Attend 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.

    Product advice · a live case

    “Will these fit?” Answered from your truth, before they buy.

    The question that fills your queue before anyone buys. Attend answers it from your own truth and live stock, in your voice, and hands the ones it cannot stand behind to a person.

    See it work → Book a demo
    New message · web chat 09:14
    Will this fit our space? Our alcove is about 2 metres wide.
    Attend is reading it
    What answering it by hand costs you

    Right now, every one of these is answered from scratch.

    Your team answers each one by hand, tabbing between the size chart, the product record, and live stock. Slow, and different depending on who is on the desk.

    ~15%
    of e-commerce support contacts are pre-sale product and fit questions, and more in fit-heavy categories.
    HiveDesk / Freshworks · 2025
    53%
    of apparel returns come down to size and fit. In furniture: “it didn’t fit the space.”
    Coresight · 2023
    ~3x
    more likely to buy when a shopper can get a fast, accurate answer before they buy.
    Live-chat CX benchmarks · 2025

    External research, cited above.

    How the crew answers this one

    It answers from your truth, and stops on the one it can’t.

    Attend · product adviceobserve mode · sample data
    QWill this fit our space? Our alcove is about 2 metres wide.
    The 3-seater is 198cm wide, so it fits a 2 metre alcove with a centimetre each side. If the wall is tight, the 2-seater at 158cm gives more room.
    from your canonProduct guide · Dimensions
    QDo you have the desk in oak, ready to ship?
    Yes, the oak finish is in stock and ready to dispatch. Want me to reserve one while you decide?
    canon + live stockProduct and stock · live
    QIs this chair rated for all-day, everyday office use?
    not in your canonIt will not promise a durability rating your canon does not state. Held for a person.

    Sample data, in observe mode. On your own tickets, every answer is cited to its source, and the one it cannot stand behind is held for a person.

    The same question, answered four ways

    Product advice is easy to answer fast, and easy to answer wrong.

    A fit tool
    True FitFit Analytics
    Good at one thing: a fit guess on the product page. It cannot see your live stock, it is not your voice, and it cannot answer anything else.
    A general chatbot
    off-the-shelf AI
    Fast to set up. It answers from the open web, makes things up, and sounds nothing like you. One wrong answer is public.
    By hand
    your team + macros
    Real judgment, real warmth. But it is slow, every agent answers differently, and the know-how leaves when they do.
    Attend, on this job
    Answers from your own product truth and live stock, in your voice. When it cannot be sure, a person steps in. You own it, and every answer is yours to check.
    What it grounds in for this job

    Two sources, and your channels. No open web, ever.

    Your canonFit and product truth Product and stockLive stock and lead time, from your ERP Your channelsWeb chat, WhatsApp, email

    Attend connects to the systems you already run. See the integrations →

    Proof

    Every reply, and the line behind it, is yours to inspect.

    from your canonsample log · TCK-40912 · 09:14 CET
    Cited: Product guide · Dimensions, checked against live stock. Held cases are logged too.
    pulled from your canoncited the linenothing from the open weblogged and replayable

    Every answer, and every hold, is one record you can open, replay, and export. Designed around the EU AI Act, on a source you own.

    You own it EU AI Act, by design EU residency on our roadmap A person is always reachable
    Own the answer your customers hear

    Answer “will these fit?” the same way, every time.

    From your own truth, in your voice, with the source shown, and a person on the hard ones.

    Book a demoSee it work →

    The pilot is risk-free on the investment. If it does not hit the KPIs you agree, you do not pay for the sprint.

    See how the first weeks work: First steps →