Puestario
Security & dataSee live agentsSign up for a call
Menu

INSIDE YOUR AGENT

Permissions

The agent checks who is asking, where they are asking, and what they may use.

A name is not a key.

Example · not a live agent
Ana · approved staff · private chat

“Read my approved sales sheet.”

  1. 1Ana is on the approved list.
  2. 2Her record allows this sales range.
  3. 3She is asking to read it.

Allowed to ask Sheets.

Only that range is requested. The app still needs a working connection.

What else should I know?

Like checking a name at the school gate. A name in a message is not an ID.

  • Founders manage the agent from verified private chats.
  • Staff use only the data they are allowed to use.
  • Groups have their own approved people and data.

USER.md holds company language and time zone. Staff access is stored in control.json.

Staff

Approved app data, own private notes and own private reminders.

Cannot add staff, change company settings or read someone else’s private notes.

Founders

Either verified founder can manage people and groups from private chat.

Company and app changes need an open Setup window. Client owners are not automatically founder admins.

Installer

At the Mac: install, connect accounts, run checks and record evidence.

Being called “installer” in chat does not grant founder access. Local machine access is a separate responsibility.

Group

Approved members can use data explicitly allowed in this group.

No private notes. People in the real WhatsApp group can see messages; membership needs a human review.

The parts, in plain language

Use this overview to understand the whole agent before exploring the interactive examples. It describes the public pilot kit; custom agents such as Emily have their own implementation and permissions.

Instructions

These seven files tell the AI its name, how to speak, and how to do its job.

Like a school handbook. It explains the way to do things.

  • Name and speaking style.
  • Language, time zone and work instructions.
  • How to ask for tools, notes and reminders.

Instructions guide the AI. The permission checker decides which actions are allowed.

Explore this part ↗

Permissions

The agent checks who is asking, where they are asking, and what they may use.

Like checking a name at the school gate. A name in a message is not an ID.

  • Founders manage the agent from verified private chats.
  • Staff use only the data they are allowed to use.
  • Groups have their own approved people and data.

USER.md holds company language and time zone. Staff access is stored in control.json.

Explore this part ↗

Tools

The AI has one protected tool menu. It can ask for approved actions from that menu.

Like a pencil case. You can only use the tools that are inside.

  • Read allowed app data.
  • Change an exact Sheets range when allowed.
  • Use notes, reminders and founder controls.

This release does not give staff general computer control, web browsing, email sending or money-moving tools.

Explore this part ↗

Private notes

A person can ask the agent to save a private note and read it back in their own private chat.

Like a personal notebook with your name on it.

  • Each person has their own notes.
  • Notes are saved in the company record.
  • Private notes stay out of shared instructions.

Saving a preference does not guarantee the model uses it every time. Full staff profiles and searchable company knowledge are future work.

Explore this part ↗

Reminders

The agent saves a job, waits for its time, checks access again, and tries to send it.

Like an alarm clock with a note attached.

  • One date, a daily time, or a repeating interval.
  • Staff reminders go to their own private chat.
  • A founder may schedule an approved shared report.

The Mac and connection must be running. A report uses one approved data source. Sending does not prove someone read it.

Explore this part ↗

Recovery

Puestario checks the agent, keeps records, and can make an encrypted recovery copy.

Like a checkup and a spare copy of your important work.

  • Logs help explain what happened.
  • Real checks are needed before handover.
  • A restored agent starts paused, with jobs off.

The gateway must be stopped for a backup. The encrypted copy goes outside the company folder; its key stays separate. Backups are not automatically scheduled.

Explore this part ↗

WhatsApp

Your message reaches OpenClaw through the linked WhatsApp account. The real sender and chat are checked.

Like the front door for your messages.

  • Dedicated linked account.
  • Approved private chats or groups.
  • Text replies in this release.

Telegram backup and voice/media handling are not built into this release. The live phone connection still needs pilot testing.

Explore this part ↗

Online AI

The online AI reads the request and instructions. It chooses what action to ask the protected tools to do.

Like a reader who understands your request and picks a tool.

  • A selected model and optional fallback models.
  • Messages and approved app results may go to the provider.
  • The AI cannot grant itself access.

A Mac mini does not make the whole AI local. Provider use has its own costs. This kit does not enforce a combined vendor spending cap.

Explore this part ↗

OpenClaw

OpenClaw runs on the Mac. Puestario plugs in its permission checks, tools and clock.

Like the engine that keeps the parts working together.

  • Receives messages and calls the selected AI.
  • Loads the two Puestario plugins.
  • Uses a separate company profile.

Pinned OpenClaw: 2026.5.27. Codex and Claude Code are optional operator tools; they are not the running agent or its staff tools.

Explore this part ↗

Version and limits

This guide documents a specific public pilot release. Installation and real-account testing are still required. Voice handling and all workflows from existing custom agents are not included in this release.

0.2.0-pilot · GitHub ↗