> ## Documentation Index > Fetch the complete documentation index at: https://docs-eos.fpt.ai/llms.txt > Use this file to discover all available pages before exploring further. # What is EOS > [!NOTE] > > **FPT AI EOS EOS** - A platform where people and Digital Workers do real work together, under one shared set of rules and controls. Welcome to the documentation for **FPT AI EOS - Enterprise Operating System (EOS)**. This is where people and Digital Workers carry out the real work of a business - quoting, resolving tickets, drafting contracts, onboarding staff, producing reports - under **one shared set of rules and controls**. EOS is not a tool for building Digital Workers. It is the operating layer your organisation runs on. ## How the business changes Most companies today work like this: the work lives in inboxes, in meetings and in people's heads. Know-how belongs to individuals, so when someone leaves, the knowledge leaves with them. Managers only see results once the quarter has closed. Improvement happens project by project, review cycle by review cycle. EOS changes those four things: | A business today | A business on EOS | | - | - | | Work lives in inboxes, meetings and personal memory | Work runs on a platform with a clear owner, an audit trail and governance | | Know-how belongs to individuals; when they leave, it leaves | Knowledge stays in the company knowledge base | | Managers see results after the books close | Managers watch work as it runs, and can stop it | | Improvement comes project by project, on a review cycle | Improvement is continuous, not once a quarter | > [!NOTE] > > "Operating System" here does not mean a computer OS. It means the shared coordination layer of the business: one place that holds the knowledge, the processes, the permissions and the logs of every Digital Worker. ## How this differs from a chatbot and from an ordinary Digital Worker platform All three are usually lumped together as "AI", but they are fundamentally different. | | Chatbot | Digital Worker platform | **EOS** | | - | - | - | - | | What it does | Replies from a script someone wrote | Performs tasks on its own, calls tools | Does the real work of each department, across systems | | Knowledge | The bot's own FAQ set | Knowledge attached to each Digital Worker | One shared knowledge source for the whole company, with citations | | Scale | One channel, one use case | Many disconnected Digital Workers | Many Digital Workers sharing skills, tools, knowledge and policy | | Control | Effectively none | Per Digital Worker, fragmented | Policy enforced inside the execution path, with immutable logs | | When it goes wrong | You find out when a customer complains | You find out at review time | Blocked or routed to an approver **before** the action completes | | Improvement | Someone rewrites the script | Fix one Digital Worker at a time | Fix once, every permitted Digital Worker benefits | > [!TIP] > > The quickest way to tell them apart: a chatbot **talks**. A Digital Worker **acts**. EOS is where that work is **assigned, supervised and accounted for** - the same way it would be for a real employee. ## Five core capabilities Governance and Knowledge are the **foundation** - every Digital Worker runs beneath them. Process, Productivity and Analytics are the **value layer**. The order matters: without policy there is nothing to supervise, and without reliable knowledge the Digital Worker gives wrong answers in every process downstream. | # | Capability | The question it answers | | - | - | - | | 1 | **Governance** | What is each Digital Worker allowed to do, and who is accountable | | 2 | **Knowledge** | What does the Digital Worker base its answers on, and where does it come from | | 3 | **Process** | Is the work following the right procedure, or reaching the right goal | | 4 | **Productivity** | What are people freed from | | 5 | **Analytics** | What do the numbers say, and what should we do next | ### 1. Governance Five steps, from the basics to the most advanced: define policy, grant permissions by context, monitor and detect violations, enforce and route to approvers, audit. What sets EOS apart is that policy is not an internal document; it is wired straight into the execution path. A customer-care Digital Worker may draft an email but not send it. An onboarding Digital Worker cannot read payroll data. Violations are blocked at the moment they occur, not discovered after the message has gone out. ### 2. Knowledge This goes beyond document lookup: comprehension, retrieval, citation, analysis, multi-source reasoning, and finally the creation of new knowledge. A question such as "Can I sign a freelancer contract, and what is the withholding tax rate?" has its answer split across two documents owned by two departments. The Digital Worker brings them together in one conversation and cites each part from its own source. ### 3. Process - Automation and process redesign Two operating modes. **Follow the procedure**: you define each step, the Digital Worker orchestrates it precisely and flags exceptions. **Reach the objective**: you define only the objective and the principles, and the Digital Worker finds the fastest route within the boundaries you allow. After a period of operation the system points out the steps that are no longer needed - a seven-step onboarding process may come down to three. ### 4. Productivity Everyone's work splits into two kinds: work that needs **judgement**, and work that only needs **execution**. EOS does not replace judgement; it makes judgement better by preparing the data, drafting the first version and pointing out the risks. It takes over the second kind entirely. For example, a QA manager who could previously review only 2-3% of 10,000 calls a week now has 100% of conversations scored automatically, and receives a list prioritised by actual risk. ### 5. Analytics Four levels: descriptive, diagnostic, predictive, prescriptive. Most organisations are stuck at the first, not for lack of data but for lack of time to turn data into insight. For example, loan approval rates fall from 78% to 62%. Instead of three to five days of manual analysis, the system shows within minutes that the drop is concentrated among applicants under 30, on short-term consumer loans, handled by two new staff members. ## Notable features for the enterprise ### Build Digital Workers in natural language, no code required Describe what you want the Digital Worker to do and the system drafts it for you to refine. Attach skills, tools, knowledge and guardrails right in the Digital Worker builder. Complex work can be split across several supporting Digital Workers that work together. ### One shared knowledge source, answers with citations Company documents go into one place, and every permitted Digital Worker draws on the same source. Answers come with specific citations, so users know which document the information came from. Update a policy once and every related Digital Worker reflects the change immediately. ### Guardrails and human approval You set the boundaries for a single Digital Worker or for the whole workspace: topics that are off limits, personal data that must be masked, risky actions that need human approval before they run. Change one shared policy and a whole set of Digital Workers changes with it. ### Connects directly to the systems you already use Digital Workers read and write directly in your CRM, ERP, HRIS, SharePoint or Jira through connectors and MCP, so data is never copied out of its system of record. Digital Workers serve customers on the web, Zalo, Teams, email and the voice contact centre. ### Test first, publish after Every change stays in a draft until you publish. There is a test tab for trial runs and versioning to roll back when you need to, so the Digital Worker currently serving customers is never affected by the version you are editing. ### Logs and compliance reporting Every action a Digital Worker takes is recorded immutably. You can replay exactly what happened in any session, and export a compliance report on request. ### Organisation and cost governance Permissions by role, by workspace and by individual Digital Worker. Data isolation between business units. Cost, quality and performance for every Digital Worker in one place. ## The knowledge loop: the more you use it, the better it gets This is what separates EOS from a collection of disconnected tools. Daily work produces new knowledge, and that knowledge flows back into the platform: 1. **Work** - people and Digital Workers run thousands of tasks a day. 2. **Capture** - exceptions, better ways of working and customer insight are kept rather than lost. 3. **Confirm** - AI proposes, a domain expert confirms. An AI suggestion is a suggestion, not a conclusion. 4. **Enrich** - record the reasoning, the exceptions and the places where teams disagree. 5. **Publish** - once approved, the knowledge enters the shared library. 6. **Reuse** - every person and Digital Worker with permission can draw on it. Legal revises one contract clause and hundreds of sales Digital Workers use the new wording immediately. Finance updates a discount policy and every quoting flow follows. **One expert improves one thing, and the whole organisation benefits.** ## Who EOS is for | Audience | Main value | | - | - | | **Large enterprises** | Many departments on one platform, with central governance and audit | | **SMEs and startups** | Build a Digital Worker in minutes, without a large IT team to get started | | **Domain experts** | Hand repetitive work to Digital Workers and keep the work that needs judgement | | **IT and information security** | Policy enforced in the execution path, immutable logs, data isolated per workspace | EOS is designed for the work of every department: Finance, Sales, HR, Operations, Customer Service, Risk and Compliance. ## Where to start The documentation is split in two, matching the two ways people use the platform. > **FPT AI Workspace** > > For end users: chat with Digital Workers, work with Artifacts, get Digital Workers from the Digital Worker Marketplace and set up personal connections. > **FPT AI Console** > > For builders and administrators: create and edit Digital Workers, Instructions, Model, Skills, Connectors, Guardrails, publishing and organisation governance. If you are starting from scratch, we suggest this order: **1. Build your first Digital Worker** Go to the Console, describe in natural language what you want the Digital Worker to do, then refine the Instructions and choose a Model. **2. Load knowledge and connect your systems** Attach your business documents, add Skills and Connectors to your CRM, ERP or SharePoint so the Digital Worker can do real work. **3. Set the boundaries** Configure Guardrails - what the Digital Worker must not do, and which actions need human approval. **4. Test, then publish** Try it with the questions people actually ask, then publish and choose your deployment channels. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.