datarobot-external-agent-monitoring

Name: datarobot-external-agent-monitoring
Author: datarobot-oss

22stars19forks

How to install datarobot-external-agent-monitoring?

datarobot-oss/datarobot-agent-skills/datarobot-external-agent-monitoring

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-external-agent-monitoring

Installs into the current project.

Summary

Instrument any external or existing AI agent with OpenTelemetry to send traces, logs, and metrics to DataRobot for monitoring, observability, and governance. Use when the user says "add tracing/observability/monitoring to my agent", wants to instrument an existing agent project i

Files · 1

View on GitHub

SKILL.md

1	# DataRobot External Agent Monitoring Skill
2
3	This skill helps you instrument any AI agent — regardless of framework or deployment environment — to send OpenTelemetry telemetry (traces, logs, metrics) to DataRobot. It also creates a shell deployment in DataRobot as the telemetry routing target.
4
5	## Quick Start
6
7	Most common use case: Instrument an existing agent project, regardless of whether it was built on DataRobot or elsewhere, with DataRobot monitoring
8
9	1. The user invokes the skill from inside their project — typically: "Add tracing to my agent"
10	2. The skill resolves the target project (current IDE workspace / working directory if no path is given), then detects the framework and any existing OTel setup
11	3. It resolves a Use Case as the telemetry target (asks for the user's Use Case ID, or offers to create one), generates instrumentation code, and wires it in
12	4. The agent sends traces, logs, and metrics to DataRobot, where they appear under the Use Case's Tracing tab
13
14	Examples:
15	- "Add tracing to my agent" (resolves to the current workspace)
16	- "Instrument my agent in ./my_agent for DataRobot monitoring"
17
18	## When to use this skill
19
20	Use this skill when an existing DataRobot user has built an agent elsewhere and wants to bring it in for monitoring. Specifically:
21	- Bring an externally-built (brownfield) agent into DataRobot for monitoring under a Use Case
22	- Add OpenTelemetry tracing to an agent project
23	- Send agent traces, logs, and metrics to DataRobot
24	- Instrument a Google ADK, LangChain, LangGraph, CrewAI, LlamaIndex, PydanticAI, or any Python agent
25
26	## Supported Frameworks
27
28	\| Framework \| Detection \| OTel Strategy \|
29	\|-----------\|-----------\|---------------\|
30	\| Google ADK \| `google-adk` in deps or `google.adk` in imports \| Lazy trace injection via callback (ADK overwrites TracerProvider) \|
31	\| LangChain / LangGraph \| `langchain` or `langgraph` in deps/imports \| Auto-instrumentor + standard setup \|
32	\| CrewAI \| `crewai` in deps/imports \| Auto-instrumentor + standard setup \|
33	\| LlamaIndex \| `llama-index` or `llama_index` in deps/imports \| Auto-instrumentor + standard setup \|
34	\| PydanticAI \| `pydantic-ai` or `pydantic_ai` in deps/imports \| Standard setup + required `Agent.instrument_all()` (instrumentation is opt-in) \|
35	\| Generic Python \| None of the above detected \| Manual span instrumentation \|
36
37	## Workflow
38
39	Follow these steps in order. Present the plan to the user and wait for approval before executing.
40
41	### Step 1: Detect & Analyze
42
43	1. Read the project's dependency file (`requirements.txt`, `pyproject.toml`, `setup.py`, `poetry.lock`, or `uv.lock`)
44	2. Scan Python source files for framework imports
45	3. Check for existing OTel setup (look for `opentelemetry` imports, existing TracerProvider/LoggerProvider/MeterProvider configuration)
46	4. Identify the framework using the detection table above
47	5. Read the corresponding framework reference file from the `frameworks/` directory next to this SKILL.md:
48	- Google ADK → `frameworks/google-adk.md`
49	- LangChain/LangGraph → `frameworks/langchain-langgraph.md`
50	- CrewAI → `frameworks/crewai.md`
51	- LlamaIndex → `frameworks/llamaindex.md`
52	- PydanticAI → `frameworks/pydantic-ai.md`
53	- Generic Python → `frameworks/generic-python.md`
54
55	### Step 2: Check Prerequisites
56
57	1. Ensure `DATAROBOT_API_TOKEN` is available without having the user paste it into chat (a pasted token would be logged in the transcript). Check the environment and the project `.env`. If the token is missing, create or update a project `.env` file with the DataRobot variables and have the user paste their Personal API key into that file directly (in their editor); read it from there. Ensure `.env` is gitignored. This skill targets existing DataRobot users: create a Personal API key at `<your DataRobot URL>/account/developer-tools` (Personal API keys tab; see the `datarobot-setup` skill). (No DataRobot account at all? https://www.datarobot.com/trial/.)
58	2. Check if `DATAROBOT_ENDPOINT` env var is set. If not, ask the user (default: `https://app.datarobot.com/api/v2`).
59	3. Derive `DATAROBOT_OTEL_ENDPOINT` automatically: if `DATAROBOT_ENDPOINT` ends with `/api/v2`, strip it and append `/otel` (e.g., `https://app.datarobot.com/api/v2` → `https://app.datarobot.com/otel`).
60	4. Determine the telemetry target (Use Case) — this is the primary entity, and works the same whether the agent was built on DataRobot or elsewhere. Only collect the choice here; do not run any script or create/validate anything yet — that happens once in Step 4, after the user approves the plan (running

People who liked this also viewed

6 picks

Type

datarobot-external-agent-monitoring

22stars19forks

View on GitHub

How to install datarobot-external-agent-monitoring?

datarobot-oss/datarobot-agent-skills/datarobot-external-agent-monitoring

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-external-agent-monitoring

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DataRobot External Agent Monitoring Skill
2
3	This skill helps you instrument any AI agent — regardless of framework or deployment environment — to send OpenTelemetry telemetry (traces, logs, metrics) to DataRobot. It also creates a shell deployment in DataRobot as the telemetry routing target.
4
5	## Quick Start
6
7	Most common use case: Instrument an existing agent project, regardless of whether it was built on DataRobot or elsewhere, with DataRobot monitoring
8
9	1. The user invokes the skill from inside their project — typically: "Add tracing to my agent"
10	2. The skill resolves the target project (current IDE workspace / working directory if no path is given), then detects the framework and any existing OTel setup
11	3. It resolves a Use Case as the telemetry target (asks for the user's Use Case ID, or offers to create one), generates instrumentation code, and wires it in
12	4. The agent sends traces, logs, and metrics to DataRobot, where they appear under the Use Case's Tracing tab
13
14	Examples:
15	- "Add tracing to my agent" (resolves to the current workspace)
16	- "Instrument my agent in ./my_agent for DataRobot monitoring"
17
18	## When to use this skill
19
20	Use this skill when an existing DataRobot user has built an agent elsewhere and wants to bring it in for monitoring. Specifically:
21	- Bring an externally-built (brownfield) agent into DataRobot for monitoring under a Use Case
22	- Add OpenTelemetry tracing to an agent project
23	- Send agent traces, logs, and metrics to DataRobot
24	- Instrument a Google ADK, LangChain, LangGraph, CrewAI, LlamaIndex, PydanticAI, or any Python agent
25
26	## Supported Frameworks
27
28	\| Framework \| Detection \| OTel Strategy \|
29	\|-----------\|-----------\|---------------\|
30	\| Google ADK \| `google-adk` in deps or `google.adk` in imports \| Lazy trace injection via callback (ADK overwrites TracerProvider) \|
31	\| LangChain / LangGraph \| `langchain` or `langgraph` in deps/imports \| Auto-instrumentor + standard setup \|
32	\| CrewAI \| `crewai` in deps/imports \| Auto-instrumentor + standard setup \|
33	\| LlamaIndex \| `llama-index` or `llama_index` in deps/imports \| Auto-instrumentor + standard setup \|
34	\| PydanticAI \| `pydantic-ai` or `pydantic_ai` in deps/imports \| Standard setup + required `Agent.instrument_all()` (instrumentation is opt-in) \|
35	\| Generic Python \| None of the above detected \| Manual span instrumentation \|
36
37	## Workflow
38
39	Follow these steps in order. Present the plan to the user and wait for approval before executing.
40
41	### Step 1: Detect & Analyze
42
43	1. Read the project's dependency file (`requirements.txt`, `pyproject.toml`, `setup.py`, `poetry.lock`, or `uv.lock`)
44	2. Scan Python source files for framework imports
45	3. Check for existing OTel setup (look for `opentelemetry` imports, existing TracerProvider/LoggerProvider/MeterProvider configuration)
46	4. Identify the framework using the detection table above
47	5. Read the corresponding framework reference file from the `frameworks/` directory next to this SKILL.md:
48	- Google ADK → `frameworks/google-adk.md`
49	- LangChain/LangGraph → `frameworks/langchain-langgraph.md`
50	- CrewAI → `frameworks/crewai.md`
51	- LlamaIndex → `frameworks/llamaindex.md`
52	- PydanticAI → `frameworks/pydantic-ai.md`
53	- Generic Python → `frameworks/generic-python.md`
54
55	### Step 2: Check Prerequisites
56
57	1. Ensure `DATAROBOT_API_TOKEN` is available without having the user paste it into chat (a pasted token would be logged in the transcript). Check the environment and the project `.env`. If the token is missing, create or update a project `.env` file with the DataRobot variables and have the user paste their Personal API key into that file directly (in their editor); read it from there. Ensure `.env` is gitignored. This skill targets existing DataRobot users: create a Personal API key at `<your DataRobot URL>/account/developer-tools` (Personal API keys tab; see the `datarobot-setup` skill). (No DataRobot account at all? https://www.datarobot.com/trial/.)
58	2. Check if `DATAROBOT_ENDPOINT` env var is set. If not, ask the user (default: `https://app.datarobot.com/api/v2`).
59	3. Derive `DATAROBOT_OTEL_ENDPOINT` automatically: if `DATAROBOT_ENDPOINT` ends with `/api/v2`, strip it and append `/otel` (e.g., `https://app.datarobot.com/api/v2` → `https://app.datarobot.com/otel`).
60	4. Determine the telemetry target (Use Case) — this is the primary entity, and works the same whether the agent was built on DataRobot or elsewhere. Only collect the choice here; do not run any script or create/validate anything yet — that happens once in Step 4, after the user approves the plan (running

People who liked this also viewed

6 picks

Type