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

# Fini FAQ

> Short, official answers to the questions teams most often ask about Fini: what it is, how it works, where it runs, accuracy, security, and pricing.

Fini (usefini.com) is an AI agent for customer support that resolves tickets across chat, email and voice in 130+ languages, takes actions in your systems, and maintains its own knowledge base. The answers below are short by design; each one links to the page that covers the topic in depth.

## About Fini

<AccordionGroup>
  <Accordion title="What is Fini?">
    Fini is an AI agent for customer support built for regulated industries such as fintech, banking, insurance and healthcare. It answers from approved knowledge, takes actions in your systems through deterministic workflows, keeps its knowledge base up to date, and escalates to your team with full context when it should. See [What is Fini](/en/what-is-fini).
  </Accordion>

  <Accordion title="Who makes Fini?">
    Fini is made by Fini Technologies Inc., founded in 2022 and backed by Y Combinator. Fini serves 100+ customers and handles 3M+ resolutions a month. For general questions, contact [founders@usefini.com](mailto:founders@usefini.com).
  </Accordion>

  <Accordion title="Do I have to replace my helpdesk to use Fini?">
    No. Fini runs on top of the helpdesk you already use, including Zendesk, Intercom, Front, HubSpot, Salesforce, Gorgias, LiveChat and Microsoft 365. Your tickets, queues and human team stay where they are. See [Fini on top of your helpdesk](/en/deploy/on-top-of-your-helpdesk).
  </Accordion>

  <Accordion title="How long does it take to go live?">
    A knowledge agent is live on day 1, agentic workflows by day 14, and full autonomy by day 30. Each milestone maps to concrete product steps, from connecting Sources to building Rulebook workflows and Test Suite checks. See [Rollout timeline](/en/rollout-timeline).
  </Accordion>

  <Accordion title="What languages does Fini support?">
    Fini supports 130+ languages. You control language at ingestion (the **Language** training preference in Sources), in knowledge scoping (language folders and Attribute filters in Articles), and in the agent's prompts. See [Supported languages](/en/supported-languages).
  </Accordion>
</AccordionGroup>

## How Fini works

<AccordionGroup>
  <Accordion title="How does Fini decide what to say?">
    Each message goes through Reply Rules, a Planning step, customer Attributes, then either a deterministic Rulebook workflow or an answer from approved Articles, and finally Guardrails before delivery. Every step is recorded in the AI Steps trace. See [How Fini works](/en/how-fini-works).
  </Accordion>

  <Accordion title="Where does Fini get its answers?">
    From **Articles**, the curated knowledge graph that is the single source of truth for each agent. Content enters through Sources (help center, files, Notion, Google Drive, Confluence, Zendesk Help Center) and reaches Articles only after the review and publish workflow. See the [Knowledge overview](/en/knowledge/overview).
  </Accordion>

  <Accordion title="What is RAGless retrieval?">
    Fini does not chunk documents or use embeddings. It uses LLMs to reason over a knowledge graph built from your approved knowledge, so answers are grounded in reviewed content. See [How Fini works](/en/how-fini-works#5b-or-the-agent-answers-from-approved-knowledge) and [What is RAGless](https://www.usefini.com/blog/what-is-ragless).
  </Accordion>

  <Accordion title="Can Fini take actions, like issuing a refund?">
    Yes. You connect [Actions](/en/api-reference/actions) to your APIs and call them from Tool nodes in [Rulebook](/en/automations/rulebook) behavior trees, which run deterministically: the same inputs produce the same path every time. See the [Refunds use case](/en/use-cases/refunds).
  </Accordion>

  <Accordion title="How does Fini keep its knowledge up to date?">
    A background AI pass detects knowledge gaps and conflicts in live conversations and drafts fixes, which always land in [Review](/en/knowledge/review) and never publish without human approval. [Magic Articles](/en/knowledge/magic-articles) and **Generate Knowledge** in Inbox turn raw content or resolved conversations into articles; their **Status After Generation** setting decides whether a draft goes to Review or straight to Published.
  </Accordion>

  <Accordion title="When does Fini hand a conversation to a human?">
    When a Planning escalation trigger (*Escalation Topics*) matches, an Intent Rule branch ends in a handoff Reply, the agent hits an article whose **Escalation** field is set to **Yes**, a Guardrail can't produce a safe reply, or the customer asks for a person. For widget conversations, a Business Rule with the **On Escalation** trigger creates the ticket in your helpdesk. The conversation reaches your team with the transcript, knowledge used and reasoning trace attached. See [Escalation and handoff](/en/use-cases/escalation-and-handoff).
  </Accordion>

  <Accordion title="Can I see why Fini gave a specific answer?">
    Yes. Every Fini reply in [Inbox](/en/testing/inbox) has an **AI Steps** trace showing planning, attributes loaded, the rule that ran, how the answer was composed, the tags applied and the guardrail verdicts.
  </Accordion>

  <Accordion title="Can I test Fini before it talks to customers?">
    Yes. Start with an **Internal Comment** rule in [Reply Rules](/en/automations/reply-behavior) so the agent posts internal notes only (shadow mode), and build regression checks in [Test Suite](/en/testing/test-suite) before switching to direct reply.
  </Accordion>
</AccordionGroup>

## Channels

<AccordionGroup>
  <Accordion title="Which channels does Fini work on?">
    Chat (the Fini widget on web, in your app and on mobile, plus helpdesk chat), email (helpdesk email, Microsoft 365 shared mailboxes or native Fini email), and voice. Fini also runs in a hosted Help Center, in Slack, and over the API. See the [Channel overview](/en/deploy/overview).
  </Accordion>

  <Accordion title="Does Fini work on phone support?">
    Yes. Fini runs as a voice agent on inbound phone support, configured from **Voice** in the agent sidebar, and calls appear in Inbox with the same trace as chat and email. You can port an existing number, forward calls, or connect over SIP, and escalation can be a live transfer to a phone queue or a ticket, with the transcript handed over. See [Fini on voice](/en/deploy/voice).
  </Accordion>
</AccordionGroup>

## Performance and accuracy

<AccordionGroup>
  <Accordion title="How accurate is Fini?">
    Fini's stated benchmark across deployments is a 90% resolution rate at 99% accuracy; it is not a guarantee for every account, and results depend on your knowledge and workflows. See [How accuracy is measured](/en/performance/how-accuracy-is-measured).
  </Accordion>

  <Accordion title="What is the difference between resolution rate and deflection rate?">
    In Fini Analytics, **AI resolution rate** counts only conversations with status **Resolved by AI**, while **Deflection rate** is 100% minus **Human escalation rate**, so it also counts conversations still waiting on the customer. Fini treats resolution rate as the metric that matters. See [Resolution vs deflection](/en/performance/resolution-vs-deflection).
  </Accordion>

  <Accordion title="How does AI CSAT compare to human CSAT?">
    Fini's published figures are AI CSAT 4.9 versus human CSAT 4.7. You can track CSAT and sentiment for your own agent in [Analytics](/en/analytics#csat-and-sentiment).
  </Accordion>
</AccordionGroup>

## Security and data

<AccordionGroup>
  <Accordion title="Is Fini secure and compliant?">
    Yes. Fini is SOC 2 Type II compliant, ISO/IEC 27001:2022 certified, PCI DSS Level 1 certified, HIPAA-compliant and BAA-eligible, and supports GDPR and CCPA. Policies, subprocessors and the pen-test report are on the [Trust Center](https://security.usefini.com/). See the [Security overview](/en/security/overview).
  </Accordion>

  <Accordion title="Is Fini HIPAA compliant?">
    Yes. Fini is HIPAA-compliant and BAA-eligible for enterprise customers. Fini's BAA template or your own are both fine, and typical turnaround is about one week; request it through your Fini account team. See [HIPAA](/en/security/hipaa).
  </Accordion>

  <Accordion title="Is Fini PCI DSS compliant?">
    Yes. Fini is PCI DSS Level 1 certified, the highest level of the Payment Card Industry Data Security Standard. To request the attestation (AOC), contact your Fini account team. See [PCI DSS](/en/security/pci-dss).
  </Accordion>

  <Accordion title="Does Fini store card numbers or health details from conversations?">
    Fini automatically masks sensitive data, including card numbers and health details, everywhere it stores conversation data (transcripts, Inbox and AI Steps traces). Fields you hide from the AI are also redacted in AI Steps. Still, don't ask customers for card or health details your workflow doesn't need, and add [Guardrails](/en/configuration/guardrails) as an extra layer. See [Data handling](/en/security/data-handling#masking-sensitive-data).
  </Accordion>

  <Accordion title="Does Fini train AI models on my data?">
    No. Fini does not use customer data to train foundation models. Data is encrypted with AES-256 at rest and TLS 1.2+ in transit, with US or EU data residency; with EU data residency, data is stored and processed in the EU. See [Data handling](/en/security/data-handling).
  </Accordion>
</AccordionGroup>

## Pricing

<AccordionGroup>
  <Accordion title="How much does Fini cost?">
    Fini pricing starts at \$0.49 per resolution, a usage-based rate with no per-seat fees. See the [pricing page](https://www.usefini.com/pricing) for current plans and rates, and [How pricing works](/en/billing/how-pricing-works) for the mechanics.
  </Accordion>

  <Accordion title="What counts as a resolution?">
    A resolution counts only when Fini fully solves the issue, no human ever touches the conversation, and the customer does not reply for 72 hours. See [What counts as a resolution](/en/billing/what-counts-as-a-resolution) for edge cases.
  </Accordion>

  <Accordion title="Is there a money-back guarantee?">
    Yes. Under the 90-Day Money-Back Guarantee, eligible new enterprise customers owe nothing for the first 90 days if automated resolution is below 90% of eligible queries, AI CSAT does not outperform human CSAT, or average first response is above 30 seconds. Eligibility applies (new enterprise customers with 1M+ annual tickets, among other conditions). See [Money-back guarantee](/en/billing/money-back-guarantee) and the [guarantee terms](https://www.usefini.com/security/fini-guarantee-terms).
  </Accordion>
</AccordionGroup>

## Related

<CardGroup cols={2}>
  <Card title="What is Fini" icon="circle-info" href="/en/what-is-fini">
    The official explainer.
  </Card>

  <Card title="How Fini works" icon="gears" href="/en/how-fini-works">
    The lifecycle of one conversation.
  </Card>

  <Card title="Rollout timeline" icon="calendar-days" href="/en/rollout-timeline">
    Day 1, 14 and 30.
  </Card>

  <Card title="Security overview" icon="shield-halved" href="/en/security/overview">
    Compliance, data handling and the Trust Center.
  </Card>
</CardGroup>


## Related topics

- [What is Fini](/en/what-is-fini.md)
- [Billing FAQ](/en/billing/billing-faq.md)
- [Security overview](/en/security/overview.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.