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

# Approvals

> A consequential action waits for a person, with the evidence needed to decide — and the decision becomes part of the run's record.

An approval is how an agent asks before doing something consequential. The work pauses on a
question, a person approves or rejects it with the evidence in front of them, and only then does the
action happen. This page explains where approvals come from, where you answer them, and what the
decision leaves behind.

## Why a decision, not a rule

A guardrail is the right control when the answer is always the same: this tool call must never
happen. An approval is for the case where the answer depends on the situation — restarting this
particular workload, at this hour, given what the investigation found.

That distinction is why both exist. A rule that has to be right for every case gets written
permissively and stops protecting anything; an approval keeps a person on the trigger for exactly
the actions where judgement is the point.

## Where an approval comes from

<Steps>
  <Step title="A workflow step that asks a person">
    A workflow can contain a step whose job is to put a question to a human. The run parks there —
    it is not failed, and it is not quietly retried — until somebody answers, and the workflow
    continues from that answer.
  </Step>

  <Step title="A guardrail that holds an action">
    A guardrail can refuse a specific action until a person allows that exact action, rather than
    blocking the whole class of them outright.
  </Step>
</Steps>

In both cases the request carries what a decision needs: what the agent proposes to do, which agent
and run it belongs to, and the record it came out of — so you are approving a specific action with
its evidence, not a permission in the abstract.

## Answering one

Pending decisions collect in **Attention**, with approve and deny beside each one, and a run that is
waiting shows what it is waiting on — its status reads *waiting*, against the action it prepared.
The platform overview carries the same queue as an **Approvals** card, counting the agent actions
awaiting a human and linking straight into Attention. Approving applies exactly what was proposed;
rejecting ends that path rather than leaving the action pending.

<Warning>
  Nothing pushes an approval at you today — pending decisions wait to be found rather than arriving as
  a notification. If a workflow depends on a timely decision, make checking the inbox part of
  somebody's routine.
</Warning>

Approvals are answered in the console. An agent cannot approve its own held action, and there is no
chat or tool path to answer one — deciding is deliberately a human-only surface.

## What the decision leaves behind

Every approval and rejection becomes part of the run's durable
[evidence](/manage-your-agents/run/runs-evidence), and the guardrail decision behind a held action is
recorded whichever way it goes. Afterwards you can answer both questions that matter: what was
proposed, and who let it happen.

A run that was held for a human is also distinguishable from one that resolved untouched — so "was
a person in this loop?" is a property of the run rather than something you have to reconstruct from
timestamps.

## Next steps

<CardGroup cols={2}>
  <Card title="Standards & Guardrails" href="/security-and-governance/controls/standards-guardrails">
    The rules that decide when an action needs a person at all.
  </Card>

  <Card title="Orchestration" href="/manage-your-agents/run/orchestration">
    How a workflow step parks on a question and resumes.
  </Card>

  <Card title="Runs & evidence" href="/manage-your-agents/run/runs-evidence">
    Where a paused run and its decision live.
  </Card>

  <Card title="Audit log" href="/security-and-governance/controls/audit-log">
    The record of who decided what.
  </Card>
</CardGroup>


## Related topics

- [Remediation Executor](/manage-your-agents/build/catalog/remediation-executor.md)
- [Data flow](/get-started/architecture/data-flow.md)
- [Attention](/manage-your-agents/run/attention.md)
- [Klaudia Investigator](/manage-your-agents/build/catalog/klaudia-investigator.md)
- [Remediation](/manage-your-agents/build/catalog/remediation.md)