# AI use cases for Graphify (Graphify-Labs/graphify) Repo: [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | Use cases: 4 | Page: https://dedupedai.com/use-cases/graphify-labs-graphify/ Graphify is a tool that turns a codebase, its docs, configs, and PDFs into a knowledge graph that an AI coding assistant can query instead of grepping files. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Map an unfamiliar codebase in one run: https://dedupedai.com/use-cases/graphify-labs-graphify/map-unfamiliar-codebase-in-one-run/ - Answer architecture questions from the graph: https://dedupedai.com/use-cases/graphify-labs-graphify/answer-architecture-questions-from-graph/ - Trace how two components connect before a change: https://dedupedai.com/use-cases/graphify-labs-graphify/trace-links-between-two-components/ - Link design docs and PDFs to the code they describe: https://dedupedai.com/use-cases/graphify-labs-graphify/link-docs-and-pdfs-to-code/ ## How to map an unfamiliar codebase in one run with Graphify Repo: [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Build a browsable graph and a highlights report for a project you have not worked in before. **Who it is for:** A developer who has just joined a team or inherited a repo and needs the layout before making changes. **The problem:** Reading files one by one is slow, and it is hard to see which concepts and subsystems matter most. **The outcome:** A graph.html you can click through, a GRAPH_REPORT.md listing key concepts and suggested questions, and a graph.json for later queries. ### Steps 1. Run `uv tool install graphifyy` (or `pipx install graphifyy`) to install the CLI. 2. Run `graphify install` once so it registers the skill with your assistant. 3. Open your AI assistant in the repository and type `/graphify .` 4. Open `graphify-out/graph.html` in a browser and read `graphify-out/GRAPH_REPORT.md`. ### Prompt to paste into your agent ```text In the Graphify-Labs/graphify repo setup, run `/graphify ` on the target repository at . Confirm that graphify-out/ contains graph.html, GRAPH_REPORT.md, and graph.json, then summarize the top concepts listed in GRAPH_REPORT.md. ``` ### Caveat Code parsing is local and deterministic, but docs, PDFs, and media use your assistant's model or a configured API key for the semantic pass. 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/graphify-labs-graphify/map-unfamiliar-codebase-in-one-run/ ## How to answer architecture questions from the graph with Graphify Repo: [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Ask plain-language questions and get scoped answers instead of grepping through files. **Who it is for:** An engineer or AI agent that needs to understand how a class or subsystem works before editing it. **The problem:** Grep returns many matches without showing how the pieces relate, so answers take long to assemble. **The outcome:** A short explanation of one concept, with its source location, community, and every connection tagged EXTRACTED or INFERRED. ### Steps 1. Complete the build step with `/graphify .` so graph.json exists in graphify-out/. 2. Run `graphify explain "APIRouter"` (replace the name with a concept from GRAPH_REPORT.md). 3. Run `graphify query ""` to get a scoped subgraph for a plain-language question. (inferred, check the README) 4. Check each connection's tag: EXTRACTED means explicit in the source, INFERRED means derived by Graphify. ### Prompt to paste into your agent ```text Using the Graphify-Labs/graphify repo, run `graphify explain ""` on the target project at and list its connections. Expected output is the node's source location, community, and connections with their EXTRACTED or INFERRED tags; verify that any claim you make from an INFERRED edge is labeled as inferred. ``` ### Caveat The README example shows a FastAPI graph, so the exact query output on your repo will depend on how it parses. 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/graphify-labs-graphify/answer-architecture-questions-from-graph/ ## How to trace how two components connect before a change with Graphify Repo: [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Find the path between two modules or concepts to see what a change could affect. **Who it is for:** A developer or reviewer preparing a change that touches two parts of a system that may depend on each other. **The problem:** A change to one module can reach another through calls, imports, or inheritance that is not obvious from the file list. **The outcome:** A printed path showing how the two things connect, which helps scope the change and the review. ### Steps 1. Make sure the graph is built by running `/graphify .` in your assistant. 2. Run `graphify path A B` with the names of the two concepts, replacing A and B. 3. Run `graphify explain` on any intermediate node on the path to see its source location and connections. 4. Note which links are EXTRACTED and which are INFERRED before deciding how far the change reaches. ### Prompt to paste into your agent ```text In the Graphify-Labs/graphify repo, run `graphify path ` against the graph in /graphify-out/. Expected output is the chain of nodes connecting the two, with edge tags; verify each hop has a source location before listing it as a dependency. ``` ### Caveat A path shows connections the graph resolved, so treat INFERRED hops as leads to confirm in the code rather than proof. 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/graphify-labs-graphify/trace-links-between-two-components/ ## How to link design docs and PDFs to the code they describe with Graphify Repo: [Graphify-Labs/graphify](https://github.com/Graphify-Labs/graphify) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Put docs, PDFs, and rationale comments into the same graph as the source they explain. **Who it is for:** A team lead or engineer whose design decisions live in ADRs, RFCs, PDFs, and code comments that are hard to connect to the code. **The problem:** Decisions are recorded in documents, but finding which code they apply to means manual searching. **The outcome:** A graph where NOTE, WHY comments and ADR or RFC citations appear as nodes linked to the related code, alongside the docs themselves. ### Steps 1. Place the docs and PDFs you want included inside the repository you will map. 2. Run `/graphify .` in your assistant from the repository root. 3. Open `graphify-out/GRAPH_REPORT.md` and find the rationale and doc nodes it lists. 4. Run `graphify explain` on a code node that a doc cites to see the linked rationale. ### Prompt to paste into your agent ```text Using the Graphify-Labs/graphify repo, run `/graphify ` on the target project and then `graphify explain ""` for one concept that an ADR or RFC cites. Expected output is the concept's connections including the doc reference; verify the doc reference appears as a node before reporting the link. ``` ### Caveat The semantic pass over docs and media calls your assistant's model or a configured API key, so check that setting before mapping sensitive documents. 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/graphify-labs-graphify/link-docs-and-pdfs-to-code/