Canonical: https://molo17.com/ai-hub/use-cases/ Markdown mirror: https://molo17.com/ai-hub/use-cases/index.md Title: AI use cases · Gluesync AI Hub · MOLO17 Description: Gluesync AI Hub use cases: ask your data in plain language, triage sync health, explain alerts, discover PII, automate pipelines, schedule reports, embed agents in applications, and answer executive questions from Claude or ChatGPT, under your permissions. [Gluesync AI Hub](/ai-hub/) · What teams do with Spark agents # 18 things teams actually do with AI on their own data. AI Hub is not a chat box bolted onto a database. It is Spark agents with Core Hub tools, the Enterprise brain, your models, and your permissions, reachable from chat, SQL, schedules, APIs, and the AI clients your company already uses. These are the use cases teams start with, each with the prompt that opens it, the tools it needs, and where it runs. [Book a demo](/book-a-demo/) [Read the AI Studio docs](https://docs.molo17.com/gluesync/latest/gs-modules/ai-studio.html) 1. 01 Start with a question in AI Studio or SQL 2. 02 Publish the agent and give it only the tools it needs 3. 03 Schedule it, embed it, or call it from any AI client [Data, analytics, and BI4](#data-teams)[Operations, DBAs, and on-call4](#operations)[Platform and integration engineering5](#engineering)[Security, compliance, and governance3](#governance)[Executives and the whole company2](#business) 4 use cases ## Data, analytics, and BI Data and analytics teams ### Ask your data, in your words A business question lands and the person who knows the schema is in a meeting. The answer waits for a ticket, a view, or another spreadsheet. Spark turns the question into governed SQL on the live source or target, runs it read-only under the caller's permissions, and returns the numbers with the SQL beside them. The same question also works as a gluesync.ai row from any JDBC client. > Try > > How many orders did we sync yesterday, broken down by country? Tools - `list_sql_capable_agents` - `list_saved_queries` - `get_saved_query` - `execute_sql` - `explain_sql` Runs in - Chat - SQL - MCP client [SQL AI →](/ai-hub/sql-ai/)[Query Studio →](/query-studio/) BI and reporting teams ### Let the BI tool ask the question Tableau, DataGrip, DBeaver, and the reporting job from 2019 all speak SQL. The AI stack speaks HTTP. Someone has to write the adapter nobody wants to own. The gluesync.ai virtual table is served by Query Forge like any other table. A SELECT with a question returns one row with the plain-language answer, a proposed SQL draft that is never auto-executed, citations, and a conversation ID for the follow-up. Read-only tools only, the caller's token only. > Try > > SELECT answer, proposed\_sql FROM gluesync.ai WHERE question = 'which customers churned last quarter in the crm-sync pipeline?'; Tools - `gluesync.ai` - `spark_agent` - `conversation_id` - `provider_id` Runs in - SQL [SQL AI →](/ai-hub/sql-ai/)[Query Forge →](/query-forge/)[AI as SQL solution →](/solutions/ai-as-sql/) Analysts and team leads ### Describe a chart and keep it current Visualize ships with Gluesync 2.3.1 A simple chart of a synced entity takes a BI license, a dataset, and a refresh job before anyone sees a bar. Describe the chart to Spark. Visualize grounds it to real columns through the Enterprise brain, renders it in the Control Plane, refreshes it by hand, on a Chronos schedule, or when the bound entity changes, and publishes a chart or a whole canvas at a stable public URL. > Try > > Chart monthly order totals for the last year from the ORDERS entity and refresh it every night. Tools - `search_enterprise_brain` - `execute_sql` - `create_schedule` Runs in - Chat - Schedule [Enterprise brain →](/ai-hub/enterprise-brain/)[Schedules and events →](/schedules-and-events/) Enterprises with mainframe and midrange estates ### Bring IBM i, Db2, and Oracle into AI without touching the host The most valuable data sits in systems that no AI vendor connects to, and the teams that own them will not install anything new on the box. Gluesync already replicates from IBM i, Db2, Oracle, SQL Server, and 16 dialect engines. Spark, Query Studio AI, and gluesync.ai reason over the schema Gluesync discovers and query the replica or the source read-only, so legacy data joins the AI estate without a new agent on the host. > Try > > Summarize open invoices older than 90 days from the IBM i ledger and propose the SQL you used. Tools - `discover_tables` - `describe_entity_schema` - `execute_sql` - `explain_sql` Runs in - Chat - SQL - MCP client [AI on legacy databases →](/solutions/ai-on-legacy/)[SQL AI →](/ai-hub/sql-ai/) 4 use cases ## Operations, DBAs, and on-call Operations and DBAs ### Triage sync health before anyone asks Pipeline status, per-entity progress, agent metrics, and webhook dead letters live in four screens. Correlating them during an incident costs the minutes you do not have. One question returns pipelines in error, the entity and reason behind each, growing source lag, and the dead letters that explain a silent webhook, correlated in a single answer. > Try > > Which pipelines are in error right now, and why? Tools - `get_pipeline_status` - `get_pipeline_entities_status` - `get_agent_metrics` - `get_webhook_dead_letters` - `get_notifications` Runs in - Chat - Schedule - MCP client [Gluesync platform →](/gluesync/)[AI Workflows →](/ai-hub/ai-workflows/) On-call engineers ### Explain this alert A CRITICAL notification arrives at 02:00 with an entity name and an error code. The runbook is three clicks and one wiki away. Ask AI Studio to explain the notification. Spark receives a read-only tool set scoped to that alert's pipeline, agent, and entity, searches the documentation and anonymized support knowledge, and answers in plain language with no write path disguised as a summary. > Try > > Explain this alert and tell me whether it needs action tonight. Tools - `get_notifications` - `get_pipeline_entities_status` - `search_documentation` - `search_support_knowledge` Runs in - Chat - Schedule [AI Studio →](/capabilities/ai-studio/)[AI Workflows →](/ai-hub/ai-workflows/) Operations leads ### Put the answer on a schedule The same health question is asked every morning. Somebody opens the dashboard, copies numbers into a message, and forgets on Fridays. Any answer Spark can produce once, it can produce every morning. A Chronos schedule fires a published agent version, the prompt template fills in the context, and the digest is delivered by email or webhook before the stand-up. > Try > > Every weekday at 8am, email me a report of pipelines that fell behind overnight. Tools - `create_schedule` - `list_schedules` - `run_schedule` - `set_schedule_enabled` - `send_email_notification` Runs in - Chat - Schedule [AI Workflows →](/ai-hub/ai-workflows/)[Schedules and events →](/schedules-and-events/) Operations leads ### Reach the right people, the right way An agent found the problem. Now it has to tell someone, with the right severity, through channels security already approved. Spark escalates through the webhooks and alert emails Core Hub already has configured, at the INFO, WARNING, or CRITICAL severity you ask for, and can summarize and mark the day's notifications as read. > Try > > Notify ops by webhook and email that the orders pipeline is stalled. Tools - `send_webhook_notification` - `send_email_notification` - `get_notifications` - `mark_notifications_read` - `get_webhook_configurations` Runs in - Chat - Schedule - API [AI Workflows →](/ai-hub/ai-workflows/)[Core Hub MCP →](/corehub-mcp/) 5 use cases ## Platform and integration engineering Platform engineers ### Improve a pipeline configuration Write settings, polling intervals, and column mappings were chosen on day one and never revisited. Changing them by hand means reading YAML nobody remembers. Spark reads the current configuration, explains what it would change and why, and applies it only after a Manager or Super admin confirms. Nothing executes on the first call; a pending action expires after five minutes. > Try > > Review the orders-to-analytics pipeline and suggest safer write settings. Tools - `get_pipeline` - `export_pipeline_yaml` - `update_pipeline` - `list_field_functions` - `compile_mapping_function` Runs in - Chat [AI Studio →](/capabilities/ai-studio/)[Integration capabilities →](/capabilities/integration/) Platform engineers ### Stand up pipelines from a conversation Three new pipelines mean three trips through the wizard, each with the same connection details and the same mapping decisions. Describe the pipelines once. The Pipeline creator keeps an ordered multi-pipeline plan in the conversation, resumes the first incomplete item on continue, scrubs credentials before they reach the model, and runs the same completion transition the wizard uses so the pipelines leave Draft when they are actually ready. > Try > > Create three pipelines from the SAP source to PostgreSQL analytics: customers, orders, and invoices. Tools - `create_connection` - `add_agent` - `create_pipeline` - `create_entity` - `verify_pipeline_connections` Runs in - Chat [Gluesync platform →](/gluesync/)[Integrations →](/integrations/) Integration engineers ### Automate inside and outside Core Hub Your ETL needs a fresh snapshot of one entity on demand, and your release process needs a pipeline drained and restarted without a person watching the screen. Trigger flows with their own token, sync commands, and webhooks let Spark run the operation and hand the result to your own systems. Destructive tools park in the chat with Confirm or Cancel; writes from API keys wait for a signed-in approval. > Try > > Create a trigger flow that runs a one-time snapshot of the invoices entity on demand. Tools - `create_trigger_flow` - `fire_trigger_flow` - `list_trigger_flows` - `start_sync` - `stop_sync` - `one_time_snapshot` Runs in - Chat - Schedule - API [AI Workflows →](/ai-hub/ai-workflows/)[Schedules and events →](/schedules-and-events/) Data quality teams ### Validate a migration and reconcile the differences After a snapshot, someone still has to prove that source and target agree, and explain the rows that do not. Spark starts a Validator comparison, reads the result, and explains the differences in business terms. In a chained Chronos event the comparison runs right after the snapshot, and the agent's summary reaches the team before the morning check. > Try > > Compare CUSTOMERS on source and target after last night's snapshot and summarize the differences. Tools - `trigger_data_comparison` - `get_data_comparison_run` - `list_data_comparison_differences` - `reconcile_data_comparison_differences` - `send_email_notification` Runs in - Chat - Schedule [Validator →](/validator/)[AI Workflows →](/ai-hub/ai-workflows/) Developers ### Embed a governed agent in your own application Product wants an assistant inside the customer portal. Security wants to know which model it calls, with whose key, and what it costs. Your application starts runs through the native /api/ai/v1 contract or the OpenAI-compatible /v1/chat/completions endpoint with a scoped gsa\_ key. Budgets return 402 before spend runs away, rate limits and allow-lists bound the key, and every run keeps a redacted outcome and an ordered event timeline. > Try > > POST /api/ai/v1/agents/support-triage/runs with an idempotency key and a correlation ID. Tools - `/api/ai/v1/agents/{slug}/runs` - `/v1/chat/completions` - `gsa_ platform keys` - `budgets` Runs in - API [AI Studio developer API →](/capabilities/ai-studio/#section-developer-api)[AI Workflows →](/ai-hub/ai-workflows/) 3 use cases ## Security, compliance, and governance Data governance ### Discover where your data hides Nobody is sure which of the 1,400 tables in the ERP hold personal data, or which ones changed since the last replication review. Point Spark at a connection and let it walk schemas, tables, and columns, classify PII by column name and optional sample scan, and shortlist the entities worth replicating. Classification returns labels only, never raw cells. > Try > > Which tables in the ERP source hold customer personal data? Tools - `discover_schemas` - `discover_tables` - `discover_columns` - `classify_table` - `describe_entity_schema` Runs in - Chat - MCP client [Security capabilities →](/capabilities/security/)[Enterprise brain →](/ai-hub/enterprise-brain/) Security and compliance ### Hunt for sensitive columns without SELECT \* Compliance wants proof that every column holding tax IDs, card numbers, or health data is known and masked. Sampling production tables by hand is the risk you are trying to avoid. classify\_table and classify\_schema return PII labels only. Query Studio and the AI helper mask the classified cells in the grid, copies, exports, and model prompts, and a per-user data-access matrix decides who may unmask a column. A monthly schedule can run the sweep and report new findings. > Try > > List every column classified as PII across the billing pipeline that is not yet masked on the target. Tools - `classify_schema` - `classify_table` - `describe_entity_schema` - `list_field_functions` - `send_webhook_notification` Runs in - Chat - Schedule - MCP client [Security capabilities →](/capabilities/security/)[Query Studio →](/query-studio/) Engineering and product teams ### Close the loop in GitLab, Notion, or Slack The agent found the failing entity. The fix lives in a GitLab issue, the runbook in Notion, and the team in Slack. Approved company tools are HTTPS MCP servers registered on the Enterprise brain with an allow-listed host and an encrypted token. Agents that carry the tool bundle can open the issue or post the update during a run; remote calls count as writes and wait for a signed-in approval. > Try > > Open a GitLab issue for the CUSTOMER\_ADDR source timeout and link today's run. Tools - `remote::` - `publish_skill` - `search_enterprise_brain` Runs in - Chat - Schedule [Skills and company tools →](/ai-hub/enterprise-brain/skills-and-company-tools/)[AI Workflows →](/ai-hub/ai-workflows/) 2 use cases ## Executives and the whole company Executives and business teams ### Answer the executive question in the chat they already use Leadership asks faster than the BI team can publish views, and each answer becomes another extract that drifts from the source. Claude, ChatGPT, Grok, Meta Muse, Cursor, or any MCP client connects to Core Hub, searches the Enterprise brain for the tables behind the question, and hands it to a published Spark agent. Every call runs with the permissions of the person asking; the brain stays on your infrastructure. > Try > > Which tables feed the quarterly revenue forecast, and when were they last synced? Tools - `search_enterprise_brain` - `list_published_agents` - `start_agent_run` - `get_agent_run` Runs in - MCP client - Chat [Enterprise brain →](/ai-hub/enterprise-brain/)[Connect your AI tools →](/ai-hub/enterprise-brain/connect-your-ai-tools/) Everyone who operates Gluesync ### Learn every Core Hub corner Documentation, support knowledge, global configuration, and license details are each one menu away, and the question is never about just one of them. Spark answers in context: how Gluesync handles a schema change, which global settings differ from the defaults on this Core Hub, what the license allows, and which past support cases looked like this one. > Try > > Which global settings differ from the defaults on this Core Hub? Tools - `search_documentation` - `search_support_knowledge` - `get_global_config` - `get_license_info` - `get_corehub_version` Runs in - Chat - MCP client [Core Hub MCP →](/corehub-mcp/)[Support →](/support/) How it works ## Every use case follows the same three moves. 1. 01 Ask ### A question, in the surface you already use Chat in AI Studio, a SELECT FROM gluesync.ai in your SQL client, or a prompt from Claude, ChatGPT, Grok, Meta Muse, or Cursor connected to Core Hub. Spark grounds it in the Enterprise brain and the tools on its allow-list. 2. 02 Publish ### Freeze what worked Instructions, skills, tool allow-list, routing policy, and limits become an immutable agent version. Spark can also publish the procedure it just ran as a reusable skill the whole company can call. 3. 03 Operate ### Run it on a trigger, with a budget Chronos schedules and events, webhooks, chained pipeline steps, your application through the API, or a SQL row. Runs are durable and idempotent, spend is budgeted, and writes still wait for a person. Where they run ## Five surfaces, one agent platform A use case is not tied to where it was first tried. The same published agent answers in chat, as a row, on a schedule, behind an API, and inside the AI client of your choice. Chat ### AI Studio Governed Spark agents with persisted conversations, tool traces, alert explanations, and confirmed pipeline writes, inside the Control Plane. - Caller RBAC on every tool call - Per-agent MCP allow-list - Searchable conversations with retention [AI Studio →](/capabilities/ai-studio/) SQL ### Query Studio AI and gluesync.ai Schema-grounded drafts and Tab completion in the workbench, and a virtual table any JDBC client can query for an answer row. - Read-only tools only - proposed\_sql never auto-executed - PII masked before the model [SQL AI →](/ai-hub/sql-ai/) Schedule ### Chronos and AI Workflows Published agents fired from cron, platform events, webhooks, and chained events, with prompt templates, payload allow-lists, and loop guards. - Idempotency keys absorb retries - Writes wait at WAITING\_APPROVAL - Delivery through approved webhooks and email [AI Workflows →](/ai-hub/ai-workflows/) API ### Native and OpenAI-compatible Start runs through /api/ai/v1 or call /v1/chat/completions, /v1/responses, and /v1/embeddings with scoped gsa\_ keys, budgets, and fallback routing. - model: auto routing - 402 before runaway spend - SSE event timeline per run [Developer API →](/capabilities/ai-studio/#section-developer-api) MCP client ### Claude, ChatGPT, Grok, Cursor, and more The Core Hub MCP server exposes 125 tools and the Enterprise brain to any MCP-capable client, under the caller's token. - search\_enterprise\_brain - start\_agent\_run and get\_agent\_run - publish\_skill with the right scope [Connect your AI tools →](/ai-hub/enterprise-brain/connect-your-ai-tools/) Build your own ### Starters, skills, and Craft with Spark Query, Automate, Report, Route, and Investigate starters, immutable skills, and an agent that drafts agents turn a new use case into a published version in an afternoon. - INSTRUCTION, TOOL\_BUNDLE, and KNOWLEDGE skills - JSON output contracts - Routing preview before the first token [AI Studio docs →](https://docs.molo17.com/gluesync/latest/gs-modules/ai-studio.html) FAQ ## AI use cases: questions we hear Do these use cases need a data scientist or prompt engineer? No. AI Studio ships starter patterns (Query, Automate, Report, Route, Investigate) and the use cases on this page map to them. A Manager picks a starter, adjusts the instructions, selects the Core Hub tools the agent may call, and publishes a version. Spark can draft the agent for you with Craft with Spark. Which model runs them? Whichever you register in the bring-your-own vault: OpenAI, OpenAI-compatible endpoints, Anthropic, Azure OpenAI, or a local Ollama model. The routing policy picks per run by capability, residency, health, price, latency, and quality, and you can preview the decision before any tokens are spent. Can an agent see data the user could not? No. Every tool call runs with the permissions of the signed-in user, the API-key owner, or the Chronos run owner, through existing Core Hub RBAC and Query Studio data-access rules. Columns classified as PII are masked before they reach the model. Which of these change something, and how is that controlled? Reads flow immediately. Writes need the tool on the agent's allow-list and the role to use it; proposed pipeline changes wait for a confirmation that expires after five minutes, destructive tools park with Confirm or Cancel, and writes from API keys or Chronos pause at WAITING\_APPROVAL for a signed-in person. Can I start in chat and move to automation later? Yes, that is the intended path. A question you asked once in AI Studio becomes a published agent version, and the same version is fired by a Chronos schedule, an event, a webhook, your application, or a gluesync.ai row. Nothing is rebuilt between the surfaces. Do any of these need a release after Gluesync 2.3.0? Everything on this page ships with Gluesync 2.3 except Visualize, which arrives with Gluesync 2.3.1 and is marked as such. Gluesync Connect, the hosted control plane for many sites, is coming soon, planned for Q4 2026, and available through the waitlist. Gluesync AI Hub ## Keep exploring [Overview **Gluesync AI Hub** The agent platform inside your data control plane: your models, Core Hub tools, and existing permissions. Explore →](/ai-hub/) [Foundation **Enterprise brain** The shared schema graph, memory, skills, and company tools behind every Spark agent and every AI client you connect. Explore →](/ai-hub/enterprise-brain/) [Workspace **AI Studio** Chat with governed Spark agents, publish immutable versions, route across your models, and govern spend from one workspace. Explore →](/capabilities/ai-studio/) [SQL **SQL AI** Query Studio AI and the gluesync.ai virtual table turn plain-language questions into reviewable SQL and result rows. Explore →](/ai-hub/sql-ai/) [Automation **AI Workflows** Published agents fired by Chronos schedules, platform events, webhooks, chained steps, and your own applications. Explore →](/ai-hub/ai-workflows/) [Agent layer **Spark** The Gluesync AI agent layer: Core Hub MCP tools, documentation and knowledge tools, and the caller's permissions on every call. Explore →](/spark/) Gluesync AI Hub ## Pick one use case. The platform is already there for the other 17. Every use case on this page runs on your models, your infrastructure, and your permissions, with Gluesync 2.3. Book a demo and bring the question your team keeps asking. [Book a demo](/book-a-demo/) [Get Gluesync](/get-gluesync/)