---
title: "Getting Started"
description: "Choose a route through Agent Surface by goal: make a product usable by agents, assess it, or build agents of your own."
url: "https://agentsurface.dev/docs/getting-started"
lastVerified: 2026-09-25
lastModified: 2026-09-25T05:46:01.000Z
---



## Choose your path [#choose-your-path]

| Goal                                       | Start with                                 | Then read                                                                                                                                                         |
| ------------------------------------------ | ------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Let agents find your product               | [Discovery](/docs/discovery)               | [Retrievability](/docs/retrievability), [Protocols](/docs/protocols)                                                                                              |
| Let agents operate your service            | [API Surface](/docs/api-surface)           | [Tool Design](/docs/tool-design), [MCP Servers](/docs/mcp-servers), [Authentication](/docs/authentication)                                                        |
| Make a repository easier for coding agents | [Context Files](/docs/context-files)       | [CLI Design](/docs/cli-design), [Error Handling](/docs/error-handling)                                                                                            |
| Make a web app usable by browser agents    | [Agentic UI](/docs/agentic-ui)             | [Discovery](/docs/discovery), [Protocols](/docs/protocols)                                                                                                        |
| Let agents buy from you                    | [Agentic Commerce](/docs/agentic-commerce) | [Product Data](/docs/agentic-commerce/product-data), [Checkout Protocols](/docs/agentic-commerce/checkout-protocols), [Payments](/docs/agentic-commerce/payments) |
| Prove agents can complete real tasks       | [Testing](/docs/testing)                   | [Product Journeys](/docs/scoring/product-journeys)                                                                                                                |
| Assess where you stand                     | [Scoring](/docs/scoring)                   | [Rubric](/docs/scoring/rubric), [Public Scanners](/docs/scoring/public-scanners)                                                                                  |
| Build an agent of your own                 | [Agents](/docs/agents)                     | [Agent Retrieval](/docs/agent-retrieval), [Tooling Catalog](/docs/tooling-catalog)                                                                                |

## If you are starting from zero [#if-you-are-starting-from-zero]

For an existing product, this order gets the most value earliest:

1. Write accurate context files: `AGENTS.md` and any tool-specific files that import it.
2. Make content discoverable: robots.txt policy, `llms.txt`, structured data, sitemap and Markdown routes.
3. Make command output parseable: JSON, stable exit codes and strict input validation.
4. Publish machine-readable contracts: OpenAPI, schema metadata and tool definitions.
5. Add recovery paths: RFC 9457 errors, retry guidance, idempotency and trace IDs.
6. Secure programmatic access: scoped credentials and OAuth protected resource metadata.
7. Expose tools deliberately: an MCP server with a curated tool set, annotations and approval for risky actions.
8. Test real tasks: eval cases, traces, CI gates and a before-and-after scorecard.

## Related [#related]

* [What is Agent Surface?](/docs)
* [Scoring](/docs/scoring)
* [Agents](/docs/agents)