Frequently Asked Questions

BI tools rely on pre-designed dashboards; Qurify delivers instant analysis through natural language.

• BI tools (Tableau, Power BI) are optimized for visualizing predefined metrics — when a question isn't on the dashboard, you file a request with IT
• Qurify queries and analyzes data instantly with natural language, no upfront design required — business users find answers themselves
• Searches unstructured data (documents, manuals, reports) alongside databases, combining numbers with context
• Acts as a complement to BI, covering ad-hoc analysis and document-driven insights that BI can't reach

ERP AI is limited to the currently open screen; Qurify cross-analyzes across all tables.

• Most ERP AI features can only query data on the currently open screen — tracing root causes means manually opening multiple screens one by one
• Qurify connects data across tables and screens, along with related documents, by business terms, so a single natural language question performs cross-analysis and drill-down
• It doesn't replace your ERP — it adds an intelligence layer on top, keeping all core ERP functions exactly as they are

Simple SQL is possible, but enterprise-grade accuracy is another story.

• LLM alone: Must feed the entire schema — accuracy drops sharply past ~50 tables. Can't interpret internal jargon, and guesses join paths leading to wrong results
• Qurify + LLM: Using what it has learned about your terms and data, Qurify selects only relevant tables and passes them to the LLM, maintaining accuracy at scale
• Shows the tables, SQL, and documents behind each answer, and flags parts the data cannot confirm

Qurify doesn't replace your data platform — it connects to data where it already lives.

• Schema filtering: Only the tables needed for each question are passed to the LLM — maintaining accuracy at scale
• SQL pre-check: Generated SQL is validated before execution
• Federation: Connects multiple databases in a single query across heterogeneous systems
• Hybrid analysis: Combines SQL results and document search results in one answer

At its center are evidence-based answers and their verification, and it can be extended to support decisions within business procedures.

When connected to business procedures, it works in four steps:

1. Interpret — AI reads unstructured inputs (emails, PDFs) and organizes key items
2. Verify — Registered vendor, contract price match, and similar checks run against connected data; unconfirmed items are flagged
3. Process — Journal entries and notifications go through workflows the customer defines
4. Approve — High-risk items stop at a human approval gate (HITL)

AI organizes the evidence to support the decision; staff make the final call.

All major relational databases and cloud data warehouses are supported.

• Relational DBs: PostgreSQL, MySQL, MariaDB, MSSQL, and more
• Cloud DWs: Databricks, Snowflake, Amazon Redshift, etc.
• Document formats: PDF, Word, Excel, PowerPoint, HWP — via file upload or storage integration
• Extensibility: Specialized data sources connect through custom MCP connectors, with supported types continuously expanding

Yes, it connects to every data layer.

• Raw tables, preprocessed/transformed tables, and views are all supported equally
• Multiple layers can be connected simultaneously
• Recommended approach: Start with the processed layer your business teams actually query (views/mart tables), then expand to raw layers as needed — this keeps data connection quality high and minimizes noise

Yes, if you have them we use them. You can also start without them.

• Column aliases and descriptions are read automatically when connecting to the database
• An existing data dictionary or standard term glossary helps Qurify learn your company's terms
• Without a prepared glossary, Qurify learns your terms and what your data means on its own as it is used

Yes, MCP-based architecture enables standardized integration with a wide range of systems.

• Supported systems: SAP, Oracle ERP, Salesforce, plus groupware, internal wikis, and file servers
• Simple setup: Add data sources by configuring an MCP connector — no custom API development needed
• Flexibility: REST APIs and webhooks also supported for systems without MCP support
• Integration scope and approach are designed around your environment during consultation

Yes, DB (SQL) search and document (RAG) search are combined in a single agent.

• Supported formats: PDF, HWP/HWPX, DOCX, XLSX, CSV, TXT, and more
• Documents are split into chunks → vector embedded → semantic search performed
• Hybrid query example: "Pull last quarter's revenue trend from the DB and find the related contract terms from the contract PDF" → returns SQL results and document search results together

Yes. Databases stay where they are and are queried through a connection.

• Databases and warehouses: Qurify connects to your databases and queries the data it needs at question time, without copying it into a separate store
• Documents: PDF, HWP, Word, Excel, and other files are collected by upload or storage integration and then searched
• Secure environments: With an on-premise install, connection and search happen inside your network

Scope and method are designed around your environment during consultation.

Each answer shows what it was based on, what the data confirms, and what it does not.

• Evidence: The document location (passage) and the SQL used for database queries come with the answer
• Verification scope: Content confirmed by connected data is shown separately from content that is not
• Missing data: It tells you which data would be needed for verification but is not connected, so you can decide what to connect next

No. We start with one task and the data it needs.

• Scope: Together we decide which work to hand over first, which data to connect, and where it will be installed
• Pilot: A lead team uses it while answer quality is checked
• Roll out: Once quality is confirmed, use widens to the whole company and to new work agents

No one designs it by hand. Qurify learns your company's terms and what your data means as it is used.

• Data stays where it is and is connected with read access; the structure of source systems is not changed
• While teams ask questions and hand over work in their own business terms, Qurify learns what those terms and your data mean
• When the evidence is insufficient, it says it does not know instead of guessing

No need to register them in advance.

Qurify picks up the words your company uses as it is used.

A multi-layered system prevents and corrects errors.

• Source attribution: Every answer includes the original document location or SQL query for direct verification
• Automated evaluation: LLM Judge scores accuracy, evidence fidelity, and completeness in real time — low-confidence answers are flagged
• User ratings: Thumbs up/down ratings are used for improvement
• Monitoring: Admin dashboard tracks accuracy trends by query and proactively addresses recurring error patterns

This closed-loop structure means answer quality improves the more the system is used.

No fine-tuning. Your materials and what Qurify has learned are kept separate from the LLM.

• Commercial LLMs are used on a prompt basis — what Qurify learns about your terms and data is kept in Qurify, not in the LLM
• SQL generation runs with maximum-determinism settings for consistency
• No fine-tuning dependency means swapping AI models keeps what Qurify has learned
• Evidence comes from your own materials; the LLM reads and organizes it

Exact SQL text isn't guaranteed 100%, but 'result-level' reproducibility is maintained at a high level.

• Minor variations (column order, alias names) can occur due to the nature of AI
• Qurify narrows the search scope using what it has learned about your data, keeping results consistent
• Reproducibility checks run the same question multiple times and compare outputs
• Generated SQL is also pre-screened for syntax and executability errors

If the question falls within the connected data, it answers even without prior examples.

• Within the connected data — SQL is auto-generated based on what Qurify has learned about your data
• Outside coverage — it explicitly states "No related tables found" rather than fabricating an answer
• When new question types arise, connecting the data they need widens what it can answer
• Expanding data connections = expanding the AI's coverage

It keeps the answers that come out of work and the know-how only one person had, as company assets.

• What becomes an asset: Conversations with agents, documents such as reports and policies, and skills the agents build
• How it is kept: The Assetization Agent proposes asset candidates; once the owner approves, they are registered with their sources and processing history
• The results of work stay with the company even when people change

No. Only what the owner selects is registered as an asset.

• The agent only proposes results worth keeping
• Team sharing happens only for skills whose sharing scope an administrator has approved, after sensitive data and department boundaries are checked again
• Shared skills are versioned and can be withdrawn or rolled back at any time

No. What is shared is a way of working.

Employees who receive a skill use it only with data they already have access to. Skills that are used often rise in the ranking and are suggested first to employees doing similar work, and employees decide whether to use them.

Inquiry → understand the work and the data → setup (about a month) → operation. You choose between subscription (SaaS) and on-premise.

• Inquiry: Tell us one task you want solved and where the data lives; we reply within 2 business days
• Understand the work and the data: We learn the questions your teams keep asking, where the data lives, and your closed-network and security requirements
• Setup (about a month): Your data is connected where it lives while your FDE configures agents for the work you want covered. No one designs the ontology by hand; Qurify learns as it is used
• Operation: Teams work by chat, answers and know-how approved by their owners build up as company assets, and your FDE keeps adding agents for new work
• Subscription (SaaS): A monthly fee after setup. Base usage is set by company size; only usage above it is added
• On-premise: Installed on your own servers or inside a closed network. Pricing and base usage are explained in consultation after we understand your installation environment

Deliverables and criteria for each stage are agreed before we start.

On your servers or in your cloud, where it already is.

• We do not move your data to us; we connect to your ERP, business databases, and document stores
• We also build and operate on closed networks with no external connection — one system runs inside a government office building today
• By default, customer source data is not sent to external LLMs for training

No.

• Your ERP, business databases, and document stores stay as they are; we connect only the data you need
• Several systems can be connected at once and answered from one screen
• Rather than replacing your ERP's AI features, Qurify adds an evidence-verification layer on top

Yes.

• One system is installed inside a government office building and runs on the closed administrative network
• We take part in tendered projects and can help draft the functional specifications for an RFP
• The approach and contract form are set to match the institution's conditions

Enterprise-grade security is built in by default.

• Encryption: AES-256 for data at rest and in transit
• Access control: RBAC regulates access by user, department, and rank
• PII protection: Personally identifiable information is auto-detected and masked before AI answers are generated
• Audit trail: All queries, responses, and data access recorded for compliance
• Authentication: SSO/LDAP integration applies your existing auth system as-is
• Closed network: On-premise deployment supports fully air-gapped operation

Yes, AI models can be swapped freely.

• No fine-tuning dependency: Connection information lives in Qurify and the LLM is called via prompts — switching models doesn't require rebuilding knowledge assets
• On-premise LLM: If security policies restrict external API calls, deploy an open-source LLM on your own GPU servers for fully closed-network operation
• Any model with OpenAI API-compatible interface connects with a simple endpoint change

Today, Qurify is delivered as an independent web interface separate from your ERP.

• It connects to the ERP database to query data but isn't embedded inside ERP screens
• This is a deliberate design — as an independent system it isn't locked to any ERP, and it can connect multiple systems simultaneously for cross-analysis
• We are exploring embedding Qurify inside ERP screens based on production experience, with the ultimate goal of bringing natural language analysis into whatever environment users know best