> ## 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.
# What is Fini
> Fini is an AI agent for customer support that resolves tickets across chat, email and voice, takes actions in your systems, and maintains its own knowledge base.
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. It is built for regulated industries (fintech, banking, insurance, healthcare) and runs on top of the helpdesk you already use, so there is no migration: a knowledge agent is live on day 1, agentic workflows by day 14, and full autonomy by day 30.
This page is the plain explanation of what Fini is and what it does. If you already know and want a map of the docs, start at the [Introduction](/en/introduction). If you want the mechanics of a single conversation, read [How Fini works](/en/how-fini-works).
## Who Fini is for
Fini is used by support teams that handle a high volume of customer conversations and can't afford a wrong answer. Fini's customer base skews toward fintech, banking, insurance and healthcare, where every reply can carry a regulatory, financial or clinical consequence and audit requirements are non-negotiable.
Three groups inside a customer typically work with Fini:
| Who | What they do in Fini |
| - | - |
| **Support and CX leads** | Decide what the agent should handle, which workflows it runs, and when it hands off to a human. They live in [Inbox](/en/testing/inbox) and [Analytics](/en/analytics). |
| **Knowledge and operations owners** | Connect content, approve new and updated articles in [Review](/en/knowledge/review), and organize [Articles](/en/knowledge/articles) per agent. |
| **Engineering and security** | Connect [Actions](/en/api-reference/actions) and [Attributes](/en/api-reference/attributes) to internal systems, manage [API Keys](/en/deploy/api-keys) and [SSO](/en/sso-login) (Okta, Google, Slack or Microsoft Entra ID), and review Fini's [security posture](/en/security/overview). |
## What Fini does
Fini does four jobs. Each one maps to a part of the product you configure.
### 1. Answers questions from approved knowledge
Fini answers from **Articles**, the curated knowledge graph that is the single source of truth for every agent. Raw content (help center pages, files, Notion, Google Drive, Confluence, Zendesk Help Center) enters through [Sources](/en/knowledge/sources), becomes candidate knowledge, and only reaches Articles after it passes the review and publish workflow. Retrieval is RAGless: Fini does not chunk documents or use embeddings. It uses LLMs to reason over a knowledge graph built from your approved knowledge. See the [Knowledge overview](/en/knowledge/overview).
### 2. Takes actions in your systems
Fini doesn't stop at telling a customer what the policy is. With [Actions](/en/api-reference/actions) it can call your APIs mid-conversation (cancel a subscription, look up an order, update an address, reorder a card), and with [Attributes](/en/api-reference/attributes) it pulls in the customer's plan, account state or recent orders so the reply is about *this* customer. Multi-step workflows such as refunds, cancellations or identity checks are built in the [Rulebook](/en/automations/rulebook) as behavior trees that run deterministically: the same inputs produce the same path every time.
### 3. Keeps its own knowledge up to date
Fini watches the conversations it handles and proposes improvements. A background AI pass detects **gaps** (questions no article answers) and **conflicts** (two inputs that disagree) and drafts a fix. [Magic Articles](/en/knowledge/magic-articles) turns raw content or a resolved conversation into a structured article. Drafts from the background AI always land in [Review](/en/knowledge/review) and never publish without a human approving them; for Magic Articles, **Status After Generation** decides whether a draft goes to Review or straight to Published.
### 4. Escalates to your team when it should
When a conversation needs a person (by policy, because a check failed, or because the customer asked) Fini hands it to your human team with the conversation, the knowledge it used and its reasoning trace attached. You decide what triggers a handoff: escalation topics in the [Planning Prompt](/en/configuration/prompts#controlling-when-the-agent-escalates), Rulebook branches, [Guardrails](/en/configuration/guardrails) that can't produce a safe reply, and [Reply Rules](/en/automations/reply-behavior) that keep the agent silent or internal-only on sensitive intents.
The four jobs connect into one loop: approved knowledge and your systems feed the agent, the agent replies or hands off, and what it learns from conversations comes back to your team as drafts to approve.
```mermaid theme={null}
---
title: The four jobs, as one loop
---
flowchart LR
subgraph KNOW["1. APPROVED KNOWLEDGE"]
SRC["Sources"] --> REV["Review
human approval"]
REV --> ART["Articles"]
end
subgraph SYS["2. YOUR SYSTEMS"]
ATTR["Attributes
customer context"]
ACTN["Actions
called from Rulebook"]
end
FINI(("Fini
agent"))
REPLY["Reply on your surface"]
HUMAN["4. Your human team"]
DRAFT["3. Drafted fixes
gaps · conflicts"]
ART --> FINI
ATTR --> FINI
FINI <--> ACTN
FINI --> REPLY
FINI -.->|"policy, failed check,
customer asks"| HUMAN
FINI -->|"learns from conversations"| DRAFT
DRAFT --> REV
classDef source fill:#F7F7F7,color:#131415,stroke:#E8E8E8
classDef agent fill:#131415,color:#FFFFFF,stroke:#131415,stroke-width:3px
classDef surface fill:#FFFFFF,color:#131415,stroke:#131415
classDef human fill:#C3EE5E,color:#131415,stroke:#131415,stroke-width:2px
class SRC,ART,ATTR,ACTN source
class FINI agent
class REPLY,DRAFT surface
class REV,HUMAN human
```
## Where Fini runs
Fini is headless. The same agent, with the same knowledge and rules, can answer on several surfaces at once.
| Surface | How it connects | Page |
| - | - | - |
| **Your helpdesk** | Zendesk, Intercom, Front, HubSpot, Salesforce, Gorgias, LiveChat and Microsoft 365. Fini replies (or leaves internal notes) on tickets inside the tool your team already uses. | [Fini on top of your helpdesk](/en/deploy/on-top-of-your-helpdesk) |
| **Chat widget** | A snippet on your website, inside your authenticated app, or in your mobile app. Widget escalations can hand off into Zendesk, Front, Salesforce, HubSpot or Gorgias. | [Widget](/en/deploy/widget) |
| **Email** | Support addresses on your own domain routed into Fini's native Inbox and ticket workspace. | [Email](/en/deploy/email) |
| **Voice** | Inbound phone support, configured from **Voice** in the agent sidebar. Calls appear in Inbox with the same trace as chat and email. | [Fini on voice](/en/deploy/voice) |
| **Help center** | A hosted, AI-searchable help center generated from your Articles. | [Help Center](/en/deploy/helpcenter) |
| **Slack** | Internal questions in Slack channels and DMs. Separate from [Fini Scout](/en/fini-scout), the Slack coworker for your own team. | [Slack](/en/deploy/slack) |
| **API** | Public HTTP APIs with workspace-scoped API keys, for sending conversation events, ingesting documents and managing knowledge. | [API Keys](/en/deploy/api-keys) |
The full list, including the Chrome extension and cards for Discord, Freshdesk and Deskpro, is on the [Channel overview](/en/deploy/overview).
## The four aspects of an agent
Every agent in Fini has four aspects. You configure each one independently and they compose into one running agent.
```mermaid theme={null}
---
title: Four aspects compose one agent
---
flowchart LR
subgraph K["KNOWLEDGE · what it knows"]
K1["Sources · Articles
Magic Articles · Review"]
end
subgraph B["BEHAVIOR · how it acts"]
B1["Prompts · Tags · Guardrails
Intent, Business, Reply Rules
Attributes · Actions"]
end
A(("Agent"))
subgraph D["DEPLOYMENT · where it lives"]
D1["Helpdesk · Widget · Email
Voice · Help Center · Slack · API"]
end
subgraph O["OBSERVABILITY · how you watch it"]
O1["Inbox and AI Steps
Test Suite · Analytics"]
end
K1 --> A
B1 --> A
A --> D1
A --> O1
classDef agent fill:#131415,color:#FFFFFF,stroke:#131415,stroke-width:3px
classDef aspect fill:#F7F7F7,color:#131415,stroke:#131415
class A agent
class K1,B1,D1,O1 aspect
```
| Aspect | What it covers | Where to configure it |
| - | - | - |
| **Knowledge** | Sources, Articles, Magic Articles, Review. | [Knowledge](/en/knowledge/overview) |
| **Behavior** | Prompts, Tags, Guardrails, Intent Rules, Business Rules, Reply Rules, Attributes and Actions. | [Prompts](/en/configuration/prompts), [Rulebook](/en/automations/rulebook) |
| **Deployment** | The surfaces above. | [Channel overview](/en/deploy/overview) |
| **Observability** | Inbox and the AI Steps trace, Test Suite, Analytics. | [Inbox](/en/testing/inbox), [Test Suite](/en/testing/test-suite), [Analytics](/en/analytics) |
One workspace can run many agents, for example one for billing, one for onboarding and one for internal IT, each with its own knowledge scope, rules and deployments.
## Headline facts
| Fact | Detail |
| - | - |
| Channels | Chat, email and voice, plus help center, Slack and API |
| Languages | 130+ languages. See [Supported languages](/en/supported-languages). |
| Performance | 90% resolution rate at 99% accuracy, Fini's stated benchmark across deployments, not a guarantee for every account. See [How accuracy is measured](/en/performance/how-accuracy-is-measured). |
| Scale | 3M+ monthly resolutions; 100+ customers |
| CSAT | AI CSAT 4.9 vs human CSAT 4.7 |
| Time to value | Knowledge agent live on day 1, agentic workflows by day 14, full autonomy by day 30. See [Rollout timeline](/en/rollout-timeline). |
| Pricing | Usage-based, per resolution, no per-seat fees. See [How pricing works](/en/billing/how-pricing-works). |
| Compliance | SOC 2 Type II compliant, ISO/IEC 27001:2022 certified, PCI DSS Level 1 certified, HIPAA-compliant and BAA-eligible for enterprise customers, GDPR and CCPA. See [Security overview](/en/security/overview). |
| Data | Fini does not use customer data to train foundation models. US or EU data residency; with EU data residency, data is stored and processed in the EU. See [Data handling](/en/security/data-handling). |
| Company | Fini Technologies Inc., founded 2022, backed by Y Combinator |
## What Fini is not
* **Not a helpdesk you migrate to.** Fini runs on top of Zendesk, Intercom, Salesforce and the other helpdesks it integrates with. Your tickets, macros, queues and human team stay where they are; Fini reads and replies inside them. Teams that want inbound email without a third-party helpdesk can use Fini's native [Email](/en/deploy/email) channel, which routes into the Inbox ticket workspace. See [Fini on top of your helpdesk](/en/deploy/on-top-of-your-helpdesk).
* **Not a free-running chatbot.** In the Rulebook, the LLM works only inside behavior tree nodes (Check, Read, Reply, Form) and a deterministic tree walker decides which node runs when. Per-agent [Guardrails](/en/configuration/guardrails) check generated replies before delivery.
* **Not a black box.** Every reply has an [AI Steps trace](/en/testing/inbox#ai-steps-what-the-agent-actually-did): planning, the attributes it loaded, the rule it ran, how it composed the answer, the tags it applied and the guardrail verdicts.
* **Not a model trained on your data.** Fini does not use customer data to train foundation models. Any per-customer learning happens only inside that customer's environment and only with their written authorization.
* **Not self-publishing.** Knowledge changes Fini proposes on its own (gaps, conflicts, Refine with AI drafts) wait for your team to approve them.
## Related
The lifecycle of one conversation, from arrival to escalation and self-improvement.
Create an agent, add knowledge, deploy in shadow mode, and iterate.
What happens on day 1, day 14 and day 30, and what your team does at each step.
Short answers to the questions teams ask most about Fini.
## Related topics
- [Fini FAQ](/en/faq.md)
- [Fini for disputes and chargebacks](/en/use-cases/disputes.md)
- [Fini for billing and invoices](/en/use-cases/billing-and-invoices.md)
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.