diff --git a/docs.json b/docs.json
index 1a83ea22e5..28ad33c668 100644
--- a/docs.json
+++ b/docs.json
@@ -520,8 +520,8 @@
{
"group": "Get Started",
"pages": [
- "weave/agents-quickstart",
- "weave/quickstart"
+ "weave/agent-integration-quickstart",
+ "weave/custom-agents-quickstart"
]
},
{
@@ -545,6 +545,7 @@
{
"group": "Tracing basics",
"pages": [
+ "weave/quickstart",
"weave/guides/tracking/tracing",
"weave/guides/tracking/create-call",
"weave/guides/tracking/trace-tree",
@@ -1902,7 +1903,6 @@
{
"group": "Premiers pas",
"pages": [
- "fr/weave/agents-quickstart",
"fr/weave/quickstart"
]
},
@@ -3284,7 +3284,6 @@
{
"group": "スタートガイド",
"pages": [
- "ja/weave/agents-quickstart",
"ja/weave/quickstart"
]
},
@@ -4666,7 +4665,6 @@
{
"group": "시작하기",
"pages": [
- "ko/weave/agents-quickstart",
"ko/weave/quickstart"
]
},
diff --git a/fr/weave/concepts/what-is-weave.mdx b/fr/weave/concepts/what-is-weave.mdx
index 4ef8c97a50..943d50b600 100644
--- a/fr/weave/concepts/what-is-weave.mdx
+++ b/fr/weave/concepts/what-is-weave.mdx
@@ -27,7 +27,7 @@ Weave offre les fonctionnalités clés suivantes :
Weave fournit une observabilité agentique sur l’ensemble du cycle de vie des conversations des agents, y compris les sessions, les appels LLM et les exécutions d’outils.
-Si vous créez un agent, suivez le [Démarrage rapide du traçage d’agent](weave/agents-quickstart.mdx) ou découvrez comment utiliser le SDK Weave pour [tracer vos agents](/fr/weave/guides/tracking/trace-agents).
+Si vous créez un agent, suivez le [Démarrage rapide du traçage d’agent](/fr/weave/agents-quickstart) ou découvrez comment utiliser le SDK Weave pour [tracer vos agents](/fr/weave/guides/tracking/trace-agents).
Si vous utilisez un framework tiers pour agents pris en charge, comme Claude Code ou OpenAI Agent SDK, Weave l’instrumente automatiquement, sans code supplémentaire. Voir [Intégrations](/fr/weave/guides/integrations) pour la liste complète des frameworks pris en charge.
diff --git a/ja/weave/concepts/what-is-weave.mdx b/ja/weave/concepts/what-is-weave.mdx
index 34f3019a55..72f8154bba 100644
--- a/ja/weave/concepts/what-is-weave.mdx
+++ b/ja/weave/concepts/what-is-weave.mdx
@@ -27,7 +27,7 @@ Weaveは、次の中核機能を提供します。
Weave は、セッション、LLM calls、ツール実行など、エージェントとの会話のライフサイクル全体にわたるエージェント向けのオブザーバビリティを提供します。
-エージェントを開発している場合は、[エージェントトレースのクイックスタート](weave/agents-quickstart.mdx) に従うか、Weave SDK を使用して[エージェントをトレースする](/ja/weave/guides/tracking/trace-agents)方法を確認してください。
+エージェントを開発している場合は、[エージェントトレースのクイックスタート](/ja/weave/agents-quickstart) に従うか、Weave SDK を使用して[エージェントをトレースする](/ja/weave/guides/tracking/trace-agents)方法を確認してください。
Claude Code や OpenAI Agent SDK などのサポート対象のサードパーティ製エージェントハーネスを使用している場合、Weave は追加のコードなしで自動的に計装します。サポートされているすべてのフレームワークについては、[インテグレーション](/ja/weave/guides/integrations) を参照してください。
diff --git a/ko/weave/concepts/what-is-weave.mdx b/ko/weave/concepts/what-is-weave.mdx
index ce7967d680..8e855e3bdd 100644
--- a/ko/weave/concepts/what-is-weave.mdx
+++ b/ko/weave/concepts/what-is-weave.mdx
@@ -27,7 +27,7 @@ Weave는 다음과 같은 핵심 기능을 제공합니다:
Weave는 세션, LLM Call, 도구 실행을 포함한 에이전트 대화의 전체 라이프사이클 전반에 대한 관측성을 제공합니다.
-에이전트를 개발 중이라면 [에이전트 트레이싱 퀵스타트](weave/agents-quickstart.mdx)를 따라 하거나, Weave SDK를 사용해 [에이전트를 트레이스하는 방법](/ko/weave/guides/tracking/trace-agents)을 알아보세요.
+에이전트를 개발 중이라면 [에이전트 트레이싱 퀵스타트](/ko/weave/agents-quickstart)를 따라 하거나, Weave SDK를 사용해 [에이전트를 트레이스하는 방법](/ko/weave/guides/tracking/trace-agents)을 알아보세요.
Claude Code 또는 OpenAI Agent SDK와 같이 지원되는 타사 에이전트 하니스를 사용 중이라면, Weave가 별도의 코드 추가 없이 자동으로 계측합니다. 지원되는 모든 프레임워크는 [Integrations](/ko/weave/guides/integrations)에서 확인하세요.
diff --git a/snippets/_includes/agent-integration-paths.mdx b/snippets/_includes/agent-integration-paths.mdx
new file mode 100644
index 0000000000..219c0b630f
--- /dev/null
+++ b/snippets/_includes/agent-integration-paths.mdx
@@ -0,0 +1,23 @@
+## Agent harnesses
+
+Agent harnesses are end-user agent runtimes, such as coding agents and developer tools. Install the plugin or extension, then start a session in the harness to begin tracing:
+
+- [Claude Code plugin](/weave/guides/integrations/agents/claude-code-harness)
+- [Codex plugin](/weave/guides/integrations/agents/codex-harness)
+- [OpenClaw plugin](/weave/guides/integrations/agents/openclaw-harness)
+- [Pi extension](/weave/guides/integrations/agents/pi-dev-harness)
+
+## Agent SDKs
+
+Agent SDKs are libraries for building agents and multi-agent workflows in your own application code. Add `weave.init("[YOUR-TEAM]/[YOUR-PROJECT]")` to your script and Weave autopatches the SDK:
+
+- [OpenAI Agents SDK](/weave/guides/integrations/agents/openai-agents-sdk)
+- [Google Agent Development Kit (ADK)](/weave/guides/integrations/agents/google-adk)
+- [Claude Agent SDK](/weave/guides/integrations/agents/claude-agents-sdk)
+
+## Custom agents and OpenTelemetry
+
+If your agent isn't built with one of the SDKs above, or it already emits OpenTelemetry spans, use the Weave SDK directly. Weave accepts any OTel span and gives special handling to [GenAI semantic-convention attributes](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-agent-spans/) so spans render in the **Agents** view:
+
+- [Quickstart: Manually instrument an agent](/weave/custom-agents-quickstart) — a walkthrough of a small multi-turn agent.
+- [Trace your agents](/weave/guides/tracking/trace-agents) — the full reference of agent helpers and concepts.
diff --git a/weave.mdx b/weave.mdx
index 19790c16ee..d222fa2e0c 100644
--- a/weave.mdx
+++ b/weave.mdx
@@ -4,9 +4,10 @@ description: "Track, test, and improve language model apps with W&B Weave"
mode: wide
---
-W&B Weave is an observability and evaluation platform that helps you track, evaluate, and improve your LLM application. With Weave, you can:
+W&B Weave is an observability and evaluation platform that helps you track, evaluate, and improve your agents and LLM applications. With Weave, you can:
-* [Observe and debug](/weave/quickstart) your LLM application
+* [Trace and collect metrics about your agent built with popular SDKs and harnesses](/weave/agent-integration-quickstart)
+* [Manually instrument custom-built agents to collect traces and metrics](/weave/custom-agents-quickstart)
* [Evaluate](/weave/tutorial-eval) your application’s responses using LLM judges and custom scorers
## Get started
@@ -15,28 +16,29 @@ The following docs guide you through the basics of how to use Weave's suite of t
- Start by tracing a basic call to an LLM and reviewing the data in your W&B account.
+ Pick a built-in integration for your agent SDK or harness and start tracing sessions, turns, LLM calls, and tool calls in the Agents view.
- Learn how to build an evaluation pipeline using Weave scorers to test and track your application's performance.
+ Trace a custom multi-turn agent with the Weave SDK to capture sessions, LLM calls, and tool calls as OpenTelemetry spans.
- Build and evaluate RAG applications using Weave with LLM judges to measure retrieval quality.
+ Trace a basic call to an LLM and review the inputs, outputs, and code in your W&B account.
+
## Install Weave
diff --git a/weave/agent-integration-quickstart.mdx b/weave/agent-integration-quickstart.mdx
new file mode 100644
index 0000000000..1415acf7dd
--- /dev/null
+++ b/weave/agent-integration-quickstart.mdx
@@ -0,0 +1,20 @@
+---
+title: "Choose an agent integration"
+description: Pick a built-in Weave integration for your agent SDK or harness and start sending sessions, turns, LLM calls, and tool calls to the Agents view.
+keywords: ["agent integrations", "autopatch", "agent SDKs", "agent harnesses", "tracing"]
+---
+
+import AgentsPreview from '/snippets/_includes/agents-public-preview.mdx';
+import AgentIntegrationPaths from '/snippets/_includes/agent-integration-paths.mdx';
+
+
+
+W&B Weave traces multi-turn agents built with popular SDKs and harnesses without hand-instrumenting each turn. Install a plugin for your agent harness, or call `weave.init()` in code that uses a supported agent SDK, and Weave autopatches the framework. Sessions, turns, LLM calls, and tool calls render in the **Agents** view of your project.
+
+Choose from one of the following supported integrations.
+
+
+
+## Next steps
+
+Once your first session reaches Weave, see [View activity in the Agents view](/weave/guides/tracking/view-agent-activity) to explore sessions, turns, and tool calls.
diff --git a/weave/concepts/what-is-weave.mdx b/weave/concepts/what-is-weave.mdx
index 7fcfd911a1..c5cc7ea367 100644
--- a/weave/concepts/what-is-weave.mdx
+++ b/weave/concepts/what-is-weave.mdx
@@ -23,7 +23,7 @@ Weave provides the following core functionality:
Weave provides agentic observability for the full lifecycle of agent conversations, including sessions, LLM calls, and tool executions.
-If you're building an agent, follow the [agent tracing quickstart](weave/agents-quickstart.mdx) or learn to use the Weave SDK to [trace your agents](/weave/guides/tracking/trace-agents).
+If you're building an agent, start with the [agent integration quickstart](/weave/agent-integration-quickstart) to pick a built-in integration, or follow the [custom agents quickstart](/weave/custom-agents-quickstart) to manually instrument your own. To learn how the Weave SDK models agents, see [Trace your agents](/weave/guides/tracking/trace-agents).
If you're using a supported third-party agent harness, such as Claude Code or OpenAI Agent SDK, Weave instruments it automatically with no additional code. See [Integrations](/weave/guides/integrations) for all supported frameworks.
diff --git a/weave/agents-quickstart.mdx b/weave/custom-agents-quickstart.mdx
similarity index 99%
rename from weave/agents-quickstart.mdx
rename to weave/custom-agents-quickstart.mdx
index 130b7c39e9..7aff67c28a 100644
--- a/weave/agents-quickstart.mdx
+++ b/weave/custom-agents-quickstart.mdx
@@ -1,5 +1,5 @@
---
-title: "Quickstart: Trace an agent"
+title: "Quickstart: Set up custom agent observability"
description: Trace a multi-turn agent with the Weave SDK. Sessions, turns, LLM calls, and tool calls render in the Agents view of your project.
keywords: ["OpenTelemetry", "OTel spans", "multi-turn agent", "tool calls", "tracing"]
---
diff --git a/weave/guides/tracking/trace-agent-integrations.mdx b/weave/guides/tracking/trace-agent-integrations.mdx
index 1d22328018..0d0fdee0d8 100644
--- a/weave/guides/tracking/trace-agent-integrations.mdx
+++ b/weave/guides/tracking/trace-agent-integrations.mdx
@@ -5,30 +5,10 @@ keywords: ["agent harnesses", "autopatch", "OpenTelemetry", "GenAI semconv", "mu
---
import AgentsPreview from '/snippets/_includes/agents-public-preview.mdx';
+import AgentIntegrationPaths from '/snippets/_includes/agent-integration-paths.mdx';
W&B Weave can trace multi-turn agentic applications without hand-instrumenting every turn. For supported agent SDKs and harnesses, call `weave.init()` and Weave autopatches the framework. Weave captures sessions, turns, LLM calls, and tool calls, then renders them in the **Agents** view. This page links to integration guides for three categories: agent harnesses, agent SDKs, and custom agents (including those that emit OpenTelemetry spans).
-## Agent harnesses
-
-Agent harnesses are end-user agent runtimes (such as coding agents and developer tools) that produce spans Weave can capture. Install the appropriate plugin or extension, and Weave routes your harness sessions to the **Agents** view:
-
-- **[Claude Code plugin](/weave/guides/integrations/agents/claude-code-harness)**
-- **[Codex plugin](/weave/guides/integrations/agents/codex-harness)**
-- **[OpenClaw plugin](/weave/guides/integrations/agents/openclaw-harness)**
-- **[Pi extension](/weave/guides/integrations/agents/pi-dev-harness)**
-
-## Agent SDKs
-
-Agent SDKs are libraries for building agents and multi-agent workflows in your own application code. Weave autopatches the following SDKs:
-
-- **[OpenAI Agents SDK](/weave/guides/integrations/agents/openai-agents-sdk)**
-- **[Google Agent Development Kit (ADK)](/weave/guides/integrations/agents/google-adk)**
-- **[Claude Agent SDK](/weave/guides/integrations/agents/claude-agents-sdk)**
-
-## Custom agents and OpenTelemetry
-
-Use the Weave SDK directly to instrument custom agents, including any agent that emits OpenTelemetry spans. Weave accepts any OTel span and has special handling for [GenAI semantic-convention attributes](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-agent-spans/) so your spans render in the **Agents** view.
-
-To learn how to instrument custom agents with the Weave SDK directly, see [Trace your agents](/weave/guides/tracking/trace-agents). For a walkthrough, see the [Trace an agent quickstart](/weave/agents-quickstart).
+