> For the complete documentation index, see [llms.txt](https://developer.esw.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.esw.com/getting-started/get-started-with-esw/ai-coding-agents.md). # Build with AI coding agents Set up coding agents to build ESW integrations There are two ways to get your coding agent ready for ESW. Give your agent ESW's rules, ESW agent skill and a working sandbox connection. ## Follow the guide for your agent {% hint style="info" icon="message-bot" %} Each guide takes about five minutes. {% endhint %}
Cover image
:claude: Claude CodeSet up Claude Code for ESW integrations.midweek.svgClaude Code
:cursor: CursorSet up Cursor for ESW integrations.5aec7152-9c05-4405-9924-022b954cd379_1600x1000.webpCursor
:github: GitHub CopilotSet up GitHub Copilot for ESW integrations.1782292080-gh-20copilot.avifGitHub Copilot
:openai: OpenAI CodexSet up OpenAI Codex for ESW integrations.codex.svgCodex
{% hint style="info" icon="microchip" %} #### Using another agent? Most agents that support Agent Skills read skills from `.agents/skills/` in your repository. Unzip the skill there, and add the docs MCP server using your agent's own MCP settings. Or use Option 2. {% endhint %} ## Use one prompt If you prefer, paste this prompt into your coding agent from the root of your project, and replace the last line with what you want to build. The agent reads ESW's operating guide, installs the ESW skill, checks your sandbox credentials work, and then starts building. {% hint style="info" icon="mcp" %} This option does not add the docs MCP server; follow [**Option 1**](/getting-started/get-started-with-esw/ai-coding-agents.md#follow-the-guide-for-your-agent) to add the docs MCP {% endhint %} {% code title="Copy this prompt into your agent" expandable="true" %} ``` Help me build an integration with ESW (eShopWorld) APIs. 1. Read https://developer.esw.com/agents.md and follow its rules for everything below. 2. Install the ESW agent skill: download https://developer.esw.com/esw-api-integration.zip (follow redirects) and unzip it into this repository's skills folder: .claude/skills/ for Claude Code, .github/skills/ for GitHub Copilot, otherwise .agents/skills/. Keep the folder name esw-api-integration. 3. Check that ESW_CLIENT_ID, ESW_CLIENT_SECRET, ESW_TENANT_CODE and ESW_SCOPES are set as environment variables. If any are missing, tell me which ones to set. Do not ask me to paste secrets into this chat, and never write them to files or print them. 4. Get a sandbox token and run the read-only Pricing Advisor smoke test from AGENTS.md. If it does not return 200, stop and tell me why. 5. Then help me build: . Use the ESW sandbox only, and ask me before any call AGENTS.md classes as irreversible. ``` {% endcode %} ## Before you start * **Sandbox credentials.** You need a sandbox `client_id`, `client_secret` and tenant code from ESW. Store them as environment variables `ESW_CLIENT_ID`, `ESW_CLIENT_SECRET`, `ESW_TENANT_CODE`, never in your repository. The skill tells your agent to read them from there. * **Production stays off by default.** The skill and `AGENTS.md` tell agents to use the sandbox unless you explicitly ask for production and provide production credentials. ## Check it works {% code title="After setup, ask your agent" expandable="true" %} ``` Using the ESW skill, get a sandbox token and run the ESW smoke test. ``` {% endcode %} The agent should request a token with a form-encoded body and call Pricing Advisor. A `200` response confirms your credentials, scope and tenant code. If it asks you for missing values instead of guessing, the skill is working.
WhatWhereWhat it does
AGENTS.mddeveloper.esw.com/agents.mdThe full operating guide: environments, authentication, risk classes, retries, per-API rules
Agent skilldeveloper.esw.com/esw-api-integration.zipA condensed copy of AGENTS.md your agent loads automatically when you work on ESW code
OpenAPI specsdeveloper.esw.com/openapi/<api>.jsonField names, types and paths for each API
Docs MCP serverhttps://developer.esw.com/~gitbook/mcpLets your agent search these docs while it works
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://developer.esw.com/getting-started/get-started-with-esw/ai-coding-agents.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.