A product of BEAS Solution

Generic AI Report

Ask your data. Ship the answer.

Natural-language questions become reusable widgets, shared metrics, and executive dashboards — grounded in approved business rules, running on your own OpenSearch and LLM.

Sign in to Report Explore capabilities

Built for enterprises that keep identity, search, and files inside their environment.

Capabilities

From a question to an operating board

One platform for ad-hoc answers, reusable analytics, and governed data prep — without moving your data out of your control.

Natural-language report

Ask in plain language. Get text, HTML, tables, charts, or KPIs — and turn strong answers into widget drafts in one step.

Widgets & shared metrics

Build a library of ECharts, tables, and HTML widgets. Share dashboard queries so one metric definition drives many boards.

Executive dashboards

Drag-and-drop layouts with a common date range, cross-filters, drill-down, live or frozen share links, and export to PDF or Excel.

AI Guide grounding

Upload approved policy PDFs and index dictionaries so answers stay aligned with how your business actually works.

Data prep & adaptors

Prepare reporting indices from OpenSearch, PostgreSQL, MongoDB, CSV, and Excel — with PII controls and approval gates.

Anomaly monitoring

Schedule detectors, triage incidents, and keep human approval before any operational write from chat-driven drafts.

How it works

Your workspace. Your keys. Your cluster.

Each customer owns a workspace with bring-your-own LLM and OpenSearch. Identity stays with you — role-based access, invites, and full audit trails.

  1. 01

    Connect

    Configure your LLM provider and OpenSearch endpoint. Test connections, then unlock report and live boards.

  2. 02

    Ask & refine

    Chat against approved indices. Prefer chart, table, or narrative output. Save strong replies as widgets.

  3. 03

    Operate

    Assemble dashboards, schedule anomaly runs, share securely, and keep every view and export in the audit log.

Start here

From registration to your first answer

Each customer owns a workspace with bring-your-own LLM and OpenSearch. Create an account, verify email, connect your stack, then ask questions in natural language.

Getting started

What you can do

Ad-hoc questions in Report, reusable widgets, executive dashboards, shared metric DSL, anomaly monitors, data prep, file ingest, AI Guide grounding, and full audit trails.

  1. Register a workspace and verify email
  2. Sign in, then complete LLM + OpenSearch setup
  3. Invite teammates when you are ready

Accounts

Username & password SaaS login

Create a workspace on register, or join through an invitation. Email verification is required before the first sign-in. The registration owner becomes Tenant admin.

  • Workspace name, email, username, password
  • Verify via inbox link or resend from verify-email
  • Forgot / reset password when mail is configured

Workspace

Connect your LLM and OpenSearch

Report chat and live dashboards unlock only after both connection tests pass. Secrets are encrypted at rest; leave password fields blank to keep stored values.

Workspace setup

Guided wizard for Tenant admins

Step 1 — choose OpenAI, Ollama, or OpenAI-compatible; set base URL, API key, chat and embedding models. Step 2 — OpenSearch URL, credentials, optional insecure TLS for labs. Then test connections and finish.

  • Setup incomplete: shell may open; chat and boards stay locked
  • “I’ll configure later” defers the gate for this session
  • Both tests OK → setup complete and product unlocks

Workspace settings

Credentials, tests, and members

Tenant admins manage BYO credentials, re-run connection tests, invite members, and remove teammates. Status chips show LLM and OpenSearch verification at a glance.

  • Save LLM / OpenSearch fields without re-entering secrets
  • Test connections to clear setup deferral
  • Invite with Tenant admin, User, Reporter, or Viewer roles

Product

Screens that turn questions into operating boards

The same capabilities documented in the in-product guide — Report, widgets, dashboards, governed data paths, and monitoring.

AI Report

Natural-language workspace

Ask against OpenSearch with optional index scope and output preference. Get text, HTML, tables, charts, or KPIs; answer clarifications; save widget drafts; use history, voice input, and print.

OpenAPI catalogs

Registered HTTP APIs via MCP

Point Report at OpenAPI catalogs so the assistant can list, get, summarize, and propose patches — with human approval before any mutation applies.

Dashboards

Executive boards

Combine widgets and decorations with layout presets, a shared date range, cross-filters, drill-down, live or frozen share links, and PDF / Excel / email export.

Widgets

Reusable visualizations

Library of ECharts, tables, text, and HTML widgets with studio, versions, import/export, mapping hints, and admin index approval for pending definitions.

Dashboard queries

Shared metric DSL

One validated query definition referenced by many widgets — keep executive metrics consistent across boards.

Anomalies

Scheduled detection

Define monitors, run now or on schedule, triage open incidents, and keep human approval before chat-driven operational writes.

Data prep

Visual pipelines

Read from adaptors or OpenSearch, map fields across a graph, and write staging or production reporting indices that chat and widgets can query.

Ingest

CSV / Excel under governance

Load files into granted indices with staging or production environments, bulk size control, PII rules, schemas, and job-level failure detail.

Data adaptors

PostgreSQL, MySQL, MongoDB

Store encrypted connection settings once; Data Prep adaptor nodes reference the id — passwords never land in published graph JSON.

AI Guide

Ground answers in policy

Upload business-rule PDFs and approve index-mapping analyses so Report cites approved RAG chunks instead of guessing field meanings.

Logs

Audit & business errors

Trace who viewed, exported, or changed configuration. Investigate business exceptions with filterable admin tables.

Access

Roles that match how teams actually work

The sidenav hides what you cannot use; the API still enforces access on every request.

Roles and access

Workspace roles

Tenant admin Setup, credentials, invites, approvals, all product menus
User Analyst builder — Report through data prep, adaptors, and logs
Reporter Report, dashboards, widgets, and shared queries
Viewer Open boards in view mode — no create, edit, share, or export

Super Admin

Platform operators

Platform admin users land on the Super Admin portal — not tenant Report. They manage mail, every workspace’s BYO settings, users, invitations, and operational logs.

  • Mail settings for verification, invites, and scheduled exports
  • Workspaces list — edit LLM / OpenSearch per tenant
  • Users, invitations, audit logs, business errors

Architecture

Your keys. Your cluster. Our application plane.

A browser SPA talks to a Spring Boot API. Application documents live in MongoDB; files in MinIO. Each workspace brings its own LLM and OpenSearch.

Layers

Runtime stack

  • React SPA with role-aware shell and i18n
  • Spring Boot API, REST + STOMP progress
  • MongoDB for product documents
  • Customer OpenSearch for reporting & RAG
  • Customer LLM for chat and embeddings

Configuration

Workspace-scoped BYO

LLM provider, base URL, models, and OpenSearch endpoint are configured per workspace. Platform mail and branding stay with operators. Feature flags gate prep, ingest, and related admin surfaces.

Capability catalog

Visible screens, mapped APIs

Accounts, setup, Report, dashboards, widgets, anomalies, data prep, ingest, adaptors, AI Guide, OpenAPI catalogs, logs, and Super Admin — each backed by documented API families under the product context path.

Security & governance

Designed for controlled AI — not shadow IT.

Credentials are encrypted at rest. Secrets never reappear in the UI. Access follows roles. Anomaly and OpenAPI mutations wait for human approval.

  • Encrypted storage for LLM, OpenSearch, and data-adaptor secrets
  • OIDC / Keycloak-ready identity with tenant isolation
  • PII redaction, hashing, and partial masking on ingest
  • Audit trails for views, exports, and administrative actions
Sign in to your workspace

Ready when your data is.

Sign in to BEAS Generic AI Report and start with the questions your leadership already asks.

Go to Sign in

BEAS Solution

Efficiency through AI

Enterprise software for intelligent automation, document operations, and AI-native reporting — headquartered in Podgorica, Montenegro.

Address
Business Tower Montenegro
Bulevar knjaza Danila Petrovica 13/32
81101 Podgorica, Montenegro

Email
contact@beassolution.com

Web
beassolution.com

Product login
report.beassolution.com