Applied AI glossary
Short, precise definitions of the terms that appear in applied AI work, written for business leaders and engineers who need a shared vocabulary. Each definition is the one Applicat AI uses in its own engagements.
A
- Agentic workflow
A multi-step business process in which AI agents read inputs, decide next actions and execute them through integrations, with people at defined checkpoints.
Related: AI agent, Human-in-the-loop
- AI agent
A software system that uses a model to decide on and carry out actions towards a goal, calling tools such as search, databases and application interfaces to do so. What distinguishes an agent is that it takes actions in systems of record.
Related: Agentic workflow, Tool use
- AI governance
The policies, controls and records that determine how AI systems are approved, monitored and changed, including accountability, human oversight and documentation for regulators and auditors.
Related: Guardrails, Human-in-the-loop
- Applied AI
The practice of taking existing AI capabilities, in particular frontier models, and applying them to specific business processes to produce measurable results in production.
Applied AI sits between research, which creates new capabilities, and strategy, which advises on them. Its unit of success is a system running in production with measured outcomes.
Related: Frontier model, Managed AI operations
B
- Business operating system (BOS)
The layer a company builds and runs its own AI applications and agents on: governed connections to its systems, one identity and permissions model, permission-aware retrieval, one model gateway, a build surface, an evaluation harness, an audit trail and a register of what exists.
Applicat AI builds a business operating system inside a client's own cloud tenancy, so that the things every AI application needs exist once, under the client's control, and each new application inherits them. The same phrase is also used for a management framework of meetings and metrics, which is a different thing.
Related: AI governance, Managed AI operations, Orchestration
C
- Containment rate
In customer and service operations, the share of requests resolved by an AI system without a person becoming involved.
Related: Human-in-the-loop
- Context window
The amount of text, measured in tokens, that a model can consider at once, including instructions, retrieved content and conversation history.
Related: Token
D
- Data residency
Requirements about the geographic location in which data may be stored and processed, which shape model, region and architecture choices for AI systems.
Related: Open-weight model
- Digital coworker
An AI agent that works alongside people on real tasks inside an organisation's systems, taking throughput and synthesis while people keep judgment and accountability.
Related: AI agent, Human-in-the-loop
E
- Embeddings
Numerical representations of text, images or other content that place similar items close together, enabling semantic search and retrieval.
Related: Vector database, Retrieval-augmented generation (RAG)
- Evaluation (evals)
A repeatable set of test cases and scoring methods used to measure an AI system's accuracy, safety, cost and behaviour, run before go-live and on every change.
Evaluation suites built from an organisation's own cases are what turn model choice and go-live decisions from opinion into evidence.
Related: Regression testing, Groundedness
F
- Fine-tuning
Further training of an existing model on specific examples to specialise its behaviour. Used selectively in applied AI, when evaluation shows it outperforms prompting and retrieval.
Related: Evaluation (evals)
- Forward-deployed engineer
An engineer who works inside a client organisation, in its tools and its meetings, designing and building systems against the constraints as they actually are on the ground.
Related: Applied AI
- Frontier applied AI company
A company that builds applied AI systems on frontier models and takes responsibility for those systems in production.
Applicat AI describes itself with this term: frontier because of the models it builds on, applied because its work is measured by systems in production.
Related: Applied AI, Frontier model
- Frontier model
One of the most capable AI models available at a given time, typically produced by a small number of AI labs such as Anthropic, OpenAI and Google, alongside the strongest open-weight models.
Because the frontier moves every few months, systems built on frontier models should isolate the model behind evaluated interfaces so that upgrades are tests rather than rebuilds.
Related: Model-agnostic, Open-weight model
G
- Groundedness
The degree to which an AI system's answer is supported by the sources it was given, as opposed to invented. Measured as part of evaluation.
Related: Retrieval-augmented generation (RAG), Hallucination
- Guardrails
Controls that constrain what an AI system may read, say or do: input filtering, output checks, tool permissions, rate and cost limits and escalation rules.
Related: Human-in-the-loop, AI governance
H
- Hallucination
An output that is fluent and confident but not supported by the source material or by fact. Reduced through grounding, citations, refusal behaviour and evaluation.
Related: Groundedness
- Human-in-the-loop
A design in which a person reviews, approves or corrects an AI system's output or action at defined points, typically where the consequence of an error is high.
A well-designed checkpoint gives the reviewer the evidence and the time to make a real decision in seconds.
Related: Agentic workflow, Guardrails
I
- Inference
Running a trained model to produce an output. Inference cost and latency are core operating metrics of an AI system in production.
Related: Token
M
- Managed AI operations
The ongoing operation of AI systems after go-live: quality and cost monitoring, regression evaluation, model upgrade management, incident response and value reporting.
Related: Observability, Evaluation (evals)
- Model Context Protocol (MCP)
An open standard for connecting AI models and agents to tools and data sources through a common interface, reducing bespoke integration work.
Related: Tool use
- Model-agnostic
An architecture and delivery approach that is not tied to one model provider, choosing and switching models on the basis of evaluation.
Related: Frontier model
- Multimodal
A model or system that works with more than one kind of input, such as text, images, documents, audio and video.
Related: Frontier model
O
- Observability
The instrumentation that makes an AI system's behaviour visible in production: traces of each step, quality scores, latency, cost and failure modes.
Related: Managed AI operations
- Open-weight model
A model whose weights are published, so that it can be run inside an organisation's own environment. Often called simply an open model, and usually chosen for data residency, cost or latency reasons.
Related: Frontier model, Data residency
- Orchestration
The layer that coordinates models, tools, retrieval, memory and checkpoints into a working system, including error handling, retries and logging.
Related: AI agent, Observability
P
- Pilot trap
The pattern in which AI prototypes succeed as demonstrations but never reach production because they were built outside real data, integration, security and governance constraints.
The Applicat Method avoids the pilot trap by proving on real data inside the production perimeter from the start.
Related: Applied AI
R
- Regression testing
Re-running an evaluation suite after any change to a model, prompt, retrieval source or tool to confirm that behaviour has not degraded.
Related: Evaluation (evals)
- Retrieval-augmented generation (RAG)
A technique in which relevant passages are retrieved from an organisation's own content at question time and supplied to the model as context, so answers are grounded in those sources and can be cited.
Related: Groundedness, Embeddings
T
- Token
The unit in which models read and produce text, roughly three-quarters of an English word. Model usage and cost are measured in tokens.
Related: Context window, Inference
- Tool use
The ability of a model to call functions, APIs or applications, for example to look up an order, create a ticket or run a query, as part of producing a result. Also called function calling.
Related: AI agent, Model Context Protocol (MCP)
V
- Value case
A statement of the measurable business outcome an AI use case is expected to change, the baseline, the target and how it will be measured in production.
Related: Applied AI, Evaluation (evals)
- Vector database
A data store optimised for searching embeddings by similarity, used to retrieve relevant content for AI systems.
Related: Embeddings
Bring the frontier into production.
Tell us about the process you want to change. We reply within one business day.