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

# Opening strategies

> Open the platform to everyone or curate specific use cases, and how to open without chaos.

Once the structure is set, you decide how widely to open agent creation. There are two strategies, and **the choice is yours**.

<CardGroup cols={2}>
  <Card title="Open to everyone" icon="door-open">
    Anyone can create agents for themselves. Broad enablement, with controls so it does not turn into chaos. Detailed below.
  </Card>

  <Card title="Curated use cases" icon="list-check">
    Only selected, prioritized use cases are built and rolled out. Tighter, slower, and easier to govern. Follow the [use-case lifecycle](./use-case-lifecycle) for each.
  </Card>
</CardGroup>

## Open without chaos

The open strategy works only with guardrails. The goal: let everyone experiment, but keep sharing, publishing, and sensitive data under control.

<Steps>
  <Step title="Default: create, do not share">
    Everyone can create agents for themselves, but **no one can share or publish** by default. This is enforced with [tool permissions](/products/agent-factory/tool-permissions) and [sharing settings](/products/agent-factory/settings).
  </Step>

  <Step title="Train and raise awareness">
    Start with training and AI Act awareness. People govern themselves better when they understand the rules. See [compliance](/resources/security/compliance).
  </Step>

  <Step title="Identify the agents that matter">
    Use [Insights](/products/ai-insights/adoption) and [Governe](/products/ai-governance/overview) to spot the most used and most relevant agents. Internal committees select the **AI champions** who earn the right to share.
  </Step>

  <Step title="Validate compliance, then publish or share">
    When an agent proves relevant, the committee validates it against compliance criteria. Only then can it be published or shared to a group or the whole organization, through an access-validation workflow. See [creating agents](/products/agent-factory/creating-agents) and [join rules](/products/ai-governance/identity-access).
  </Step>

  <Step title="Publish common agents centrally">
    The central team can also publish common agents available to everyone, to the whole organization or to a restricted audience with an access-validation workflow.
  </Step>

  <Step title="Activate the guardrails">
    Committees validate the guardrails to activate. The platform team can force [hooks](/products/agent-factory/hooks) (for example data controls based on classification) and set the [runtime safeguards](/products/agent-factory/runtime-safeguards) and guardrails required at platform or organization level.
  </Step>
</Steps>

## The guardrail model: tighten downward, tightest wins

Every control in the workflow above rides on one model: governance is a cascade of envelopes. Each level can only tighten the one above, on conflict the tightest limit wins, and inside its own envelope each level distributes freely.

<Frame>
  <img src="https://mintcdn.com/prismeai/0zf8VGzwhBRxRTcR/images/governance-quota-cascade.svg?fit=max&auto=format&n=0zf8VGzwhBRxRTcR&q=85&s=84ad2e92654104b8680e0672d0adca5f" alt="Governance as nested envelopes: platform plan, then organization, then agent, then the effective user limit. Each level can only tighten the one above, the tightest limit wins on conflict, and each level distributes freely within its envelope." width="1200" height="530" data-path="images/governance-quota-cascade.svg" />
</Frame>

This is where the central controls live:

* **Models and tools**: restrict which LLMs and tools an agent may call. See [model governance](/products/ai-governance/model-governance) and the [capabilities catalog](/products/ai-governance/capabilities).
* **Hooks**: force data controls based on classification. See [hooks](/products/agent-factory/hooks).
* **Data retention**: cap how long conversations, documents, tasks, and artifacts are kept. See [data retention](/products/ai-governance/retention).
* **Quotas**: usage envelopes per organization, agent, and user.

## Next steps

<CardGroup cols={2}>
  <Card title="Who does what" icon="users-gear" href="./operating-model">
    The committees, champions, and squads behind these controls
  </Card>

  <Card title="Governe" icon="shield-check" href="/products/ai-governance/overview">
    The product that enforces all of the above
  </Card>
</CardGroup>