hurozo Attend

Worker Tools

Manage worker

Tune the role and tools for this agency teammate. Graph wiring stays internal.

Tools

Loading...

Worker View

No tools selected
Team worker Untitled Agent Describe what this agent should do. HurozoAgent

Worker Chat

Describe the worker you want to add to this team, or what you want to change.
Draft JSON 
{}

Teams

Teams are managed from Agency.

Connectors

Connectors

Connect services for the current agency

Loading connectors…

Agency

Team workspace

Planning

Filters

Build

Runs

Execution activity

Runs

Inspect Worker work, tool calls, reasoning summaries, and failures.

Select a run to inspect its activity.

Files

Agency files

    Documentation

    Contact Us

    New message

    To: hi@hurozo.com

    Hurozo CLI

    Terminal-first agent work

    Hurozo CLI

    The same Hurozo agent runtime, model routes, approvals, and connected tools from your shell.

    Install with Homebrew 
    brew tap hurozo/hurozo-cli
brew install hurozo-cli

    View latest GitHub release

    Hurozo CLI running in a terminal

    Model routing

    Switch between Hurozo, Gemini, Opus, and ChatGPT-backed routes when your account is configured for them.

    Approvals

    Review tool permissions from the terminal and keep remembered decisions scoped to the exact operation.

    Second opinions

    Use model arbitration to ask another available route for critique, checks, or a different perspective.

    Connected tools

    Use the same account-backed connectors and skills available in Hurozo's desktop and WebCLI experiences.

    First run

    After installation, run hurozo. The CLI walks you through account authentication and any model-specific sign-in or secret setup that your selected route requires.

    Hurozo SDK

    Python agent invocation

    Hurozo SDK

    Invoke saved Hurozo agents from Python using the same API tokens, inputs, outputs, and runtime routing used by Agent Builder.

    Install 
    pip install hurozo
    getting_started.pyPython
    import json
import os

from hurozo import Agent

os.environ["HUROZO_API_TOKEN"] = "YOUR_API_TOKEN"
agent = Agent("sentiment-analyser")
inputs = {
    "prompt": "Analyze sentiment and return JSON. Text:",
    "input": "I am very happy!",
}

result = agent.run(inputs)
print(json.dumps(result, indent=2))

    Agent lookup

    Use an agent name, saved agent id, or agent UUID. The SDK resolves the correct execution target.

    Structured inputs

    Pass a Python dictionary matching the API input keys exposed by the saved workflow.

    Hosted runtime

    Runs against Hurozo's execution endpoint, including model routing, tools, outputs, and usage accounting.

    Token setup

    Create an API token from Account settings -> Manage API Tokens, then set it as HUROZO_API_TOKEN before running scripts.

    Ask Attend

    Ask us anything.

    Every answer comes from our own canon, on the channel you choose, and a person is always one tap away. This is Hurozo's real support, running on Attend.

    From your truthChat, WhatsApp, voiceA person, one tap away
    Common questions

    Read any answer, then keep asking.

    Each one opens a live conversation with the crew, continued from right where you stopped reading.

    How it works
    How is this different from a chatbot we could build?

    Most bots are rented black boxes. You cannot see what they said, prove it, or stop them walling a customer off.

    Attend is a crew you own. Every reply is drafted from your truth, held at your gate, logged, and a person is always one tap away.

    ✓own it, prove it · positioning
    Can it go off brand?

    It answers from your canon, not from the open internet, so it stays on your brand and on your facts.

    When your canon has no answer, it does not guess. It says so and holds the ticket for a person.

    ✓grounded in canon · canon + the gate
    Does it work on WhatsApp and phone calls?

    One crew answers across web chat, WhatsApp, and voice, from the same canon, in the same voice.

    The conversation is one thread, so a customer can start on chat and continue on WhatsApp without repeating themselves.

    ✓one thread, any channel · channels
    Trust and data
    Where is our data hosted?

    Your data stays in the EU, and so does the reasoning, on infrastructure you control.

    Every answer traces back to a line in your own canon, and every action is logged and held.

    ✓from our truth · residency + canon
    How do we prove what it answered?

    Every draft, edit, hold, and send is logged and mapped to the EU AI Act, Articles 12, 13 and 14.

    So you can show exactly what was answered, from what source, and who approved it.

    ✓logged and held · audit trail
    Which AI model does it use?

    You choose the model, and you can switch or fail over between providers without rebuilding anything.

    Nothing is locked to one vendor, and the record stays provider-neutral.

    ✓your model · model router
    Cost
    What does it cost?

    You pay for what it runs, not per seat, so it does not get more expensive every time you add a teammate.

    The exact model depends on your volume, so I would rather size it with you than guess. Book a demo and we will walk your numbers.

    ✓usage, not per seat · pricing model

    A working demo. Answers come from Hurozo's own canon, the way our real support runs on Attend. Ask a follow-up and the conversation opens in the support window, right where you left off. WhatsApp and voice are real routes: they hand the conversation to the actual app or a live call, carrying your context. Nothing you type here leaves this page.

    The new reality of service

    Every answer on this page is a live conversation waiting to happen.

    Book a demo Ask us something →
    You own it Answers from your truth Chat, WhatsApp, voice, one thread A person is always reachable EU-resident
    Questions? Ask our crew. A person is one tap away.
    ×