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: The data connection structure selects only relevant tables and provides pre-verified join paths and business rules, 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: The data connection structure selects only the tables needed for each question — maintaining accuracy at scale
• Join-path verification: Only pre-verified paths are used, with SQL 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, existing assets can be imported and reused.

• Column aliases and descriptions are collected automatically when connecting to the database
• Synonym dictionaries can be bulk-imported via CSV or registered through the conversational curation tool
• Existing semantic layers, data dictionaries, and standard term glossaries are all supported
• Qurify builds them into its data connection structure, adding table relationships and join-path verification on top of the glossary

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. Qurify connects data in stages under the principle that simpler is better.

• Levels 1–2: Map core business data to standard terminology
• Level 3: Connect unstructured materials such as contracts and emails
• Levels 4–5: Research and experimental

Each level goes through 'ping-pong' verification — a back-and-forth on semantic definitions with your team — and is promoted only once fully validated, so you control risk while seeing results fast.

Through a 4-step automated pipeline.

1. Description generation — AI reads table/column metadata from your DB schema and auto-generates natural language descriptions
2. Physical structure mapping — Schema → table → column relationships are structured
3. Existing SQL incorporation — Join patterns and filter conditions from business teams' existing report SQL are integrated
4. Semantic layer extraction — AI analyzes everything to auto-extract synonyms, business rules, domain categories, and join paths

Staff review and adjust the resulting structure, and questions outside the registered scope get a stated limit rather than a guess.

The structure is rebuilt and swapped in atomically — no service interruption.

• Previous customizations (synonyms, business rules) are preserved after rebuild
• Even at hundreds of tables, rebuild finishes in minutes to tens of minutes
• Rebuild cycles can be automated with a scheduler
• Incremental sync (updating only changed parts) is planned for a future release

Yes, the AI uses them right away.

For example, registering 'COGS' as a synonym for a specific column means any question mentioning 'COGS' will be routed to the correct data.

Three ways to register:

• Conversational curation tool — type in natural language (e.g., "COGS means the same as cost_detail.total_amount")
• AI suggestions — review and confirm synonyms the AI proposes while building the data connection structure
• CSV bulk import — import an existing data dictionary at once

Yes, registering 'example SQL' serves two purposes.

• Connection strengthening: Join patterns and filter conditions from those queries are analyzed and added to the connection structure
• Pattern learning: When similar questions come in, the same query patterns are referenced
• Accuracy benchmark: Registered example SQL is also used to compare AI-generated SQL results against known-correct results for accuracy measurement

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 feedback: Thumbs up/down continuously improves the data connection structure and prompts
• 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 the data connection structure are kept separate from the LLM.

• Commercial LLMs are used on a prompt basis — connection information such as business terms and join paths is stored separately in Qurify
• SQL generation runs with maximum-determinism settings for consistency
• No fine-tuning dependency means swapping AI models doesn't require rebuilding your connection information
• 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
• Schema filtering based on the data connection structure and example SQL patterns ensure result consistency
• 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 registered tables, columns, and join paths — SQL is auto-generated from connection information
• Outside coverage — it explicitly states "No related tables found" rather than fabricating an answer
• When new question types arise, adding relevant tables and business terms makes them immediately answerable
• Expanding data connections = expanding the AI's coverage

As long as join paths are registered in the data connection structure, accuracy holds even with multi-table joins.

• 3–4+ joins use only pre-verified paths — unregistered join paths are never generated
• Aggregation errors from 1:N relationships (fan-out) are prevented by defining aggregation rules or registering correct SQL patterns
• The key accuracy variable isn't the number of joins — it's whether those join paths have been registered and verified

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): The Ontology Agent ties your data into an ontology while your FDE configures agents for the work you want covered
• Operation: Teams work by chat 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