> ## Documentation Index
> Fetch the complete documentation index at: https://docs.exterview.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Gradientflo Agents

> The 10 specialized agents that make up the post-hire workforce inside Gradientflo, grouped by stage of the employee journey, with what each one is accountable for and its current status.

## Purpose

[Gradientflo](/gradientflo/overview) is the second application on [Smaya](/smaya/overview), and it runs a workforce of **10 specialized agents**. Each is accountable for one job. You combine them into [AI Employees](/smaya/ai-employees) — named roles with a mandate, bounded authority and named human owners.

**Most of them teach.** Onboarding and project training are delivered by **AI tutors** — conversational agents that carry your organization's project, team and company knowledge to a new hire and answer, explain and coach through the first ninety days. They run over the same **voice and avatar** interfaces as Exterview's interview agents, so a new hire talks to them rather than reading a portal.

<Info>
  **Availability.** **Available** means you can use it today. **Upcoming** means
  it is on the way and not yet usable. Gradientflo is a separate, Upcoming
  application, so every Gradientflo agent is Upcoming. <Icon icon="star" />
  marks the seven that seed first.
</Info>

## Onboarding — 4 agents

The first ninety days, where most of the value of a good hire is won or lost.

| Agent                                            | Accountable for                                                                                                             | Status   |
| ------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------- | -------- |
| **Onboarding Tutor Agent** <Icon icon="star" />  | Teaching a new hire their project, team and organization from day one, and answering from your own material, with citations | Upcoming |
| **Buddy Workflow Agent** <Icon icon="star" />    | Assigning and running the buddy relationship that carries a new hire through their first weeks                              | Upcoming |
| **Milestone Cadence Agent** <Icon icon="star" /> | Running a reliable 30/60/90 check-in rhythm for every hire, with nothing dependent on a manager remembering                 | Upcoming |
| **Ramp Risk Agent** <Icon icon="star" />         | Surfacing early signals that a hire is struggling, before it becomes an exit                                                | Upcoming |

## Development — 3 agents

Closing the gap between the person hired and the person the role needs.

| Agent                                         | Accountable for                                                                             | Status   |
| --------------------------------------------- | ------------------------------------------------------------------------------------------- | -------- |
| **Coaching Nudge Agent** <Icon icon="star" /> | Prompting the right conversation at the right moment, to the manager or the hire            | Upcoming |
| **Objective Tutor Agent**                     | Running a guided training session on one specific objective, bounded to its source material | Upcoming |
| **Learning Connector Agent**                  | Mapping a development gap to the learning your organization already licenses                | Upcoming |

## Performance — 2 agents

Whether the hire is working, and what to do when it is not.

| Agent                                               | Accountable for                                                                 | Status   |
| --------------------------------------------------- | ------------------------------------------------------------------------------- | -------- |
| **Role Fit Review Agent** <Icon icon="star" />      | Re-evaluating fit against the same criteria the person was originally hired on  | Upcoming |
| **Development Planning Agent** <Icon icon="star" /> | Turning an identified gap into a structured, specific plan a manager can act on | Upcoming |

## Operations — 1 agent

| Agent                                                       | Accountable for                                                                                         | Status   |
| ----------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- | -------- |
| **Assimilation Admin Agent** <Icon icon="triangle-alert" /> | Administrative work across the post-hire process, confirming with a person before every change it makes | Upcoming |

<Icon icon="triangle-alert" /> **The module's first write-capable agent.** It is
the row most likely to face a security review rather than pass one, so it ships
behind permission scoping and human confirmation on every write — not ahead of
them.

<Icon icon="star" /> **Why these seven seed first.** They are the closed loop: a
hire is answered, checked on, watched for risk, and re-evaluated against the
criteria they were hired on. The other three extend that loop outward — into
learning content, and into acting on your systems — and both extensions depend
on the loop working first.

## When a tutor does not know

A design decision worth stating plainly, because it is unusual and deliberate.

**The tutors answer without escalating to a human.** A new hire's whole reason for asking an AI tutor is that they do not want to interrupt a colleague — or do not want to look like they should already know. An agent that answers "ask your manager" hands the problem straight back and defeats its own purpose.

So instead of escalating, a tutor that is not confident enough to answer **defers and logs**: it says it does not have a reliable answer yet, records the gap, and the gap becomes a signal that your onboarding material is incomplete.

<CardGroup cols={2}>
  <Card title="Never a confident guess" icon="shield">
    Answers come from your own curated material with citations. Below the confidence threshold, it declines rather than improvising.
  </Card>

  <Card title="Never 'ask your manager'" icon="user-x">
    Deferring back to a human is the failure mode this agent exists to remove, not
    its fallback.
  </Card>

  <Card title="The gap becomes the signal" icon="chart-line">
    Every deferral is logged. A cluster of them tells you exactly which part of
    your onboarding material is missing.
  </Card>

  <Card title="Writes still need a person" icon="user-check">
    This applies to answering only. Anything that changes a record or contacts someone still waits for a named human.
  </Card>
</CardGroup>

## What no agent may ever do

<CardGroup cols={2}>
  <Card title="Judge performance" icon="gavel">
    Role fit and development output is evidence prepared for a manager. A judgment about a person's performance is made by a named human.
  </Card>

  <Card title="Assess without notice" icon="megaphone">
    No agent runs a background assessment of an employee before that employee has
    been told it happens, and the notice is recorded as its own act.
  </Card>

  <Card title="Exceed the person using it" icon="lock">
    Effective authority is the intersection of the agent's scope and the user's
    permissions.
  </Card>

  <Card title="Act without a record" icon="clipboard-list">
    Every action, proposal and approval is captured and attributed.
  </Card>
</CardGroup>

## Why this proves the platform

Three of the ten run on **the same underlying expertise as a recruiting agent** — the Knowledge Agent, the Journey Nudge Agent and the Resume Screening Agent each now serve two business functions.

That reuse is the entire argument for an Agent OS. A second function does not mean a second product: it means new roles composed largely from capability that already exists, already governed, already audited.

<CardGroup cols={2}>
  <Card title="The subject changes" icon="user">
    Recruiting agents act on a **candidate**. HR agents act on an **employee**. The platform treats who is being assessed as a declared property, not an assumption baked into the code.
  </Card>

  <Card title="The scope changes" icon="folder">
    Recruiting work is scoped to a **requisition**. Onboarding work is scoped to an **onboarding journey**. The rule that criteria never change mid-stream applies identically to both.
  </Card>
</CardGroup>

## Related

<div className="kb-links">
  *   <span className="kb-ico">
        <Icon icon="graduation-cap" />
      </span>
    [Gradientflo](/gradientflo/overview). The application these agents belong to.
  *   <span className="kb-ico">
        <Icon icon="users" />
      </span>
    [Exterview Agents](/agents/exterview). The 26 pre-hire agents.
  *   <span className="kb-ico">
        <Icon icon="trending-up" />
      </span>
    [Roadmap to 100](/agents/roadmap).
</div>