Canonical: https://molo17.com/solutions/ai-as-sql/ Markdown mirror: https://molo17.com/solutions/ai-as-sql/index.md Title: AI as SQL on Query Forge | Gluesync solutions | MOLO17 Description: Ask federated Gluesync agents in natural language from JDBC — answer + reviewable SQL draft. Gluesync 2.3. Solutions · Gluesync 2.3 # AI as SQL — ask any LLM with Query Forge You already speak SQL when you need a precise answer. Sometimes you want to ask first. AI as SQL puts that ask on Query Forge: one `jdbc:gluesync://` connection, your identity, a normal result row with an answer and an optional SQL draft. You review. You run. Not another chatbot bolted onto sync. Not a free pass past your permissions. Coming in Gluesync 2.3 [Book a demo](/book-a-demo/) [Request early access](/contacts/?topic=ai-hub#contact-form-section) Query Forge · gluesync.ai Authenticated ``` SELECT answer, proposed_sql, citations, conversation_id FROM gluesync.ai WHERE question = ?; ``` answerproposed\_sql Here is what I found…SELECT … `Review proposed_sql before you run it.` The problem ## The question is conversational. The work still belongs in SQL. DataGrip, DBeaver, JDBC scripts, and Query Forge already carry identity and reach federated schemas. AI as SQL keeps the question and its inspectable result on that governed wire. The approach ## Level up any database query engine: natural language in, generated SQL out — your queries have never been so powerful. Query the `gluesync.ai` virtual catalog. Query Forge returns a structured ResultSet under the caller’s PAT and RBAC, using the model provider configured in your BYO vault. Eight outcomes · One JDBC surface ## From a natural-language question to a reviewable next query. 01 ### Ground AI in any BI, ETL or workflow Anything that can open a JDBC connection can invoke an LLM as a normal SELECT: Tableau, Power BI and Looker reports, Talend, Informatica and Pentaho jobs, dbt models, Airflow and scheduler steps. Warehouse-native AI functions only reach the data already loaded in that warehouse — this one runs an AI step inside the ETL processes you already have, across the federated estate, without exporting rows to a separate AI service. `any JDBC client` 02 ### Show the SQL — don’t run it yet Read proposed\_sql as a normal result column and inspect the statement before choosing to execute it. The draft is never run automatically. `proposed_sql` 03 ### Get an answer in natural language Receive answer and citations together as an inspectable work product: a plain-language explanation with the references used to build it. `answer + citations` 04 ### Ask → review → run Keep a visible trust loop. AI drafts the next SQL statement; you review it and own the side effect of running it. `review before run` 05 ### Stay in DataGrip or DBeaver Use the same Query Forge connection as your federated schemas. Query Studio AI remains a separate door for teams working in the Gluesync editor. `jdbc:gluesync://` 06 ### Script it and demo it Parameterize WHERE question = ? in JDBC scripts, audited jobs, and playbooks authenticated with the caller’s Personal API Token. `WHERE question = ?` 07 ### Federate, then ask on the same wire Combine Query Forge JOINs with FROM gluesync.ai. In Gluesync 2.3, name-in-question grounding matches a whole table, schema, agent, or database name, case-insensitively — never a substring. A unique match grounds the question; a stronger score wins; equal-strength collisions fail closed; no match leaves grounding empty. Explicit pipeline\_id and agent\_id always win. BYO provider\_id selection remains available. `FROM gluesync.ai` 08 ### Follow up in the same session Pass conversation\_id into the next question to continue the thread while keeping each response structured as a ResultSet. `conversation_id` How it fits ## Query Forge is the foundation. AI as SQL scales the intelligence. [ Available today ### Query Forge The shipped federated JDBC gateway and the wire AI as SQL builds on. Explore →](/query-forge/)[ Gluesync 2.3 ### AI as SQL The gluesync.ai virtual catalog that returns an answer and optional SQL draft. Explore →](/query-forge/#sql-callable-ai)[ In the editor ### Query Studio AI The Gluesync editor helper for drafting SQL from visible schema context. Explore →](/query-studio/)[ Gluesync 2.3 ### AI Studio The BYO provider vault prerequisite for selecting the model behind the request. Explore →](/capabilities/ai-studio/) What does not change ## Your infrastructure and access model stay in force. - **BYO models**Provider credentials stay in the AI Studio vault. - **Caller PAT + RBAC**Every request carries the JDBC caller’s identity and permissions. - **Read-only MCP**Tool access remains on the governed read-only path. - **Review before run**`proposed_sql` is returned and never auto-runs. Continue exploring [Explore Query Forge ](/query-forge/)[See the Gluesync AI Hub ](/ai-hub/)[Bring AI to legacy databases ](/solutions/ai-on-legacy/)[Read the AI as SQL story ](/blog/ai-as-sql-query-forge-gluesync-ai/) FAQ ## Frequently asked questions Answers about asking natural-language questions through Query Forge and reviewing generated SQL before it runs. What is AI as SQL in Gluesync? AI as SQL lets a JDBC client send a natural-language question to the gluesync.ai virtual catalog and receive a structured ResultSet with an answer and an optional SQL draft. Does AI as SQL automatically execute generated SQL? No. proposed\_sql is returned as a reviewable result column and is never run automatically; the caller decides whether to execute it. What does an AI as SQL result contain? The ResultSet includes an answer, citations, an optional SQL draft, and a conversation\_id for follow-up questions in the same session. Can AI as SQL work from existing SQL tools and BI workflows? Yes. It uses the Query Forge JDBC connection, so it works from DataGrip, DBeaver, JDBC scripts, and other clients that already speak JDBC — including BI and ETL tools. Is AI as SQL available today? No. AI as SQL is coming with Gluesync 2.3. Teams can book a demo or request early access to preview the workflow. Gluesync 2.3 ## Ask Query Forge before you write the next query. AI as SQL is coming with Gluesync 2.3. Preview this new SQL workflow with our team. [Book a demo](/book-a-demo/) [Request early access](/contacts/?topic=ai-hub#contact-form-section)