Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 2 additions & 4 deletions colabs/weave/agent_evals.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
"# Evaluate your AI agent with Weave\n",
"\n",
"This notebook shows how to evaluate an AI agent with Weave using the\n",
"**Agents / Conversations** workflow — the agent is traced as a conversation of\n",
"**Agent Lens Conversations** workflow — the agent is traced as a conversation of\n",
"turns and tool calls (OpenTelemetry spans), and you score it with\n",
"`weave.EvaluationLogger`.\n",
"\n",
Expand Down Expand Up @@ -238,9 +238,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"When you ran `weave.init()` above, Weave printed a **View Weave data at ...**\n",
"link. Open it and select the **Agents** tab: this conversation appears as a turn\n",
"with the model call and tool calls nested inside it."
"Open `https://forge.coreweave.com/agent-lens/<TEAM>/<PROJECT>` using the team and project configured above, then select **Conversations**. Open the recorded conversation to inspect its turns, model calls, and tool calls. The scoring and evaluation links in the following sections remain in Weave."
]
},
{
Expand Down
26 changes: 13 additions & 13 deletions colabs/weave/custom-agents-quickstart.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -6,15 +6,15 @@
"source": [
"# Quickstart: Trace an agent\n",
"\n",
"Trace a multi-turn agent with the Weave SDK. Conversations, turns, LLM calls, and tool calls render in the Agents view of your project.\n",
"Trace a multi-turn agent with the Weave SDK. Conversations, turns, LLM calls, and tool calls render in the Agent Lens Conversations view.\n",
"\n",
"The Weave SDK allows you to trace custom agents or agents created using popular SDKs. This quickstart guides you through how to manually integrate Weave into a custom-built multi-turn agent to emit and capture OpenTelemetry spans and render them in Weave's Agents view.\n",
"The Weave SDK allows you to trace custom agents or agents created using popular SDKs. This quickstart guides you through how to manually integrate Weave into a custom-built multi-turn agent to emit and capture OpenTelemetry spans and render them in Agent Lens Conversations.\n",
"\n",
"If you are looking to integrate Weave with popular SDKs or harnesses, such as the Claude Agents SDK or Codex, see [Choose an agent integration](https://docs.wandb.ai/weave/agent-integration-quickstart). Weave autopatches into several popular agent-building SDKs and agent harnesses for quick integration.\n",
"If you are looking to integrate Weave with popular SDKs or harnesses, such as the Claude Agents SDK or Codex, see [Choose an agent integration](https://docs.coreweave.com/products/agent-lens/get-started/integrations?utm_source=github&utm_medium=referral&utm_campaign=agent-lens-integrations-2026q4&utm_content=examples-custom-agents-quickstart). The matching guide specifies the required SDK or plugin and how to group turns. This notebook keeps its existing Weave Conversation SDK instrumentation; new custom integrations can use the [Forge SDK quickstart](https://docs.coreweave.com/products/agent-lens/get-started/custom-agents).\n",
"\n",
"## What you'll learn\n",
"\n",
"The code in this guide sets up a small research agent that can look things up on Wikipedia. It asks three questions (three turns), lets the AI decide when to search Wikipedia for an answer, and uses Weave to record every step (the conversation, each question, each AI response, and each Wikipedia lookup) so you can see exactly what happened in the Weave Agents view.\n",
"The code in this guide sets up a small research agent that can look things up on Wikipedia. It asks three questions (three turns), lets the AI decide when to search Wikipedia for an answer, and uses Weave to record every step (the conversation, each question, each AI response, and each Wikipedia lookup) so you can see exactly what happened in the Agent Lens Conversations view.\n",
"\n",
"This guide shows you how to:\n",
"\n",
Expand All @@ -23,11 +23,11 @@
"- Wrap LLM calls with `weave.start_llm()` and record usage\n",
"- Wrap tool executions with `weave.start_tool()` and record results\n",
"- Record complete token usage and a priceable model so token counts and cost render\n",
"- View the resulting conversation, turns, and tool calls in the Agents view\n",
"- View the resulting conversation, turns, and tool calls in Agent Lens Conversations\n",
"\n",
"## How the Weave SDK works with agents\n",
"\n",
"The Weave SDK includes a generic OTel ingest system for agents, meaning that Weave can capture information from any OTel span in your agent's code. However, Weave requires special handling of the following spans to render your agent's traces in the Agents view of the Weave UI.\n",
"The Weave SDK includes a generic OTel ingest system for agents, meaning that Weave can capture information from any OTel span in your agent's code. However, Weave requires special handling of the following spans to render your agent's traces in Agent Lens Conversations of the Weave UI.\n",
"\n",
"| Function | Maps to | OTel span |\n",
"| --- | --- | --- |\n",
Expand All @@ -47,7 +47,7 @@
"source": [
"## Prerequisites\n",
"\n",
"- A W&B account and [API key](https://wandb.ai/authorize)\n",
"- A W&B account and [API key](https://forge.coreweave.com/settings#apikeys)\n",
"- Python 3.10+\n",
"- An OpenAI API key\n",
"\n",
Expand All @@ -71,7 +71,7 @@
"source": [
"## Initialize Weave\n",
"\n",
"`weave.init()` authenticates with W&B and configures the OTel exporter that sends agent spans to the **Agents** view. If the project does not exist on your team, Weave creates it the first time you write to it."
"`weave.init()` authenticates with W&B and configures the OTel exporter that sends agent spans to the Agent Lens **Conversations** view. If the project does not exist on your team, Weave creates it the first time you write to it."
]
},
{
Expand Down Expand Up @@ -274,11 +274,11 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## See your agent traces in the Agents view\n",
"## See your agent traces in Agent Lens Conversations\n",
"\n",
"When `weave.init()` runs, it prints a link to your project where you can see:\n",
"Open `https://forge.coreweave.com/agent-lens/<TEAM>/<PROJECT>` using the team and project configured above, then select **Conversations**. You can see:\n",
"\n",
"- A row in the **Agents** tab for `research-bot`\n",
"- A conversation for `research-bot`\n",
"- One conversation containing three turns\n",
"- Each turn (`invoke_agent`) with two `chat` spans and an `execute_tool` span nested inside\n",
"- Token counts, latency, model, and the full message exchange on each `chat`\n",
Expand All @@ -287,8 +287,8 @@
"\n",
"## Next steps\n",
"\n",
"- Get a better understanding of how to [trace agents with Weave](https://docs.wandb.ai/weave/guides/tracking/trace-agents) and what features and options are available in the Weave SDK.\n",
"- See [Choose an agent integration](https://docs.wandb.ai/weave/agent-integration-quickstart) for more options on how to integrate Weave with your agents."
"- Get a better understanding of how to [trace agents with Agent Lens](https://docs.coreweave.com/products/agent-lens/tracing/instrument) and what features and options are available in the Weave SDK.\n",
"- See [Choose an agent integration](https://docs.coreweave.com/products/agent-lens/get-started/integrations?utm_source=github&utm_medium=referral&utm_campaign=agent-lens-integrations-2026q4&utm_content=examples-custom-agents-quickstart) for more options on how to integrate Weave with your agents."
]
}
],
Expand Down
Loading