SKILL

agent-observability-auto-experiment

datadog-labsListed

Primary machine endpointhttps://github.com/datadog-labs/agent-skills/tree/HEAD/agent-observability/agent-observability-auto-experiment

Use with an agent

SUMMARY

What it does

Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and r

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

machine-learningweight 100 · confidence 88software-developmentweight 80 · confidence 88infrastructure-operationsweight 80 · confidence 88

MACHINE-READABLE ENDPOINTS

How agents read it

REST JSONhttps://aiworkshub.io/api/v1/resources/RES_789E46596A81Canonical source

https://github.com/datadog-labs/agent-skills/blob/157edafdc1007e2550c5051649caaff5be32f3b8/agent-observability/agent-observability-auto-experiment/SKILL.md

ACCESS

Access requirements

Protocols: agent-skills
Authentication: type: none · required: false
Pricing: model: free
Version: 157edafdc100

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.