# AI use cases for Helix Foundry (HelixDB/helix-foundry) Repo: [HelixDB/helix-foundry](https://github.com/HelixDB/helix-foundry) | Use cases: 3 | Page: https://dedupedai.com/use-cases/helixdb-helix-foundry/ Helix Foundry connects your company's data (PostgreSQL, MySQL, S3, Stripe, PostHog, GitHub, Linear and more, plus documents and table files), lets an agent draft an ontology over it, and loads it into HelixDB as one connected graph. You explore it as a graph or records, trace every value back to its row or quote, and ask questions with cited answers. It runs hosted or locally with Docker Compose. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Turn your company's databases and docs into one queryable graph: https://dedupedai.com/use-cases/helixdb-helix-foundry/turn-company-data-into-a-queryable-graph-with-helix-foundry/ - Ask cited questions across Stripe, GitHub and Linear: https://dedupedai.com/use-cases/helixdb-helix-foundry/ask-cited-questions-across-stripe-and-linear-with-foundry/ - Load PDFs, Markdown and CSV files into a graph you can question: https://dedupedai.com/use-cases/helixdb-helix-foundry/load-documents-and-csv-files-into-a-helixdb-graph/ ## How to turn your company's databases and docs into one queryable graph with Helix Foundry Repo: [HelixDB/helix-foundry](https://github.com/HelixDB/helix-foundry) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Run Foundry locally, connect a database, let the agent draft an ontology and load it into HelixDB. **Who it is for:** An ops or data lead whose customers, invoices and tickets live in different systems. **The problem:** Answering cross-system questions means manual joins and nobody trusts where the numbers came from. **The outcome:** A HelixDB graph you can explore, with answers that cite the row or quote behind each value. ### Steps 1. Run `git clone https://github.com/helixdb/helix-foundry.git` and `cd helix-foundry` 2. Start it with `docker compose up -d --wait` (export ANTHROPIC_API_KEY or OPENAI_API_KEY first if you want Claude or OpenAI) 3. Open http://localhost:3000; there is no sign-in 4. Connect PostgreSQL or another source, or choose Use the sample for the Acme Corp demo 5. Review and edit the ontology the agent drafts, make a version current, and load it ### Prompt to paste into your agent ```text Run HelixDB/helix-foundry locally with Docker Compose, connect , review the ontology the agent drafts, load it, and ask: . Show the cited rows behind the answer. ``` ### Caveat This card is written from the HelixDB/helix-foundry README, not from a test run by Deduped. Before you start, make sure you have Docker with Compose v2 to run locally. Check the repo for newer instructions before you rely on these steps. Risk, data-access: Foundry reads the databases you connect; use a read-only database user and the sample data first. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/helixdb-helix-foundry/turn-company-data-into-a-queryable-graph-with-helix-foundry/ ## How to ask cited questions across Stripe, GitHub and Linear with Helix Foundry Repo: [HelixDB/helix-foundry](https://github.com/HelixDB/helix-foundry) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Connect SaaS sources and ask questions whose answers trace back to the exact record. **Who it is for:** A founder who wants to know which paying customers are blocked by open issues. **The problem:** Billing, code and issue data live in separate tools with no shared view. **The outcome:** Answers that join Stripe, GitHub and Linear data, each value traceable to its source. ### Steps 1. Start Foundry locally or use the hosted version at foundry.helix-db.com 2. Connect Stripe, GitHub and Linear 3. Let the agent draft types and links between them, then edit the rules 4. Load the version and ask questions in plain language 5. Follow each value back to its row before acting on an answer ### Prompt to paste into your agent ```text In HelixDB/helix-foundry, connect Stripe, GitHub and Linear, load a graph linking customers, repos and issues, and answer: which customers paying over have open bugs? Cite each record. ``` ### Caveat This card is written from the HelixDB/helix-foundry README, not from a test run by Deduped. Before you start, make sure you have Docker with Compose v2 to run locally. Check the repo for newer instructions before you rely on these steps. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/helixdb-helix-foundry/ask-cited-questions-across-stripe-and-linear-with-foundry/ ## How to load PDFs, Markdown and CSV files into a graph you can question with Helix Foundry Repo: [HelixDB/helix-foundry](https://github.com/HelixDB/helix-foundry) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Upload documents and table files into Foundry so they join the same graph as your databases. **Who it is for:** A team whose key facts live in PDFs, notes and spreadsheets rather than a database. **The problem:** Facts in documents never connect to the records they talk about. **The outcome:** Documents and table files loaded as part of one graph, with answers quoting the passage they came from. ### Steps 1. Run Foundry with `docker compose up -d --wait` 2. Upload Markdown, text or PDF documents and CSV or TSV table files 3. Let the agent draft types and links that tie the documents to your other data 4. Load and explore as a graph or as records 5. Ask a question and check the quote each answer cites ### Prompt to paste into your agent ```text Use HelixDB/helix-foundry to load , draft an ontology that links them, and answer with quotes from the source documents. ``` ### Caveat This card is written from the HelixDB/helix-foundry README, not from a test run by Deduped. Before you start, make sure you have Docker with Compose v2 to run locally. Check the repo for newer instructions before you rely on these steps. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/helixdb-helix-foundry/load-documents-and-csv-files-into-a-helixdb-graph/