docs: AI developers

.gitbook/developers/ai/mcp.mdx → .gitbook/developers-ai/documentation-mcp.mdx

@@ -1,6 +1,6 @@
 ---
-title: MCP Server
-description: Connect AI assistants to Injective documentation using the Model Context Protocol
+title: Documentation MCP Server
+description: Connect AI assistants to Injective documentation using the Model Context Protocol (MCP)
 ---
 
 The Injective documentation provides a Model Context Protocol (MCP) server that allows AI assistants like

.gitbook/developers-ai/index.mdx

@@ -0,0 +1,80 @@
+---
+description: >-
+  Build on Injective with generative AI software engineering.
+title: AI developers
+---
+
+## Why build using generative AI tools on Injective?
+
+With generative AI coding tools, you can build applications very quickly, including on Injective.
+However building very fast in the wrong direction is not ideal.
+You will find skills, agents, workflows, and MCP servers here that will help you with effective AI software engineering.
+
+## What types of generative AI tools are available?
+
+- **LLMs** -
+    Large language models (LLMs) are the base-layer technology powering almost all generative AI software engineering.
+    Almost all AI development tools are wrappers around LLMs.
+    Popular ones include Claude Opus (Anthropic), Gemini (Google), and Kimi (Moonshot AI).
+- **LLM Providers** -
+    Low- and mid-tier LLMs are possible to run on retail/ consumer hardware.
+    However the top-tier LLMs need to be accessed remotely.
+    You have 3 main options:
+    - **Local providers** - For example, using LM Studio or Ollama.
+    - **Remote providers from model developers** - For example, accessing Claude Opus via an Anthropic subscription.
+    - **Remote providers from model aggregators** - For example, accessing Claude Opus, Gemini, or Kimi via an OpenRouter subscription.
+- **Tools** -
+    These can be anything from functions, to scripts, to command-line interfaces (CLIs) that are packaged up in a manner
+    that make them understood or callable by LLMs.
+    For example, if you want the LLM to access real-time information,
+    i.e. information that was no available to it when the LLM was trained,
+    you would need to give it access to call tools for web searches or other data APIs.
+- **MCP** -
+    Model-Context-Protocol (MCP) is a protocol designed for discovery and calling of tools by LLMs.
+    They are designed to standardise the way for different LLMs and LLM providers to invoke tools.
+    Previously each LLM or LLM provider had competing standards/ protocols for doing so.
+- **Skills, workflows, agents** -
+    These are markdown files that optionally reference supporting resources, tools, MCP servers and others.
+    They are designed specifically to work with AI engineering harnesses (but can be used in other contexts).
+    They can be recursive, for example a skill can reference other skills.
+    Likewise workflows are usually a set of skills with a defined order;
+    and agents are are sets of workflows and skills.
+    Note that the term "agents" is overused, with multiple definitions, so the above does not apply in other contexts.
+- **AI engineering IDEs** -
+    These are either dedicated IDEs or plugins within IDEs that allow you to prompt LLMs,
+    including execution of tool calls or MCPs,
+    and use their output to work on the code base that is open within the IDE.
+    Popular ones include: Roo, Cline, and Cursor.
+- **AI engineering Harnesses** -
+    These are command line interfaces (CLIs) or terminal user interfaces (TUIs) that are designed around
+    invoking LLMs for coding tasks.
+    The operate directly on the file system, and often come with baked-in optimisations and utilities for engineering tasks.
+    These tend to be more powerful than working with AI engineering IDEs,
+    as they work best when skills, workflows, and agents are used.
+    Popular ones include: Claude Code (Anthropic), Codex (OpenAI), and OpenCode (unaffiliated).
+- **AI engineering Orchestrators** -
+    These are tools that act as wrappers around harnesses.
+    Their main intent is to enable long-running loops or parallelisation of harness invocation,
+    such that it becomes possible have LLMs working autonomously on longer and more complex tasks
+    without the need for constant human supervision.
+    Popular ones include: Ralph, GSD.
+
+## Which types of generative AI tools will work when developing on Injective?
+
+LLMs, LLM Providers, Tools, MCP, Skills, Workflows, Agents, AI engineering IDEs, AI engineering Harnesses, AI engineering Orchestrators.
+In short, all of them!
+In fact, that is the point of this **AI Developer** section!
+
+## MCP Servers
+
+### Injective Documentation MCP
+
+How to use the [Injective documentation MCP server](/developers-ai/documentation-mcp)
+to obtain up-to-date information from this documentation site.
+If you ask any LLM about Injective,
+it will likely give you out-of-date information, as it does with any fast moving technology.
+This is because their information is obtained from its training data,
+which is by definition "frozen in time".
+By adding this MCP to your AI development workflow,
+not only will you get up-to-date information about developing on Injective,
+you will also have citations for that information in the form of URLs from this documentation site.

.gitbook/developers/index.mdx

@@ -2,7 +2,7 @@
 description: >-
   The goal of this section is to help developers build their projects on
   Injective
-title: Overview
+title: Developers
 ---
 
 Injective is the only blockchain specifically designed for cross-chain trading, derivatives, DeFi, and Web3 applications. Positioned to become the premier global destination for DeFi ecosystem builders, Injective offers a multitude of advantages for developers, empowering them to build more powerful applications in less time.

.gitbook/docs.json

@@ -107,12 +107,6 @@
               "developers/index",
               "developers/convert-addresses",
               "developers/network-information",
-              {
-                "group": "AI development",
-                "pages": [
-                  "developers/ai/mcp"
-                ]
-              },
               {
                 "group": "injectived",
                 "pages": [
@@ -171,6 +165,13 @@
               "redirects/https_api_injective_exchange"
             ]
           },
+          {
+            "group": "AI Developers",
+            "pages": [
+              "developers-ai/index",
+              "developers-ai/documentation-mcp"
+            ]
+          },
           {
             "group": "Infrastructure",
             "icon": "network-wired",
@@ -1220,6 +1221,14 @@
     "eyebrows": "breadcrumbs"
   },
   "redirects": [
+    {
+      "source": "/developers/ai/",
+      "destination": "/developers-ai/"
+    },
+    {
+      "source": "/developers/ai/mcp",
+      "destination": "/developers-ai/documentation-mcp"
+    },
     {
       "source": "/defi/community-burn",
       "destination": "/defi/community-buyback"