|
2 | 2 | title: The Graph's AI
|
3 | 3 | ---
|
4 | 4 |
|
5 |
| -Build with speed and scale faster with The Graph's AI Suite. |
| 5 | +Build with speed and scale faster with The Graph's AI. |
6 | 6 |
|
7 |
| -## What is AI on The Graph? |
| 7 | +## Using AI on The Graph? |
8 | 8 |
|
9 |
| -AI on The Graph connects large language models (LLMs) like Claude to onchain data indexed by The Graph. This allows developers to build AI systems that query blockchain data directly using natural language. This eliminates the need to write code or manage infrastructure. |
| 9 | +[Graph Assistant](/ai-suite/graph-assistant/introduction/) is a powerful **agentic** application that empowers users to easily interact with blockchain data. Ask questions in simple, natural language and get rich, AI powered insights. Both technical developers and non-technical product teams can move faster, make smarter decisions, and gain a clearer understanding than ever before. |
10 | 10 |
|
11 |
| -Instead of relying on static datasets or centralized APIs, you can now access live, verifiable blockchain data using [Graph Assistant](/ai-suite/graph-assistant/introduction/), [Subgraph MCP](), [Token API MCP](). |
12 |
| - |
13 |
| -Fetch fast access to accurate, real-time onchain data. |
| 11 | +Instead of relying on static datasets or centralized APIs, you can now access live, verifiable blockchain data using [Graph Assistant](/ai-suite/graph-assistant/introduction/), Subgraph MCP, and Token API MCP. |
14 | 12 |
|
15 | 13 | ## Why Use Onchain Data with AI?
|
16 | 14 |
|
17 |
| -If you're building with AI in web3, onchain data is necessary. Wallets, tokens, governance, and transactions all live onchain, but are often very difficult to access at scale without an indexing or custom solution. |
| 15 | +Using onchain data with AI unlocks powerful new ways to interact with and understand blockchain ecosystems. |
18 | 16 |
|
19 |
| -The Graph solves this by making onchain data available through [Subgraphs]() and [TokenAPI]() via [Graph Assistant](). |
| 17 | +- **AI as an interface**: Developers can use AI to interact directly with The Graph's data through their agents or build AI-powered applications on top of it. This streamlines development and opens up more intuitive, dynamic use cases. |
| 18 | +- **AI as a product**: For non-technical users, AI can turn complex onchain data into accessible insights. Assistants powered by AI enable anyone to explore, analyze, or act on blockchain data, without requiring any coding. |
20 | 19 |
|
21 |
| -### Benefits |
| 20 | +### Benefits of Using Graph Assistant |
22 | 21 |
|
23 |
| -- Easy access to data in real-time |
24 |
| -- Save time and scale faster |
25 |
| -- Fast access to indexed blockchain data |
26 |
| -- Verifable answers tied to onchain activity |
27 |
| -- Context-aware agents that interact with live data |
| 22 | +- **Natural language Input**: You don't need to write complex queries or sift through dashboards. Simply ask your question in plain English and get clear, accurate results. |
| 23 | +- **Multi-source support**: Works across multiple Subgraphs and The Graph's APIs. The assistant automatically determines which data source to use, so you don't have to switch tools or manage endpoints. |
| 24 | +- **Schema-free access**: You don't need to understand the schema. You can refer to tokens, protocols, dates, or addresses using natural language. The assistant takes care of the rest. |
28 | 25 |
|
29 | 26 | There's no need to maintain backend infrastructure or manually pull and clean blockchain data.
|
30 | 27 |
|
31 | 28 | ## Conversational Querying with Graph Assistant
|
32 | 29 |
|
33 |
| -Graph Assistant allows Claude to understand and query The Graph using plain language. You describe what you want, and the assistant translates it into the correct query against a Subgraph or Token API endpoint. |
34 |
| - |
35 | 30 | **Example queries:**
|
36 | 31 |
|
37 |
| -- "List top holders of this token by balance." |
38 |
| -- "Show GRT transfers to this address in the past 7 days." |
39 |
| -- "Get proposals this wallet voted on in May." |
| 32 | +- "Give me the daily volume on Uniswap." |
| 33 | +- "List the top-5 swaps by USD value in the last 24 hours." |
| 34 | +- "List the 20 most recently registered .eth names." |
| 35 | +- "Whats the best liqudity pool to put my ETH into?" |
| 36 | +- "Total delegated stake in The Graph network?" |
40 | 37 |
|
41 |
| -[Graph Assistant](/ai-suite/graph-assistant/introduction/) uses the Model-Comprehensible Protocol (MCP) to understand data schemas, identify relevant fields, and return structured results. |
| 38 | +Graph Assistant will eventually be a one-stop shop for interacting with The Graph. Right now, it's an agentic AI app that uses state-of-the-art AI techniques, LLMs, and MCPs to understand and answer your questions about Subgraph and Token API data. |
42 | 39 |
|
43 |
| -You don't need to write GraphQL or study Subgraph schemas manually. |
| 40 | +## Why This Matters? |
44 | 41 |
|
45 |
| -## Why This Matters for Developers |
46 |
| - |
47 |
| -If you need fast access to token data, user behavior, governance activity, or protocol metrics, this stack gives you a direct path. You save time, avoid technical overhead, and can ship faster. |
| 42 | +Graph Assistant is a powerful agentic application that lets you interact with blockchain data using natural language through a simple chat interface. Unlike a basic chatbot, Graph Assistant can understand your intent, build complex queries, and execute them automatically. This gives you rich, AI-powered insights from onchain data without writing any code. |
48 | 43 |
|
49 | 44 | - No custom backend
|
50 | 45 | - No manual querying
|
51 | 46 | - No deep GraphQL knowledge required
|
52 |
| - |
53 |
| -You get verifiable blockchain data, ready for use in AI applications, chat interfaces, analytics dashboards, and automation workflows. |
0 commit comments