Software factory

Machine learning operations (MLOps)

The engineering and operational practices used to build, deploy, observe, govern, and maintain machine-learning systems throughout their lifecycle.

Promotion

Moving an artifact or change into a more trusted lifecycle state, such as accepted, merged, released, or deployed, after required evidence and policy checks.

Agent development lifecycle

The recurring process for building, evaluating, deploying, observing, improving, and governing an agent system over its operational life.

Agentic coding

Software development performed with coding agents that can plan, edit, run tools, and iterate, usually under active human direction or review.

Agentic software engineering

The discipline of designing software work so goal-directed AI agents can perform substantial engineering while humans retain product judgment, architecture, governance, and accountability.

Clanker

A derogatory slang term for a robot, AI system, or automated technology, used jokingly or hostilely to express disdain for machines or their perceived replacement of human work.

Coding agent

An AI agent equipped to inspect a software project, edit files, run development tools, test changes, and return or promote a software outcome.

Coding assistant

An AI system that helps a human write, explain, search, review, or modify code while the human remains the primary driver of the workflow.

Cognitive debt

The accumulated loss of shared human understanding, reasoning continuity, or recovery competence caused by repeatedly delegating cognition without rebuilding comprehension.

Context economy

The effect of software and repository structure on the amount and quality of context an agent must consume to make a correct change.

Controlled self-improvement

Versioned modification of prompts, skills, memory, workflows, routing, or harness code under fixed evaluations, limited rollout, observation, and automatic reversion.

Cost per accepted durable outcome

The total model, infrastructure, validation, retry, review, incident, and human-attention cost divided by outcomes that are accepted and remain useful over time.

Digital twin

A sufficiently faithful executable representation of a system or environment used to test behavior, scenarios, or changes before affecting the real target.

Human attention budget

The finite amount of skilled human judgment available for specification, review, exception handling, security, and recovery across automated work.

Improvement graph

A proposed graph of optimizers, evaluators, counter-metrics, auditors, and promotion gates governing how an AI system changes.

Large language model operations (LLMOps)

The practices used to evaluate, deploy, observe, govern, and maintain applications built around large language models.

Production truth

Evidence from sustained real operation, including defects, incidents, maintenance, user outcomes, and recovery, used to judge whether a factory actually works.

Run contract

The machine-readable and human-auditable agreement for one agent run: objective, scope, inputs, tools, permissions, budgets, acceptance evidence, stop conditions, and escalation path.

Semantic failure

A failure in which the system completes its mechanical workflow but the result is wrong in meaning, intent, or real-world consequence.

Single-writer control

A design in which only one authorized component may modify a sensitive persistent state, simplifying policy, audit, and conflict handling.

Software factory

A repeatable production system that turns software demand into accepted, operated software through standardized processes, tooling, controls, and feedback.

Spec-driven development

A development approach in which a written specification, constraints, and acceptance evidence guide implementation before or alongside code generation.

Token budget

An explicit allocation or ceiling for token consumption across a request, run, task, user, workflow, or time period.

Token burn

The amount or rate of model tokens consumed by a request, run, workflow, user, or organization over a defined scope and time window.

Token efficiency

The useful, quality-constrained outcome produced per token consumed, or its reciprocal, tokens consumed per accepted outcome.

AI slop

A contested label for low-quality, low-effort, often high-volume content produced or amplified with generative AI.

Dark software factory

A domain-bounded software production system in which humans specify intent, risk, and policy while a model-harness-environment system plans, builds, verifies, ships, observes, and repairs software with little routine human intervention.

Outcome maxing

Optimizing an AI workflow for accepted results rather than easy-to-count activity proxies such as prompts, tokens, spend, or generated output.

Token maxing

Deliberately or incentive-drivenly maximizing the tokens consumed by AI work, often by expanding context, reasoning, turns, agents, or tasks, while treating greater usage as a route to capability or a proxy for productivity.

Token minning

An emerging counterterm for systematically reducing AI token consumption while preserving an explicit threshold for useful outcome quality.

Token spin

Token-consuming AI activity that produces insufficient learning, accepted work, or maintained value for its total cost.

Useful intelligence per dollar

A proposed AI value scorecard relating dependable, successful work to the full cost required to produce it, rather than treating token price or usage as the result.

Vibe coding

Building software by prompting and accepting generated behavior with limited understanding or inspection of the underlying code.