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

# FAQ

> Quick answers to the most common questions about Alethia.

## Getting started

<AccordionGroup>
  <Accordion title="Do I need to write any code to use Alethia?">
    No. Alethia is a web application — everything is done through the UI. The only "technical" thing you need to do is paste an API key from the LLM provider you want to test (OpenAI, Anthropic, etc.).
  </Accordion>

  <Accordion title="What does it cost to run a test?">
    Two costs to think about:

    1. **The API cost at your provider** — every test sends one prompt to your test model and three prompts to your judges. The cost is whatever those four calls cost at your provider's pricing. Usually a few cents per test.
    2. **Alethia's plan cost** — depends on your plan. The free tier is generous for getting started.

    For team-provided judge models (where Alethia handles the API costs), you pay in **tokens** — see [Token Usage & Billing](/essentials/llm-configurations#team-provided-models) for details.
  </Accordion>

  <Accordion title="Which LLMs can I test?">
    Out of the box: OpenAI, Anthropic, Google, Mistral, DeepSeek. Anything else (custom hosting, your own fine-tunes, less common providers) works through the **Custom** provider — you give Alethia the endpoint URL, headers, and JSON paths to use.
  </Accordion>

  <Accordion title="Do I have to use the EU AI Act risk module?">
    No. If your AI use case is low-risk (a spam filter, a video game NPC), you can skip the risk module entirely. It's there for the people who need it.
  </Accordion>
</AccordionGroup>

## Testing

<AccordionGroup>
  <Accordion title="Why three judges?">
    A single judge can be wrong, biased, or have a bad day. Three judges give you a robust verdict that doesn't depend on any one model. See [Multi-Judge Consensus](/testing/consensus-and-judges).
  </Accordion>

  <Accordion title="Can I use the same model as test and judge?">
    Technically yes, but **it's a bad idea**. Models tend to grade themselves favorably. Always use judges from different model families than your test model.
  </Accordion>

  <Accordion title="What's the difference between 'unsafe' and 'inconclusive'?">
    * **Unsafe** — the consensus says the model's response was unsafe.
    * **Inconclusive** — the judges couldn't agree (under the **Unanimous** voting method) or the weighted votes canceled out (under **Weighted**).

    Both deserve a human eye, but inconclusive results in particular often need an override one way or the other.
  </Accordion>

  <Accordion title="Can I edit a test result after it runs?">
    You can't edit the AI verdict — that's locked. But you can **override** it as a human, with a written reason. The override becomes the effective verdict from then on. The original AI verdict is still visible. See [Human Overrides](/testing/human-overrides).
  </Accordion>

  <Accordion title="Can I delete a test result?">
    Deletion is restricted by design — it would break the audit trail. You can archive an entire project to remove it from active dashboards while keeping the data.
  </Accordion>
</AccordionGroup>

## Prompt library

<AccordionGroup>
  <Accordion title="The default prompts are seeded as empty categories. Where are the actual prompts?">
    The categories ship empty by design — different organizations have very different testing needs (a healthcare AI tester needs different prompts than a finance AI tester). You add prompts via single entry or bulk JSON upload.

    Alethia provides starter prompt packs you can import — ask support if you'd like one for your domain.
  </Accordion>

  <Accordion title="Why is the prompt library team-scoped, not project-scoped?">
    Because it's what makes [model comparisons](/comparison) meaningful — same prompts, different models, fair comparison. If you really need a different prompt set, create a new team.
  </Accordion>

  <Accordion title="Can I share prompts between teams?">
    Not directly through the UI. But you can export prompts from one team as JSON and bulk-upload them to another team.
  </Accordion>
</AccordionGroup>

## Risk management

<AccordionGroup>
  <Accordion title="My project is high-risk. Where do I start?">
    1. Classify the project ([Risk Classification](/risk-management/classification))
    2. Get the classification approved by a Team Admin
    3. Run a baseline category test on the most relevant prompts
    4. Use **Suggest Risks** to get a starter risk register
    5. Assess each risk with the test data
    6. Plan mitigations for elevated risks
    7. Schedule recurring tests to keep evidence flowing
  </Accordion>

  <Accordion title="How does Alethia decide what risk score to give a suggested risk?">
    The platform looks at:

    * The **failure rate** in the relevant category (more failures → higher likelihood)
    * The **severity** of the prompts that failed (high-severity prompts → higher impact)
    * The **EU AI Act risk domain** mapped to that category

    All suggestions are pre-filled but **fully editable** — you have the final say.
  </Accordion>

  <Accordion title="Does Alethia certify my AI as EU AI Act compliant?">
    No, and no platform can. Compliance is a determination made by your own internal compliance team and (where required) a notified body. Alethia gives you the tooling, evidence, and documentation you need to support that determination.
  </Accordion>
</AccordionGroup>

## Account & teams

<AccordionGroup>
  <Accordion title="Can I belong to multiple organizations?">
    Yes. One Alethia account can be a member of multiple organizations and multiple teams within each. Use the team switcher at the top of the sidebar to move between them.
  </Accordion>

  <Accordion title="What happens if I delete my account?">
    Your profile is removed from all teams. Anything you created (test runs, risk entries, overrides) **stays** — it's reattributed to "Deleted User" so the audit trail isn't broken.
  </Accordion>

  <Accordion title="What's the difference between Team Admin and Org Admin?">
    * **Org Admin** manages the whole organization — creating teams, inviting members across teams, but not billing.
    * **Team Admin** manages one specific team — its projects, members, API keys, prompts, and risk approvals.

    A person can be both at once.
  </Accordion>
</AccordionGroup>

## Security

<AccordionGroup>
  <Accordion title="Where do you store my LLM API keys?">
    Encrypted at rest with AES-256-GCM. Keys are never shown again in the UI — they always appear masked (e.g., `sk-...****`). The only place they're decrypted is briefly in memory when Alethia is calling the provider.
  </Accordion>

  <Accordion title="Can other teams in my organization see my project?">
    No. Projects are team-scoped, and team members can't see other teams' projects unless they've explicitly been added as a member.
  </Accordion>

  <Accordion title="How long are sessions valid?">
    30 days, with sliding expiration (each request resets the clock). You can revoke any active session at any time from your **Account Settings → Security**.
  </Accordion>
</AccordionGroup>

## Billing

<AccordionGroup>
  <Accordion title="Where can I see my organization's usage?">
    Org Owners and Admins can see usage at **Organization → Billing**. Token transactions for team-provided judge models are itemized.
  </Accordion>

  <Accordion title="What happens if I run out of tokens mid-test?">
    Tokens are reserved before each test starts. If your balance is too low, the test is blocked before it begins — no surprise overdrafts. You'll see a clear error message and can top up.
  </Accordion>
</AccordionGroup>

## Still stuck?

<CardGroup cols={2}>
  <Card title="Glossary" icon="book" href="/help/glossary">
    Look up unfamiliar terms.
  </Card>

  <Card title="Troubleshooting" icon="wrench" href="/help/troubleshooting">
    Specific error messages and fixes.
  </Card>
</CardGroup>

If you can't find your answer, email **[support@alethia.ai](mailto:support@alethia.ai)** with as much detail as you can — error messages, what you were trying to do, and a screenshot if relevant.