI-readable docs

This site builds llms.txt and llms-full.txt so agents can discover the product, boundaries, and public surfaces.

Visible receiver output

A good trial starts with a natural-language request and ends with a receiver-owned CSV or Sheet row, while watasu keeps plaintext payload custody out of scope.