/DocumentPromptLibrary
Write internal documentation for a shared library of production prompts — e.g. twelve prompts shared across three product teams.
AI Agents & Promptingadvanced#prompt-library#reuse
Model Ops
60 commands
/VersionModelRouter
Set up prompt/model versioning for a model-routing layer choosing between models — e.g. routing simple queries to a cheap model and hard ones.
AI Agents & Promptingmedium#routing#model-selection
/RedTeamLlmApiCall
Red-team for failure modes and abuse cases in a production LLM API integration — e.g. a call to a chat completion endpoint used in a.
AI Agents & Promptingeasy#api#integration
/CompareTokenBudgetPolicy
Compare model options for a per-user token budget policy — e.g. capping free-tier users at 10.
AI Agents & Promptingadvanced#tokens#rate-limit
/OptimizeFineTunedModel
Optimize latency and cost for a custom fine-tuned model — e.g. a model fine-tuned on 3.
AI Agents & Promptingmedium#fine-tuning#custom-model
/DocumentPromptCache
Write internal documentation for a prompt/response caching layer — e.g. caching identical FAQ answers for one hour.
AI Agents & Promptingeasy#cache#latency
/RedTeamEvalDataset
Red-team for failure modes and abuse cases in a held-out evaluation dataset — e.g. 200 hand-labeled examples used to score every new prompt version.
AI Agents & Promptingadvanced#eval#dataset
/FineTuneGuardrailFilter
Plan a fine-tuning run for an input/output content filter — e.g. a filter blocking PII from appearing in model responses.
AI Agents & Promptingmedium#guardrails#moderation
/CompareEmbeddingPipeline
Compare model options for an embedding generation pipeline — e.g. embedding 50,000 support articles nightly.
AI Agents & Promptingeasy#embeddings#vectors
/DocumentIncidentPostmortem
Write internal documentation for a postmortem for an AI-related incident — e.g. a bot that gave incorrect refund amounts for two hours.
AI Agents & Promptingadvanced#incident#postmortem
/VersionPromptLibrary
Set up prompt/model versioning for a shared library of production prompts — e.g. twelve prompts shared across three product teams.
AI Agents & Promptingmedium#prompt-library#reuse
/RedTeamModelRouter
Red-team for failure modes and abuse cases in a model-routing layer choosing between models — e.g. routing simple queries to a cheap model and hard ones.
AI Agents & Promptingeasy#routing#model-selection
/FineTuneLlmApiCall
Plan a fine-tuning run for a production LLM API integration — e.g. a call to a chat completion endpoint used in a.
AI Agents & Promptingadvanced#api#integration
/OptimizeTokenBudgetPolicy
Optimize latency and cost for a per-user token budget policy — e.g. capping free-tier users at 10.
AI Agents & Promptingmedium#tokens#rate-limit
/DocumentFineTunedModel
Write internal documentation for a custom fine-tuned model — e.g. a model fine-tuned on 3.
AI Agents & Promptingeasy#fine-tuning#custom-model
/VersionPromptCache
Set up prompt/model versioning for a prompt/response caching layer — e.g. caching identical FAQ answers for one hour.
AI Agents & Promptingadvanced#cache#latency
/FineTuneEvalDataset
Plan a fine-tuning run for a held-out evaluation dataset — e.g. 200 hand-labeled examples used to score every new prompt version.
AI Agents & Promptingmedium#eval#dataset
/CompareGuardrailFilter
Compare model options for an input/output content filter — e.g. a filter blocking PII from appearing in model responses.
AI Agents & Promptingeasy#guardrails#moderation
/OptimizeEmbeddingPipeline
Optimize latency and cost for an embedding generation pipeline — e.g. embedding 50,000 support articles nightly.
AI Agents & Promptingadvanced#embeddings#vectors
/VersionIncidentPostmortem
Set up prompt/model versioning for a postmortem for an AI-related incident — e.g. a bot that gave incorrect refund amounts for two hours.
AI Agents & Promptingmedium#incident#postmortem
/RedTeamPromptLibrary
Red-team for failure modes and abuse cases in a shared library of production prompts — e.g. twelve prompts shared across three product teams.
AI Agents & Promptingeasy#prompt-library#reuse
/FineTuneModelRouter
Plan a fine-tuning run for a model-routing layer choosing between models — e.g. routing simple queries to a cheap model and hard ones.
AI Agents & Promptingadvanced#routing#model-selection
/CompareLlmApiCall
Compare model options for a production LLM API integration — e.g. a call to a chat completion endpoint used in a.
AI Agents & Promptingmedium#api#integration
/DocumentTokenBudgetPolicy
Write internal documentation for a per-user token budget policy — e.g. capping free-tier users at 10.
AI Agents & Promptingeasy#tokens#rate-limit
/VersionFineTunedModel
Set up prompt/model versioning for a custom fine-tuned model — e.g. a model fine-tuned on 3.
AI Agents & Promptingadvanced#fine-tuning#custom-model
/RedTeamPromptCache
Red-team for failure modes and abuse cases in a prompt/response caching layer — e.g. caching identical FAQ answers for one hour.
AI Agents & Promptingmedium#cache#latency
/CompareEvalDataset
Compare model options for a held-out evaluation dataset — e.g. 200 hand-labeled examples used to score every new prompt version.
AI Agents & Promptingeasy#eval#dataset
/OptimizeGuardrailFilter
Optimize latency and cost for an input/output content filter — e.g. a filter blocking PII from appearing in model responses.
AI Agents & Promptingadvanced#guardrails#moderation
/DocumentEmbeddingPipeline
Write internal documentation for an embedding generation pipeline — e.g. embedding 50,000 support articles nightly.
AI Agents & Promptingmedium#embeddings#vectors
/RedTeamIncidentPostmortem
Red-team for failure modes and abuse cases in a postmortem for an AI-related incident — e.g. a bot that gave incorrect refund amounts for two hours.
AI Agents & Promptingeasy#incident#postmortem
/FineTunePromptLibrary
Plan a fine-tuning run for a shared library of production prompts — e.g. twelve prompts shared across three product teams.
AI Agents & Promptingadvanced#prompt-library#reuse
/CompareModelRouter
Compare model options for a model-routing layer choosing between models — e.g. routing simple queries to a cheap model and hard ones.
AI Agents & Promptingmedium#routing#model-selection
/OptimizeLlmApiCall
Optimize latency and cost for a production LLM API integration — e.g. a call to a chat completion endpoint used in a.
AI Agents & Promptingeasy#api#integration
/VersionTokenBudgetPolicy
Set up prompt/model versioning for a per-user token budget policy — e.g. capping free-tier users at 10.
AI Agents & Promptingadvanced#tokens#rate-limit
/RedTeamFineTunedModel
Red-team for failure modes and abuse cases in a custom fine-tuned model — e.g. a model fine-tuned on 3.
AI Agents & Promptingmedium#fine-tuning#custom-model
/FineTunePromptCache
Plan a fine-tuning run for a prompt/response caching layer — e.g. caching identical FAQ answers for one hour.
AI Agents & Promptingeasy#cache#latency
/OptimizeEvalDataset
Optimize latency and cost for a held-out evaluation dataset — e.g. 200 hand-labeled examples used to score every new prompt version.
AI Agents & Promptingadvanced#eval#dataset
/DocumentGuardrailFilter
Write internal documentation for an input/output content filter — e.g. a filter blocking PII from appearing in model responses.
AI Agents & Promptingmedium#guardrails#moderation
/VersionEmbeddingPipeline
Set up prompt/model versioning for an embedding generation pipeline — e.g. embedding 50,000 support articles nightly.
AI Agents & Promptingeasy#embeddings#vectors
/FineTuneIncidentPostmortem
Plan a fine-tuning run for a postmortem for an AI-related incident — e.g. a bot that gave incorrect refund amounts for two hours.
AI Agents & Promptingadvanced#incident#postmortem
/ComparePromptLibrary
Compare model options for a shared library of production prompts — e.g. twelve prompts shared across three product teams.
AI Agents & Promptingmedium#prompt-library#reuse
/OptimizeModelRouter
Optimize latency and cost for a model-routing layer choosing between models — e.g. routing simple queries to a cheap model and hard ones.
AI Agents & Promptingeasy#routing#model-selection
/DocumentLlmApiCall
Write internal documentation for a production LLM API integration — e.g. a call to a chat completion endpoint used in a.
AI Agents & Promptingadvanced#api#integration
/RedTeamTokenBudgetPolicy
Red-team for failure modes and abuse cases in a per-user token budget policy — e.g. capping free-tier users at 10.
AI Agents & Promptingmedium#tokens#rate-limit
/FineTuneFineTunedModel
Plan a fine-tuning run for a custom fine-tuned model — e.g. a model fine-tuned on 3.
AI Agents & Promptingeasy#fine-tuning#custom-model
/ComparePromptCache
Compare model options for a prompt/response caching layer — e.g. caching identical FAQ answers for one hour.
AI Agents & Promptingadvanced#cache#latency
/DocumentEvalDataset
Write internal documentation for a held-out evaluation dataset — e.g. 200 hand-labeled examples used to score every new prompt version.
AI Agents & Promptingmedium#eval#dataset
/VersionGuardrailFilter
Set up prompt/model versioning for an input/output content filter — e.g. a filter blocking PII from appearing in model responses.
AI Agents & Promptingeasy#guardrails#moderation
/RedTeamEmbeddingPipeline
Red-team for failure modes and abuse cases in an embedding generation pipeline — e.g. embedding 50,000 support articles nightly.
AI Agents & Promptingadvanced#embeddings#vectors
/CompareIncidentPostmortem
Compare model options for a postmortem for an AI-related incident — e.g. a bot that gave incorrect refund amounts for two hours.
AI Agents & Promptingmedium#incident#postmortem
/OptimizePromptLibrary
Optimize latency and cost for a shared library of production prompts — e.g. twelve prompts shared across three product teams.
AI Agents & Promptingeasy#prompt-library#reuse
/DocumentModelRouter
Write internal documentation for a model-routing layer choosing between models — e.g. routing simple queries to a cheap model and hard ones.
AI Agents & Promptingadvanced#routing#model-selection
/VersionLlmApiCall
Set up prompt/model versioning for a production LLM API integration — e.g. a call to a chat completion endpoint used in a.
AI Agents & Promptingmedium#api#integration
/FineTuneTokenBudgetPolicy
Plan a fine-tuning run for a per-user token budget policy — e.g. capping free-tier users at 10.
AI Agents & Promptingeasy#tokens#rate-limit
/CompareFineTunedModel
Compare model options for a custom fine-tuned model — e.g. a model fine-tuned on 3.
AI Agents & Promptingadvanced#fine-tuning#custom-model
/OptimizePromptCache
Optimize latency and cost for a prompt/response caching layer — e.g. caching identical FAQ answers for one hour.
AI Agents & Promptingmedium#cache#latency
/VersionEvalDataset
Set up prompt/model versioning for a held-out evaluation dataset — e.g. 200 hand-labeled examples used to score every new prompt version.
AI Agents & Promptingeasy#eval#dataset
/RedTeamGuardrailFilter
Red-team for failure modes and abuse cases in an input/output content filter — e.g. a filter blocking PII from appearing in model responses.
AI Agents & Promptingadvanced#guardrails#moderation
/FineTuneEmbeddingPipeline
Plan a fine-tuning run for an embedding generation pipeline — e.g. embedding 50,000 support articles nightly.
AI Agents & Promptingmedium#embeddings#vectors
/OptimizeIncidentPostmortem
Optimize latency and cost for a postmortem for an AI-related incident — e.g. a bot that gave incorrect refund amounts for two hours.
AI Agents & Promptingeasy#incident#postmortem