A reference from Weave

Find a term

Understand the metrics, models, and methods behind modern engineering. Clear definitions, practical examples, and a closer look at what the numbers actually mean.

Terms beginning with P

140 terms

  • Prompt compression

    Prompt compression is a language-model concept about context selection and limits. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Prompt engineering

    Prompt engineering is the practice of designing and testing instructions, examples, context, and output requirements that guide a language model toward a useful result. It is an iterative engineering activity supported by evaluation and observability.

    LLM fundamentals

  • Prompt injection

    Prompt injection is an attack or unintended instruction that causes a language model to treat untrusted content as higher-priority guidance. It can redirect an application, expose data, or trigger tools in ways the developer did not intend.

    LLM fundamentals

  • Prompt injection defense

    Prompt injection defense is a language-model concept about instruction design and control. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Prompt length

    Prompt length is the serving concept concerned with prompt length during AI inference.

    Inference performance

  • Prompt overhead

    Prompt overhead is request context supporting execution rather than the primary user payload. It gives teams a way to name, measure, or reason about an economic property of an AI workload without treating raw usage as proof of value.

    Token costs and AI ROI

  • Prompt registry

    Prompt registry is a language-model concept about representation and similarity. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Prompt robustness

    Prompt robustness is a language-model concept about representation and similarity. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Prompt sensitivity

    Prompt sensitivity is a defined lens for examining AI system behavior with a stated task, evidence, and interpretation rule.

    Evaluations and benchmarks

  • Prompt template

    Prompt template is a language-model concept about generation behavior and sampling. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Prompt variable

    Prompt variable is a language-model concept about context selection and limits. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Prompt version

    Prompt version is a language-model concept about instruction design and control. It names a mechanism, representation, prompting pattern, decoding control, or context behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Propensity score

    Propensity score is a statistical or measurement concept used to describe, compare, or interpret engineering data. Its meaning depends on the unit of analysis, data-generating process, and question being asked.

    Measurement and experimentation

  • Propensity score matching

    Propensity score matching is a statistical or measurement concept used to describe, compare, or interpret engineering data. Its meaning depends on the unit of analysis, data-generating process, and question being asked.

    Measurement and experimentation

  • Provider adapter

    Provider adapter is a model-routing or gateway concept used to manage interface consistency for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider allowlist

    Provider allowlist is a model-routing or gateway concept used to manage policy enforcement for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider availability

    Provider availability is a model-routing or gateway concept used to manage reliable request governance for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider capability matrix

    Provider capability matrix is a model-routing or gateway concept used to manage operational visibility for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider denylist

    Provider denylist is a model-routing or gateway concept used to manage policy enforcement for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider health check

    Provider health check is a model-routing or gateway concept used to manage reliable request governance for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider health score

    Provider health score is a model-routing or gateway concept used to manage reliable request governance for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider metrics

    Provider metrics is a model-routing or gateway concept used to manage operational visibility for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider quota

    Provider quota is a model-routing or gateway concept used to manage reliable request governance for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider rate limit

    Provider rate limit is a model-routing or gateway concept used to manage reliable request governance for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider registry

    Provider registry is a model-routing or gateway concept used to manage operational visibility for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider routing

    Provider routing selects an infrastructure provider or endpoint for a model request. The policy may consider price, latency, availability, regional requirements, quotas, capabilities, or recent provider performance.

    Model routing and gateways

  • Provider SLA

    Provider SLA is a model-routing or gateway concept used to manage traffic selection for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider trace

    Provider trace is a model-routing or gateway concept used to manage operational visibility for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider version pinning

    Provider version pinning is a model-routing or gateway concept used to manage operational visibility for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider-agnostic API

    Provider-agnostic API is a model-routing or gateway concept used to manage interface consistency for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Provider-agnostic failover

    Provider-agnostic failover is a model-routing or gateway concept used to manage reliable request governance for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Proximal policy optimization

    Proximal policy optimization is a language-model concept about serving behavior and operational tradeoffs. It names a mechanism, representation, training practice, or operational behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Proxy measure

    Proxy measure is an analytical risk or quality concern that can make an engineering analysis appear more certain, comparable, or causal than it is.

    Engineering analytics

  • Proxy metric

    Proxy metric is a statistical or measurement concept used to describe, compare, or interpret engineering data. Its meaning depends on the unit of analysis, data-generating process, and question being asked.

    Measurement and experimentation

  • Psychological safety

    Psychological safety is a way to organize, support, or evaluate software work so that teams can make useful progress with less avoidable friction. It is most valuable when connected to a concrete outcome and the local conditions of the team using it.

    Developer productivity

  • Pull criteria

    Pull criteria are explicit conditions used to decide whether work is ready for the next stage. They protect flow by preventing items from entering a step when required information, capacity, or quality conditions are missing.

    Flow and capacity planning

  • Pull request size

    Pull request size describes the amount of change contained in a pull request. Tools may count added and deleted lines, changed files, commits, or a combination, so a size report should state its unit.

    Code review

  • Pull request to production time

    Pull request to production time is a software delivery concept used to describe a specific event, interval, control, or operating condition in the path from source change to production behavior. A useful definition names the boundary, unit, and decision the measure supports.

    DORA and DevOps

  • Pull request waiting time

    Pull request waiting time is a developer productivity concept that helps teams understand pull request waiting time in the context of software delivery.

    Developer productivity

  • Pull system

    A pull system starts or advances work when the receiving stage has capacity and the item meets its policy. Pulling controls WIP and makes the decision to begin work visible.

    Flow and capacity planning