Skip to content

Workers

AI workers that do the revenue work, reviewed by you.

A worker is a colleague that runs on the OS. It has a job, the triggers that start it, the tools it may use and a review step you control. Taylor and Parker come with every workspace. Custom workers take any role you describe.

AI workers are the people-shaped part of Heliyos, the AI-native OS for revenue teams. Each worker is a role, not a chatbot: Taylor is the account executive that finishes tasks, Parker is the platform admin that keeps records current, and custom workers take any job you describe in plain words. Workers run from the same customer memory the team uses, show up as assignees on the same task cards, and every action they take shows its evidence. Important actions wait in Reviews for a person. Teams deploy a worker in one click and hand off more as trust grows.

Included

Two workers, ready on day one

Taylor's avatar

Taylor

Account Executive · worker
Included

Works every task on the board like a seasoned seller. It reads the brief and the account memory, then writes the email, books the meeting or produces the document the task asks for, and you approve before anything reaches a customer.

  • Drafts the follow-up email after a call, in your voice, with the proposal attached.
  • Finds a slot on your calendar, holds it and sends the invite once you approve.
  • Writes the proposal, one-pager or deck the deal needs, from your pricing and docs.
Parker's avatar

Parker

Platform Admin · worker
Included

Keeps the customer memory true after every email and meeting. It rewrites the account summary, updates the people and deal fields, moves the stage only when the evidence supports it, and creates the one task that should follow, for a person or Taylor.

  • A meeting ends: the summary, the attendees’ roles and the next step are on the account in minutes.
  • A prospect replies: the thread is summarised, the deal stage is reconsidered, Taylor gets a task.
  • A new contact appears in a thread: the person is created, enriched and linked, no duplicates.

Custom workers

Need a third pair of hands? Describe the job.

A custom worker is stored and runs on the OS exactly like Taylor and Parker: same memory, same tools, same review step. Write the role in plain words and deploy it.

How custom workers work
  1. 01Name the role"Renewals Manager". What it owns, in two sentences.
  2. 02Pick triggers and toolsEvents, a schedule or a mention. Only the tools the job needs.
  3. 03Set what needs reviewStart with everything reviewed. Hand off more as trust grows.

Workers work together

A team, with handoffs.

Workers are not isolated bots. They hand work to each other, stop and hand it to a person when it matters, and share one memory and one knowledge base, so the work moves without anyone re-explaining the account.

Parker's avatar Parkerread the QBR transcript and created the taskTaylor's avatar Taylorwrote the proposal and the cover emailNeeds review · Sohamapproves, and it sends
  • Workers hand work to each other

    Parker reads a meeting and creates the follow-up task; Taylor picks it up, does the work and reports back what Parker should change on the account. The handoff is visible in the thread: "Parker handed off to Taylor".

  • Workers hand work to a person

    When an action matches a review rule, or a worker is unsure, it stops and hands the decision to the account owner in Reviews, with the evidence and its open questions. A person approves, edits or answers, and the run continues.

  • They share one memory and one knowledge base

    Every worker reads the same account memory and the same organisation knowledge: your pricing, docs, custom fields and files. What one worker learns on an account, the next one knows.

  • You can talk to them, and they talk to each other

    Mention @Taylor or @Parker in chat or on a task and they reply with what they did and why. On a task, workers talk among themselves to split the steps, and the conversation stays on the task for you to read.

One system

What every worker shares

  • One customer memory

    Workers read and write the same companies, people, deals, notes and conversations the team does. Nothing lives in a side database.

  • Same surfaces as people

    A worker is an assignee on a task, a participant in a thread, a name on a change. There is no separate worker dashboard to maintain.

  • Evidence on every action

    Each run shows its steps, the sources it used and the reasoning, so a person can check any decision in seconds.

  • Review built in

    Rules decide which actions wait for approval. Start with everything reviewed and loosen per worker and per action.

  • Triggers and tools, explicit

    A worker starts on named events, a schedule or a mention, and may only use the tools its job lists.

  • Deploy in one click

    Taylor and Parker are included. A custom worker is a role description, a trigger list and a review rule. No code.

How it works

How a run works

  1. 01

    Something happens

    An email arrives, a meeting ends, a task is created, a signal lands, or someone mentions the worker.

  2. 02

    The worker runs

    It reads the account memory and the trigger, plans the steps, and works them with the tools it is allowed.

  3. 03

    Outputs wait or land

    Actions that match a review rule wait in Reviews with evidence. The rest land on the record and the timeline.

  4. 04

    The worker reports

    A plain-language result, what changed, open questions and a confidence, on the task and in the thread.

FAQ

Questions people ask

What is an AI worker?
An AI worker is a role that runs on the OS: it has a job, triggers, allowed tools and a review rule, and it works alongside people on the same records and tasks. It is a colleague with a defined scope, not a general chatbot.
How is an AI worker different from an AI agent?
An agent is the technology. A worker is an agent given a job, a place in the team and a review step. Heliyos ships the job, the memory and the control, so you deploy a worker rather than build an agent.
What can a worker do without approval?
Only what your review rules allow. By default outbound email waits for a person, and you can put any action, from a deal stage change to a document share, behind review.
Can I build my own worker?
Yes. Describe the role, pick triggers and tools, set what needs review, and it runs exactly like Taylor and Parker: same memory, same cards, same evidence.
How is a worker priced?
Usage-based, on completed work, not seats. Heliyos is in closed beta; join the waitlist for current pricing.

Deploy your first AI worker, today.

Closed beta, usage-based pricing, no seats. Join the waitlist and we review your request.

Closed beta. We review every request and reply by email.