Skip to Content
AiServa
Enterprise

Private AI for the Whole Company, Inside Your Own Walls.

The same AiServa platform, used company-wide: documents searched with the source page on every answer, repetitive work handled by agents with a human sign-off, and everything able to run inside your own network.

AiServa for Enterprise

Private AI for the Whole Company, Inside Your Own Walls.

The same local AI server, scaled into a company platform: a private knowledge base that answers from your own documents with sources, document processing that reads reports, quotations and invoices, and workflow agents that take on the repetitive multi-step work. With local models, every model, document and vector stays on hardware your company owns; cloud models are used only if you add your own key.

Everything on this part of the page is built from the same AiServa features every workspace has: knowledge bases, skills, MCP servers, approvals and roles, set up by your own administrators. VYROX can help with larger rollouts, private-network or air-gapped deployments, and custom MCP servers if you want it to.

A graphite AI server rack with a violet-lit honeycomb front inside a glass-walled company server room, seen from a bright open-plan office where staff work at laptops

What Company-Wide Teams Ask About

Eight topics, in the order most IT, operations and management teams ask about them. Each links to the detail further down this page.

  1. dns 01 How Private Local AI Works Where the models run, and how company data stays inside your own infrastructure.
  2. travel_explore 02 Document Q&A and RAG Search and ask across company documents, with a source reference on every answer.
  3. description 03 Document Processing Extraction, summarisation, review and preparation of business documents.
  4. account_tree 04 Workflow AI and Agents Multi-step, repetitive processes handled by agents with a human sign-off.
  5. fact_check 05 Enterprise Use Cases Knowledge answers, extraction, quotation comparison, contract review and more.
  6. hub 06 Integration ERP, HR, email, file shares and document repositories you already run.
  7. memory 07 Hardware and Infrastructure What a rollout needs, and how it grows company-wide.
  8. admin_panel_settings 08 Access, Security and Audit Role-based access, audit trails, and offline or air-gapped deployment.
01 / Private Local AI

Four Layers, All on Your Side of the Firewall.

A private AI environment is not one model in a box. It is four layers working together, and every one of them runs on the AiServa server in your building, not in someone else's cloud.

Your Company Data

  • folder_shared Documents you upload, or save from a task
  • inventory_2 ERP and accounting, via MCP servers
  • groups HR and other systems, via MCP servers
  • mail Email through your own SMTP
  • scanner Scans and photos

dns AiServa Server, on Your Premises

account_tree

Applications and Agents

AI Agent with its tools, Knowledge Bases, Skills, Commands, Plugins, MCP Servers and workflow agents.

psychology

Language and Vision Models

Open-weight models that read, reason, summarise and write. Scans and photos read by a local vision model.

scatter_plot

Embedding Model and Vector Database

Turns every passage into a searchable vector, kept in the built-in vector store or Qdrant with its source.

shield

Access, Audit and MCP Servers

Sign-in, roles, document permissions, the audit log, Agent Runs, and the MCP servers that link to your systems.

Your People

  • laptop Browser on the office network
  • smartphone Phone, through the encrypted connection
  • desktop_windows AiServa Desktop and the Chrome extension
  • forum Phone home-screen app
  • api Your own systems via the API and webhooks

What Stays Inside

Source documents, extracted text, embeddings, the vector index, prompts, answers, task history, audit logs and the models themselves. None of it goes to a cloud AI provider unless your organisation adds its own key and chooses a cloud model.

What Crosses the Tunnel

In connected mode, the encrypted session between a signed-in user and your own server, over the outbound-only connection described under Security and Privacy.

What Needs No Internet

Everything, if you choose. In private network or air-gapped mode the portal, models and knowledge base all run on the LAN, and updates arrive on verified offline media.

02 / Private Document Q&A and RAG

Ask Your Documents. Get the Page It Came From.

Retrieval-augmented generation (RAG) means the AI does not answer from memory. It first searches your own documents, reads the most relevant passages, and only then writes an answer, citing the file, page and section it used. If your documents do not contain the answer, it tells you instead of inventing one.

  • check_circle Every answer carries numbered source references you can open
  • check_circle Ask in English, Bahasa Malaysia or Chinese, across documents in any of them
  • check_circle Staff only see answers drawn from documents they are allowed to open
  • check_circle New and edited files are picked up automatically, old versions drop out
An operations manager at a pale oak desk reading an AI answer with numbered source citations beside a highlighted page of the source document on her monitor

The Pipeline, Stage by Stage

What happens between a document landing in a Knowledge Base and a cited answer appearing on screen, all under your control. The RAG deep dive covers embedding models, vector databases, chunking and evaluation in detail, with a vector index sizing calculator.

  1. cable01

    Connect

    Documents are uploaded into organisation, department or private knowledge bases, one by one or as a ZIP, or saved straight from a task.

    Engineering: Office files, PDFs up to 5,000 pages, scans, text and data files; originals kept on your server.

  2. document_scanner02

    Parse

    Text, tables and headings are pulled out of PDF, Word, Excel, PowerPoint, email and scanned images.

    Engineering: Layout-aware parsing keeps tables as tables. Local OCR for scans and photos, including English, Bahasa Malaysia and Chinese.

  3. segment03

    Chunk

    Each document is split into passages that make sense on their own, keeping the heading they sit under.

    Engineering: Structure-aware passages of about 1,200 characters, never cut mid-sentence, tables kept whole or split between rows with the header repeated, each tagged with its file and nearest heading.

  4. scatter_plot04

    Embed

    Every passage is turned into a vector: a list of numbers that captures what it means, not just which words it uses.

    Engineering: A multilingual embedding model runs on your server by default. An OpenAI-compatible embedding API is used only if you choose one.

  5. storage05

    Index

    Vectors and their metadata are stored in the built-in vector store or in Qdrant. Only vectors and ids go to Qdrant; the text stays on your server.

    Engineering: An approximate nearest neighbour index (HNSW is the most common type), with a keyword index such as BM25 added in enterprise implementations where exact identifiers matter.

  6. manage_search06

    Retrieve

    A question is embedded the same way, and the closest passages are found by meaning and by exact terms at once.

    Engineering: Hybrid search merges semantic and keyword results, so part numbers, clause numbers and names are never missed.

  7. sort07

    Rerank

    A second, more careful model reads the shortlist and puts the genuinely relevant passages first.

    Engineering: A reranking model (usually a cross-encoder) rescores the top 20 to 50 candidates. Only the best few reach the answer model.

  8. format_quote08

    Answer

    The local language model writes the answer from those passages only, and cites each one.

    Engineering: Grounded prompting with citation markers. If the documents do not say, the assistant says so instead of guessing.

The Engineering Choices Behind It

These are the layers of any private RAG system; AiServa ships its own for each, and the examples show common alternatives. The architecture is vendor-neutral: every layer can use any capable component. The right-hand column lists popular examples only, and the RAG deep dive shows common complete stacks.

ComponentWhat It DoesWhy It MattersPopular Examples
Document Parser and OCRTurns PDF, Office files, email and scans into clean text, headings and tablesTables and scans are where most RAG accuracy is won or lost.Apache Tika, Unstructured, Docling, Tesseract, PaddleOCR, a local vision model
Embedding ModelConverts each passage and each question into a vector that captures meaningDecides whether a question in Bahasa Malaysia finds a policy written in English. Evaluated on your own documents before go-live.BGE-M3, multilingual-E5, Qwen3-Embedding, nomic-embed-text, Jina, GTE
Vector Database or Vector IndexStores vectors with their metadata and finds the nearest ones to a question quicklyScale, filtering and what your IT team already runs decide the choice, not the brand.PostgreSQL + pgvector, Qdrant, Milvus, Weaviate, Chroma, LanceDB, Elasticsearch or OpenSearch, Redis, FAISS
Keyword IndexFull-text search alongside the vectors (for example BM25)Exact identifiers (PO numbers, part codes, clause 14.2) are matched reliably, which pure vector search can miss.Built into most vector databases and search engines, or a separate full-text index
RerankerA second model that rescores the shortlist for true relevanceLifts answer quality far more cheaply than a bigger language model.bge-reranker, Jina reranker, ms-marco cross-encoders
Answer Model (LLM)An open-weight large language model, sized to your AiServa server, that writes the answer from the retrieved passagesSwappable as better open models are released, without rebuilding the knowledge base.Qwen, Llama, Gemma, Mistral families, served by Ollama, llama.cpp or vLLM
OrchestrationThe code that connects parsing, retrieval, reranking and the model into one pipelineKeeps the pipeline testable and lets each component be replaced independently.LlamaIndex, LangChain, Haystack, or a lean custom pipeline
Access FilterKnowledge base access rules applied on the server at every searchA staff member only gets passages from knowledge bases and documents they are allowed to use.Named People Only, Department or All Staff, with Allow or Deny per person or role
FreshnessRe-indexing when documents changeSuperseded versions are replaced, so an answer never quotes last year's price list or policy.Replace or re-upload a file; bulk ZIP import
EvaluationA test set of real questions with known answers from your own documentsRetrieval hit rate and citation accuracy are measured before rollout and after every change.RAGAS, TruLens, DeepEval, or a custom test harness

scatter_plot Embedding Models, in Plain Terms

An embedding model reads a passage and places it at a point in a space of several hundred to a few thousand dimensions, so that passages with similar meaning sit close together. "Leave entitlement for new staff" lands near "annual leave in the first year" even though they share few words.

We choose the model for three things: the languages in your documents, the length of passages it handles well, and its measured retrieval accuracy on your own test questions. Changing the model later means re-embedding the library, which the server does in the background.

storage Vector Databases, in Plain Terms

A vector database stores those points and finds the nearest ones to a question in milliseconds, using an approximate nearest neighbour index (commonly HNSW) rather than comparing against every passage. Alongside each vector it keeps the metadata that makes answers trustworthy: source file, page, date, department and who may see it.

For a pilot of tens of thousands of passages, a compact embedded database is enough. For millions of passages, many departments and heavy filtering, a dedicated vector database server is used, with its index backed up like any other company database.

Top-down view of an inspection report, a supplier quotation and a delivery order with fields outlined in violet, beside a tablet showing the extracted values as a table
03 / Document Processing

Reads the Paperwork So Your Team Can Decide.

Most business documents are read once, retyped once and filed. AI document processing reads them in any layout, including scans and phone photos, and hands back structured data, a summary, a review note or a first draft, with anything uncertain sent to a person. AI Agent's File Tools, PDF Tools and OCR Reader are the ready-made starting points; an enterprise deployment extends them to your own document types and systems.

data_object

Extraction

Fields, line items and tables from invoices, POs, delivery orders, certificates and forms, into JSON, Excel or straight into your ERP after review. Each value carries a confidence score and a pointer to where it was found.

summarize

Summarisation

Long reports, contracts, minutes and email threads reduced to a fixed format: key points, figures, decisions, open actions and risks, with links back to each source paragraph.

rule

Review

A document checked against a checklist, a specification, a contract standard or another document: missing items, mismatches, out-of-limit values and non-standard clauses, each with a page reference.

edit_document

Preparation

First drafts of reports, letters, NCRs, tender responses and replies, written in your house format from your templates and past documents, for a person to finish and sign.

Human in the Loop by Design

Nothing is posted, sent or approved on confidence alone. Each document type gets a threshold: above it, the result goes to a reviewer's queue ready to accept; below it, the uncertain fields are highlighted on the original page for correction. Every correction is logged and used to improve the prompts and rules for that document type.

04 / Workflow AI and AI Agents

The Multi-Step Jobs, Done the Same Way Every Time.

An AI agent is a language model that can take steps: read a document, look something up in the ERP, compare, draft, and hand the result to the right person. On AiServa, the agent runs on AI you own, can only use the tools you allow, and stops for a human decision at every point that matters.

A procurement officer and a QA engineer reviewing a wall display that compares three supplier quotations side by side under a simple approval flow diagram

How an Agent Runs a Quotation Comparison

One example of twelve. See workflow automation for the patterns, guardrails and a workflow for each profession.

  1. 01 Trigger

    Quotations arrive in purchasing@ against RFQ 2291.

  2. 02 Read

    Each PDF is parsed and its items, prices and terms extracted.

  3. 03 Look Up

    The RFQ, last purchase prices and approved vendor list are fetched from the ERP.

  4. 04 Compare

    Quotes are normalised and compared; deviations and risks flagged.

  5. 05 Approve

    The buyer reviews the table and recommendation, then approves or edits.

  6. 06 Record

    A draft PO is prepared, and Agent Runs records each step the agent took.

Good First Candidates

  • arrow_right Supplier quotation comparison and PO preparation
  • arrow_right Invoice to PO to delivery order three-way matching
  • arrow_right Report review against a specification, with a draft follow-up
  • arrow_right Shared inbox triage with draft replies
  • arrow_right Monthly management report compilation
  • arrow_right New-hire onboarding packs and policy acknowledgements

Guardrails on Every Agent

  • verified_user An allow-list of tools and systems per agent, read-only by default
  • verified_user Approval steps before anything is sent, posted or paid
  • verified_user Runs under the requesting user's permissions, never an all-access account
  • verified_user Step limits and time-outs so a run can never loop
  • verified_user A full trace of what it read, decided and proposed
05 / Enterprise Use Cases

Nine Jobs Companies Start With.

Each one is a real, repeating task with a clear input, a measurable output and a person who signs off. Open any card for what goes in, what the AI does, and what comes out.

support_agentInternal Knowledge Assistant expand_more
What Goes In
SOPs, work instructions, manuals, policies, past project files and meeting minutes.
What the AI Does
Answers staff questions in plain language from the company's own documents and shows which document and passage the answer came from.
What Comes Out
Fewer repeated questions to senior staff, and new hires who find the right procedure on day one.
AiServa Features Used
Knowledge Bases, AI Agent, Memory
document_scannerDocument Extraction expand_more
What Goes In
Invoices, delivery orders, purchase orders, claims forms and shipping documents, scanned or digital.
What the AI Does
Reads each document, pulls out the fields that matter, checks totals and cross-checks related documents you provide.
What Comes Out
An Excel sheet or CSV ready to review and post, with anything unclear flagged for a person.
AiServa Features Used
OCR Reader, File Tools, Skills
request_quoteQuotation Comparison expand_more
What Goes In
Three or more supplier quotations in different layouts, plus the original request.
What the AI Does
Extracts item, quantity, unit price, lead time, payment terms, warranty and exclusions, and lines the quotes up item by item.
What Comes Out
A side-by-side Excel comparison with every deviation from the request called out.
AiServa Features Used
File Tools, Skills, Approvals
gavelContract and Compliance Review expand_more
What Goes In
Supplier and customer contracts, NDAs, tenders and regulatory circulars.
What the AI Does
Compares a contract against your standard positions kept in a knowledge base, lists non-standard clauses, renewal dates and obligations, and checks a document against a checklist.
What Comes Out
A clause-by-clause review note with page references, ready for legal or management to decide.
AiServa Features Used
Knowledge Bases, Skills, File Tools
badgeHR Policy and Onboarding expand_more
What Goes In
Employee handbook, leave and claims policies, benefits schedules and onboarding checklists.
What the AI Does
Answers policy questions for each employee from the handbook, and drafts letters and onboarding packs for HR.
What Comes Out
Consistent answers to the same HR questions, and HR time back for the cases that need judgement.
AiServa Features Used
Knowledge Bases, Commands, File Tools
mark_email_unreadEmail Replies and Follow-Ups expand_more
What Goes In
Emails pasted or attached to a task, with your policies in a knowledge base.
What the AI Does
Drafts a reply grounded in your policies and past answers, as a card a person reviews and sends.
What Comes Out
Ready-to-send drafts, or sends through your own SMTP to addresses you typed.
AiServa Features Used
Email, Knowledge Bases, Commands
summarizeManagement Reporting and Summaries expand_more
What Goes In
Monthly reports from departments, board papers and long email threads.
What the AI Does
Summarises each report, pulls out the numbers and exceptions, and compiles them into one brief in your format.
What Comes Out
A short brief as Word or PDF, with every source listed.
AiServa Features Used
AI Agent, File Tools, Skills
assignmentTender and RFP Preparation expand_more
What Goes In
An incoming tender document plus your library of past submissions, company profile and certificates.
What the AI Does
Breaks the tender into requirements, finds the best past answer for each in your knowledge base, and drafts a compliance matrix and first-draft responses.
What Comes Out
A requirement checklist and response draft for the team to refine, instead of a blank page.
AiServa Features Used
Knowledge Bases, Skills, File Tools
fact_checkReport Review Against a Specification expand_more
What Goes In
Inspection, test or audit reports and the specification or checklist they should meet.
What the AI Does
Reads each report, compares the results with the specification and flags anything out of tolerance or missing.
What Comes Out
A summary table of exceptions and a draft follow-up for a reviewer to confirm.
AiServa Features Used
Knowledge Bases, OCR Reader, File Tools
A compact AiServa server on an office shelf with violet light lines reaching across the office to staff screens showing a spreadsheet, a staff directory, an email inbox and document folders
06 / Integration

Works with the Systems You Already Run.

No rip and replace. The AI server connects to your document repositories, ERP, HR system, email and sign-in through standard interfaces, starting read-only, and writes back only where a use case needs it and a person has approved it.

SystemHow It ConnectsWhat the AI Does With It
folder_sharedDocuments and Files Upload files or ZIP archives (25 files, 100 MB) into organisation, department or private knowledge bases; originals kept on your server. Searches and answers with citations, under each person's access rights.
inventory_2Business Systems (ERP, CRM, HR) An MCP server for the system, added by your administrators and set to ask before every use or not. Looks up records through the MCP server's tools; anything that changes data can be set to ask first, with Approvals for sign-off.
mailEmail Your organisation's own SMTP server, or drafts a person sends. Sends reviewed replies and the files a task produced.
apiYour Own Software The REST API v1, where your systems start AI Agent tasks, collect answers and files and search knowledge bases, plus signed webhooks, AiServa Desktop and the Chrome extension. API tasks run under your Rules and appear on Agent Runs; webhooks tell your systems when they finish.

Integration principles: MCP server keys stay sealed on the server, each MCP server asks before use unless you say otherwise, individual MCP server tools can be switched off, and anything that needs sign-off goes through Approvals. Tasks your own systems start through the API have nobody to ask, so anything that would ask is refused, and they are read-only unless the key has Allow Actions.

07 / Hardware and Infrastructure

Start with One Server. Grow Without Starting Over.

A company-wide rollout starts with one capable AI server, a network point and a place to put it. Growing adds servers, not a new platform: knowledge bases, apps, users and audit history carry forward. The console shows which models fit each server.

A small AiServa server on a credenza in a modern headquarters office, with a larger rack server room visible through glass in the background
Step 1

One Team

dnsOne server or your own cloud keys

One team, a first knowledge base and one repeating job.

  • check_circleCreate the workspace and invite the team
  • check_circleUpload the team's key documents
  • check_circleTurn the repeating job into a skill or command
  • check_circleCheck the answers against the sources
Step 2

Departments

dnsAdd servers as needed

More teams, department knowledge bases and the first MCP servers.

  • check_circleRoles, departments and record levels
  • check_circleMCP servers for the systems people use
  • check_circleApprovals for access and sign-off
  • check_circleAgent Runs and the audit log for IT
Step 3

Company-Wide

dnsSeveral servers, one workspace

Every department and branch, large document collections, many people at once.

  • check_circleMore AI servers paired to the same workspace
  • check_circleOrganisation skills and memory everyone shares
  • check_circleAiServa Desktop and the Chrome extension
  • check_circleOptional private-network or air-gapped deployment by VYROX

What a Rollout Needs From Your IT Team

folder_shared The first documents to load into a knowledge base

key Staff email addresses, roles and departments

backup A backup target for indexes and settings

quiz 30 to 50 real questions with known answers, to check accuracy

Power, network, placement and noise are covered under Living With a Machine in the Building, and the order to roll it out to people under Move Over in Pieces.

08 / Access, Security and Audit

Controlled, Recorded, and Able to Run Offline.

The questions an IT manager, a compliance officer and an auditor ask: who can see what, where the data sits, what is recorded, and whether it can run with no internet at all. Here are the answers.

A locked graphite server rack with a violet-lit front in a secure comms room, its network cables unplugged and coiled to show an air-gapped deployment, beside an access log clipboard

manage_accountsUser Access Control

  • check_circleStaff sign in with their own accounts and TOTP two-step sign-in; a Sign-In Policy can require two-step for everyone and limit sign-up to your email domains.
  • check_circleRoles, per-user permissions and per-tool rights decide which tools, Knowledge Bases and Apps each person can use.
  • check_circleKnowledge base access (Named People Only, Department or All Staff, with Allow or Deny) is enforced at every search.
  • check_circleSeparate knowledge bases per department, for example HR, Finance and Engineering.

lockData Security

  • check_circleWith local models, models, documents, vectors and AI Agent task history stay on hardware inside your premises.
  • check_circleProvider keys, MCP server keys and mail passwords are sealed at rest; API and pairing tokens are stored as hashes.
  • check_circleCloud AI is called only if your organisation adds its own key; with local models no outside AI API is used for embedding, retrieval or answering.
  • check_circleEach person can switch memory off and delete their saved memories and task summaries.

receipt_longAuditability

  • check_circleAn audit log records administrator changes, and Agent Runs keep the history of every task: where it came from, its tool calls, questions and refusals.
  • check_circleApprovals keep a timeline of who asked, who decided and when.
  • check_circleFile Sharing keeps a full history of every shared file.
  • check_circleCitations mean every answer can be checked against its source document.

wifi_offOffline and Air-Gapped

  • check_circleConnected mode: the standard AiServa setup, reached through the outbound-only connection.
  • check_circlePrivate network mode (optional VYROX deployment): the portal runs on your own LAN.
  • check_circleAir-gapped mode (optional VYROX deployment): fully disconnected; updates arrive on verified offline media.
  • check_circleThe same AI Agent and Knowledge Bases work in all three modes; web search, browser tasks and cloud models need internet.

Three Deployment Modes

QuestionConnectedPrivate NetworkAir-Gapped
Where AI RunsYour serverYour serverYour server
Access from Outside the OfficeYes, via outbound-only encrypted tunnelOnly over your own VPNNo
Internet Needed Day to DayYes, outbound onlyNoNo, physically disconnected
How Updates ArriveAutomatic, maintained by VYROXScheduled window or offline mediaVerified offline media only
SuitsMost SMEs and multi-site teamsRegulated firms with a strict perimeterDefence, R&D, highly sensitive IP

See It Working on Your Own Documents.

Create a workspace, upload a handful of real documents (a policy manual, three quotations, a contract) and give the AI Agent a real task. Free for 14 days with every feature.

Questions, Answered

Can multiple people in my company use the same local AI server?expand_more

Yes. One AI server serves many staff accounts, each with their own sign-in, role, department and permissions. Administrators decide which tools, Knowledge Bases and records each person can reach. Capacity depends on the server, and more servers can be added to the same workspace.

What is RAG, and how does AiServa use it for company documents?expand_more

RAG (retrieval-augmented generation) means the AI searches your own documents first, reads the most relevant passages, and only then writes an answer, citing the sources it used. AiServa Knowledge Bases do this with local embedding models on your server or any OpenAI-compatible embedding API you choose, and a built-in vector store or Qdrant, where only vectors and ids are stored and the text stays on your server. If the documents do not contain the answer, the agent says so rather than guessing.

Which embedding model and vector database does AiServa use?expand_more

Knowledge Bases use a local embedding model on your server, or an OpenAI-compatible embedding API if you choose one, with either the built-in vector store or Qdrant per Knowledge Base. Search combines keyword and meaning search with a similarity floor set for each embedding model and an optional reranker, every answer cites its sources, and the RAG Lab shows each stage of a search.

Can AiServa connect to our ERP, HR system, email and file shares?expand_more

Yes. AI Agent can use your own MCP servers and send through your organisation's SMTP. Through the REST API your systems can start AI Agent tasks, collect the answers and files, and search knowledge bases, and signed webhooks tell them when things happen. Any system with an MCP server can be connected by your own administrators, each MCP server set to ask before every use or not. VYROX can also help build MCP servers if you prefer.

Can it run fully offline or air-gapped?expand_more

Yes, as an optional VYROX deployment service. Besides the standard connected mode, AiServa can run in private network mode, with the portal on your own LAN, or fully air-gapped, with models and updates delivered on verified offline media. Web search, browser tasks and cloud models are not available without internet.

What hardware does a company-wide rollout need?expand_more

Usually one capable AI server to start with one department, plus a network point, a ventilated space and a backup target. Growing company-wide adds servers to the same workspace rather than a new platform. The console shows which models fit each server.

Create your own AiServa workspace.

Free for 14 days with every feature. Sign up, pair your own AI server or add your own cloud keys, invite your team and give the AI Agent a real task.