failure-recovery
What happens when an agent fails — retry, fallback, escalate, or graceful degradation.
142 repo starsObserved in 4 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
few-shot-patterns
Crafting examples that steer AI behavior effectively.
142 repo starsObserved in 4 repos
Agent Building
guardrail-design
Defining behavioral boundaries — what the AI should and shouldn't do.
142 repo starsObserved in 4 repos
Agent Building
handoff-protocols
Designing smooth transitions between agents and between AI and humans.
142 repo starsObserved in 4 repos
Agent Building
output-quality-rubrics
Defining what "good" looks like for AI outputs — accuracy, relevance, helpfulness.
142 repo starsObserved in 4 repos
Agent Building
persona-architecture
Defining AI character, voice, and personality traits.
142 repo starsObserved in 4 repos
Agent Building
prompt-versioning
Managing prompt iterations, testing changes, and tracking what works.
142 repo starsObserved in 4 repos
Agent Building
user-satisfaction-signals
Interpreting implicit and explicit feedback — edits, regenerations, abandonment.
142 repo starsObserved in 4 repos
Agent Building
value-specification
Translating organisational values and user expectations into system constraints.
142 repo starsObserved in 4 repos
Agent Building
agent-observability-auto-experiment
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 only if it beats the best, and repeats. Use when the user says "run an auto experiment", "hill-climb this code", "iteratively improve X and measure the delta", "optimize this prompt/file against my traces", "auto-optimize against LLM-Obs", or wants the local equivalent of the auto_experiments worker. Works from an ml_app, a dataset_id, or a list of trace_ids.
142 repo starsObserved in 3 repos
Agent Building