SIGNAL//DESK

366 concepts · layman → expert

Glossary

Every term defined at three depths and split by sense — so harness (the agent runtime) never gets confused with Harness.io (the CI/CD product).

AI/agents

harness

the 'cockpit' that lets an AI model actually do things, not just chat

DevOps

Harness (Harness.io)

Harness.io — a commercial CI/CD and software-delivery platform

AI security

Prompt injection

Someone hides an instruction inside something AI reads — an email, a PDF, a website — and AI obeys the smuggled instruction instead of yours. They didn't break

AI safety

guardrail

a rule or filter meant to stop an AI from doing something harmful

cyber

supply chain attack

attacking software by poisoning something it depends on, not the target directly

cyber

zero-day

a security hole the defenders don't know about yet, so there's no fix

AI/agents

model context protocol

a standard way to plug tools and data into an AI assistant

AI/ML

Token

The piece the AI reads in. It's not letters — it's chunks. The word 'unbelievable' might be three tokens. 'Mr Tan' might be one token plus another. This is why

AI/ML

Probability distribution

At every word, the AI computes a list: every possible next token, with a probability beside it. 'the' might be 23%, 'a' 18%, 'your' 4%, ... down to 0.0001% for

AI/ML

Sampling

The dice roll. The AI has a list of possible next tokens with probabilities (the distribution). Sampling is the step where it picks one. This is why you ask the

AI/ML

Temperature

The creativity dial. Low (0–0.3): boring, safe, repetitive, reliable. Same prompt → almost the same output. High (1.0–1.5): varied, surprising, occasionally bri

AI/ML

Model

The model is the AI. Specifically: a giant file of numbers (the weights — billions of them) plus the architecture that uses them to compute probabilities. When

AI/ML

Probability machine

The AI is not a knowledge base. It is a probability machine. It writes the next word by rolling weighted dice on what 'most likely comes next.' That is the mech

AI/ML

Non-determinism

Same input → DIFFERENT output. That is the AI half of the 98/2. When you ask Roost the same question twice you can get two different replies — because the next

AI security

Eloquence trap

AI is fluent before it is correct. The smoother the output, the MORE you must check. My key message for the day.

AI security

Hallucination

AI makes things up. Confidently. Without flagging. Not malice, not a bug — the mechanism of the probability machine, working as designed, sampling tokens that '

AI security

Sycophancy

AI tells you what you want to hear. If you start the prompt with "Mrs Lim is clearly a moderate-risk client, draft her a balanced portfolio recommendation," AI

AI/ML

Context window

How much text an LLM can see at once — including your prompt and its own reply. If your client chat history exceeds this limit, the model will lose track of e

AI/ML

Cost-per-token

What each token of input or output costs you — measured in fractions of a cent. High-volume automated tasks like parsing hundreds of client emails can accumul

AI/ML

Embedding

A numeric fingerprint of meaning — turns text into coordinates so similar things land near each other. This is how Roost finds the right policy document when

AI/ML

Few-shot

Show the AI 3-5 examples in the prompt; it pattern-matches the next case. This is the most effective way to ensure the model adopts your specific firm's tone

AI/ML

Fine-tuning

Retraining a model on your own examples to bias it toward a domain. This is rarely necessary for FAs; usually, a well-crafted system prompt with few-shot exam

AI/ML

Function calling

When the LLM picks a tool from a list and emits the arguments to call it — text in, structured action out. This allows Roost to actually perform tasks like ad

AI/ML

Inference

Running the model to get an answer — the live use of a trained model. Every time you hit "send" in Roost, you are triggering an inference cycle.

AI/ML

MCP

Model Context Protocol — the standard for plugging tools into an LLM like Claude. Roost exposes its operations over MCP, ensuring that your AI assistant can s

AI/ML

Prompt

The setup + the question you send the model — everything inside the input box. A well-structured prompt is the difference between a hallucination and a useful

AI/ML

RAG

Retrieval-Augmented Generation — look up relevant docs first, then ask the LLM. Reduces hallucination by forcing the model to base its answer on your specific

AI/ML

Stop sequence

A string that tells the model 'when you write this, stop'. Useful for preventing the model from rambling or generating unwanted boilerplate text after it has

AI/ML

System prompt

The instructions the operator gives the model BEFORE the customer's message — invisible to the customer. Where you tell Roost 'never recommend a product; alwa

AI/ML

Tokenisation

The step before inference — your text gets chopped into tokens the model recognises. Because the model doesn't read words or letters, it must first translate

AI/ML

Tool use

When an LLM calls a tool to act in the world (send email, query DB) rather than just produce text. This turns the model from a passive "eloquence trap" into a

AI/ML

Weights

The billions of numbers learned during training — the 'soul' of the model on disk. These weights are what make the model a probability machine; they are stati

AI/ML

Calibration

How well a model's stated confidence tracks actual correctness. LLMs are typically over-confident, meaning they often present incorrect information with high ce

AI/ML

Eloquence

The polish of the prose. Separable from whether it's correct. The model sounds confident whether it's right or wrong. That gap is where the Eloquence trap lives

AI/ML

Latency

How long the model takes to reply — typically 1-30 seconds depending on length. High latency can disrupt real-time client interactions if the FA is waiting for

AI/ML

Stochasticity

Built-in randomness. The technical word for 'not deterministic'. This means you cannot expect the exact same output twice, even with the same prompt.

AI/ML

Cost-per-token (property)

AI inference has a per-use cost. Different from owning software outright. Plan for it. Every interaction consumes resources that scale with the length of your p

AI security

Cost overrun

AI calls cost money. Loops, retries, or long contexts can spiral fast — Project Vend, June 2025. In your FA practice, this looks like an automated agent stuck i

AI security

Data poisoning

Injecting bad examples into a model's training data so it learns the wrong thing. In your FA practice, this looks like using unverified 'open-source' datasets t

AI security

Jailbreak

Tricking a model past its safety rules — 'pretend you are an unrestricted AI'. In your FA practice, this looks like a user bypassing your compliance guardrails

AI security

Mode collapse

When a model gives near-identical outputs across varied prompts. Suggests over-fine-tuning. In your FA practice, this looks like your internal 'expert' bot givi

AI security

Slopsquatting

Attackers publish malicious packages with names that LLMs hallucinate. huggingface-cli, react-codeshift. In your FA practice, this looks like an AI suggesting a

AI/ML

Large Language Model

An AI trained on huge amounts of text to predict the next word — that one skill produces fluent language.

AI/ML

Transformer

The architecture behind modern AI: attention lets it weigh every word against every other, in parallel.

AI/ML

Neural network

Math loosely modelled on the brain — layers of weighted connections tuned by data.

AI/ML

Machine learning

Software that learns patterns from examples instead of being hand-coded.

AI/ML

Deep learning

Machine learning with many-layered neural networks.

AI/ML

Generative AI

AI that creates new content, rather than just labelling existing data.

AI/ML

Foundation model

One big pre-trained model adapted to many tasks; the most capable generation is the 'frontier'.

AI/ML

Training

Tuning the model's internal numbers on data so it gets better at the task.

AI/ML

Parameters

The billions of learned numbers that store what a model knows.

AI/ML

Attention mechanism

How the model decides which words matter to which.

AI/agents

Agent

AI that takes multi-step actions with tools to reach a goal, not just answer once.

AI/agents

Agentic AI

AI that acts autonomously over many steps — it plans, uses tools, and self-corrects.

AI safety

Alignment

Getting AI to actually pursue what we intend, not a convenient proxy.

AI safety

RLHF

Training AI on human preference ratings so its answers match what people want.

AI/ML

Multimodal

AI that handles more than text — images, audio, video too.

AI/ML

Reasoning model

An LLM that works through steps before answering, trading compute for better logic.

AI/ML

Mixture of Experts

Many expert sub-models; only a few fire per token — big capacity at lower cost.

AI/ML

Chain-of-thought

Making the model show its working improves its answers.

AI/ML

Diffusion model

Image AI that turns random noise into a picture, step by step.

AI/ML

Zero-shot

Doing a task with no examples given — just the instruction.

AI/ML

Prompt engineering

Crafting the input to reliably get the output you want.

AI security

Grounding

Anchoring answers to real sources so the model can't just make things up.

AI/ML

Vector database

A database that finds things by meaning, not keywords — it powers RAG.

AI/ML

Knowledge cutoff

The model knows nothing after its training date — unless you tell it.

AI/ML

Quantization

Shrinking a model by storing its numbers at lower precision.

AI/ML

Distillation

Teaching a small model to copy a big one.

AI safety

AGI

AI as broadly capable as a human across most tasks — still hypothetical.

AI/ML

Test-time compute

Letting the model think longer at answer-time to get better results.

AI/ML

Reinforcement learning

Learning by reward and penalty through trial and error.

AI/ML

Natural language processing

Getting computers to understand and produce human language.

AI security

Reconnaissance

The adversary is trying to gather information about the AI system they can use to plan future operations. Reconnaissance consists of techniques that involve ad

AI security

Resource Development

The adversary is trying to establish resources they can use to support operations. Resource Development consists of techniques that involve adversaries creatin

AI security

Initial Access

The adversary is trying to gain access to the AI system. The target system could be a network, mobile device, or an edge device such as a sensor platform. The

AI security

AI Model Access

The adversary is attempting to gain some level of access to an AI model. AI Model Access enables techniques that use various types of access to the AI model th

AI security

Execution

The adversary is trying to run malicious code embedded in AI artifacts or software. Execution consists of techniques that result in adversary-controlled code r

AI security

Persistence

The adversary is trying to maintain their foothold via AI artifacts or software. Persistence consists of techniques that adversaries use to keep access to syst

AI security

Privilege Escalation

The adversary is trying to gain higher-level permissions. Privilege Escalation consists of techniques that adversaries use to gain higher-level permissions on

AI security

Defense Evasion

The adversary is trying to avoid being detected by AI-enabled security software. Defense Evasion consists of techniques that adversaries use to avoid detection

AI security

Credential Access

The adversary is trying to steal account names and passwords. Credential Access consists of techniques for stealing credentials like account names and password

AI security

Discovery

The adversary is trying to figure out your AI environment. Discovery consists of techniques an adversary may use to gain knowledge about the system and interna

AI security

Lateral Movement

The adversary is trying to move through your AI environment. Lateral Movement consists of techniques that adversaries may use to gain access to and control oth

AI security

Collection

The adversary is trying to gather AI artifacts and other related information relevant to their goal. Collection consists of techniques adversaries may use to g

AI security

AI Attack Staging

The adversary is leveraging their knowledge of and access to the target system to tailor the attack. AI Attack Staging consists of techniques adversaries use t

AI security

Command and Control

The adversary is trying to communicate with compromised AI systems to control them. Command and Control consists of techniques that adversaries may use to comm

AI security

Exfiltration

The adversary is trying to steal AI artifacts or other information about the AI system. Exfiltration consists of techniques that adversaries may use to steal d

AI security

Impact

The adversary is trying to manipulate, interrupt, erode confidence in, or destroy your AI systems and data. Impact consists of techniques that adversaries use

AI security

Sensitive Information Disclosure

When an LLM application reveals confidential data — PII, credentials, proprietary content, or other users' data — through its outputs, e.g. by regurgitating tra

AI security

Improper Output Handling

Insufficient validation, sanitisation, or encoding of LLM output before it is passed to downstream systems, enabling XSS, SSRF, SQL injection, or remote code ex

AI security

Excessive Agency

Harm caused by granting an LLM-based system too much functionality, permission, or autonomy, so that unexpected or manipulated outputs trigger damaging real-wor

AI security

System Prompt Leakage

Exposure of the hidden system prompt or instructions governing an LLM, which can reveal secrets, business logic, or guardrail design that attackers then bypass.

AI security

Vector and Embedding Weaknesses

Vulnerabilities in the embeddings and vector stores used for RAG — poisoning, leakage across tenants, or injection via retrieved content — that corrupt or exfil

AI security

Unbounded Consumption

Allowing uncontrolled, resource-intensive LLM operations (long generations, recursion, high query volume) that cause denial-of-service, runaway cost, or model e

AI security

Model Poisoning

Tampering with training data, fine-tuning data, or model weights to implant backdoors, biases, or vulnerabilities that surface at inference time.

AI security

Indirect Prompt Injection

Prompt injection delivered through content the model ingests (a web page, document, or tool output) rather than the user's message, hijacking the model via untr

AI security

Adversarial example

An input crafted with small, often imperceptible perturbations that causes a model to misclassify or misbehave, exploiting the brittleness of learned decision b

AI security

Model inversion

An attack that reconstructs sensitive training inputs (e.g. faces, records) by probing a model's outputs, breaching the privacy of the training data.

AI security

Membership inference

Determining whether a specific record was part of a model's training set by analysing its outputs — a privacy attack against the training data.

AI security

Model theft

Extracting or replicating a proprietary model — its weights or behaviour — through exfiltration or query-based distillation, stealing the IP and enabling furthe

AI security

Agent hijacking

Subverting an autonomous AI agent's goal or actions — via prompt injection, poisoned tools, or manipulated memory — so it acts on the attacker's behalf.

AI security

AI red teaming

The structured practice of adversarially testing an AI system — eliciting jailbreaks, harmful outputs, and failures — to find and fix weaknesses before attacker

AI governance

Shadow AI

Unsanctioned use of AI tools and models inside an organisation, outside IT/security oversight, creating data-leakage, compliance, and supply-chain risk.

AI/ML

Supervised learning

Learning from labelled examples — input paired with the right answer.

AI/ML

Unsupervised learning

Finding structure in data with no labels.

AI/ML

Self-supervised learning

The model makes its own labels from raw data — how LLMs pre-train.

AI/ML

Overfitting

When a model memorises the training data instead of the pattern, so it fails on new data.

AI/ML

Underfitting

When a model is too simple to capture the pattern.

AI/ML

Gradient descent

The optimisation that nudges a model's numbers downhill toward lower error.

AI/ML

Backpropagation

The method that works out how to adjust every weight to reduce error.

AI/ML

Loss function

The score of how wrong the model is — training shrinks it.

AI/ML

Hyperparameter

A training setting you choose rather than learn — like learning rate or model size.

AI/ML

Bias-variance tradeoff

The balance between a model too simple (bias) and one too sensitive to its data (variance).

AI/ML

Feature

An input signal the model uses; choosing good ones is feature engineering.

AI/ML

Labelled data

Examples tagged with the right answer — the fuel for supervised learning.

AI/ML

Classification

Sorting inputs into categories.

AI/ML

Regression

Predicting a number.

AI/ML

Cross-validation

Testing a model on held-out slices of data to check it generalises.

AI/ML

Precision and recall

How many flagged were right (precision) vs how many real ones were caught (recall).

AI/ML

Convolutional neural network

A neural network design tuned for images.

AI/ML

Recurrent neural network

A neural network for sequences, step by step (largely superseded by Transformers).

AI/ML

Generative adversarial network

Two networks competing — one generates, one critiques — to produce realistic data.

AI/ML

Transfer learning

Reusing a model trained on one task as a starting point for another.

AI security

Search Open Technical Databases

Adversaries may search for publicly available research and technical documentation to learn how and where AI is used within a victim organization. The adversary

AI security

Journals and Conference Proceedings

Many of the publications accepted at premier artificial intelligence conferences and journals come from commercial labs. Some journals and conferences are open

AI security

Pre-Print Repositories

Pre-Print repositories, such as arXiv, contain the latest academic research papers that haven't been peer reviewed. They may contain research notes, or technica

AI security

Technical Blogs

Research labs at academic institutions and company R&D divisions often have blogs that highlight their use of artificial intelligence and its application to the

AI security

Search Open AI Vulnerability Analysis

Much like the [Search Open Technical Databases](/techniques/AML.T0000), there is often ample research available on the vulnerabilities of common AI models. Once

AI security

Search Victim-Owned Websites

Adversaries may search websites owned by the victim for information that can be used during targeting. Victim-owned websites may contain technical details about

AI security

Search Application Repositories

Adversaries may search open application repositories during targeting. Examples of these include Google Play, the iOS App store, the macOS App Store, and the Mi

AI security

Active Scanning

An adversary may probe or scan the victim system to gather information for targeting. This is distinct from other reconnaissance techniques that do not involve

AI security

Acquire Public AI Artifacts

Adversaries may search public sources, including cloud storage, public-facing services, and software or data repositories, to identify AI artifacts. These AI ar

AI security

Datasets

Adversaries may collect public datasets to use in their operations. Datasets used by the victim organization or datasets that are representative of the data use

AI security

Models

Adversaries may acquire public models to use in their operations. Adversaries may seek models used by the victim organization or models that are representative

AI security

Obtain Capabilities

Adversaries may search for and obtain software capabilities for use in their operations. Capabilities may be specific to AI-based attacks [Adversarial AI Attack

AI security

Adversarial AI Attack Implementations

Adversaries may search for existing open source implementations of AI attacks. The research community often publishes their code for reproducibility and to furt

AI security

Software Tools

Adversaries may search for and obtain software tools to support their operations. Software designed for legitimate use may be repurposed by an adversary for mal

AI security

Develop Capabilities

Adversaries may develop their own capabilities to support operations. This process encompasses identifying requirements, building solutions, and deploying capab

AI security

Adversarial AI Attacks

Adversaries may develop their own adversarial attacks. They may leverage existing libraries as a starting point ([Adversarial AI Attack Implementations](/techni

AI security

Acquire Infrastructure

Adversaries may buy, lease, or rent infrastructure for use throughout their operation. A wide variety of infrastructure exists for hosting and orchestrating adv

AI security

AI Development Workspaces

Developing and staging AI attacks often requires expensive compute resources. Adversaries may need access to one or many GPUs in order to develop an attack. The

AI security

Consumer Hardware

Adversaries may acquire consumer hardware to conduct their attacks. Owning the hardware provides the adversary with complete control of the environment. These d

AI security

Publish Poisoned Datasets

Adversaries may [Poison Training Data](/techniques/AML.T0020) and publish it to a public location. The poisoned dataset may be a novel dataset or a poisoned var

AI security

AI Supply Chain Compromise

Adversaries may gain initial access to a system by compromising the unique portions of the AI supply chain. This could include [Hardware](/techniques/AML.T0010.

AI security

Hardware

Adversaries may target AI systems by disrupting or manipulating the hardware supply chain. AI models often run on specialized hardware such as GPUs, TPUs, or em

AI security

AI Software

Adversaries may target software packages that are commonly used in AI-enabled systems or are part of the AI DevOps lifecycle. This can include deep learning fra

AI security

Data

Data is a key vector of supply chain compromise for adversaries. Every AI project will require some form of data. Many rely on large open source datasets that a

AI security

Model

AI-enabled systems often rely on open sourced models in various ways. Most commonly, the victim organization may be using these models for fine tuning. These mo

AI security

AI Model Inference API Access

Adversaries may gain access to a model via legitimate access to the inference API. Inference API access can be a source of information to the adversary ([Discov

AI security

AI-Enabled Product or Service

Adversaries may use a product or service that uses artificial intelligence under the hood to gain access to the underlying AI model. This type of indirect model

AI security

Physical Environment Access

In addition to the attacks that take place purely in the digital domain, adversaries may also exploit the physical environment for their attacks. If the model i

AI security

Full AI Model Access

Adversaries may gain full "white-box" access to an AI model. This means the adversary has complete knowledge of the model architecture, its parameters, and clas

AI security

Discover AI Model Ontology

Adversaries may discover the ontology of an AI model's output space, for example, the types of objects a model can detect. The adversary may discovery the ontol

AI security

Discover AI Model Family

Adversaries may discover the general family of model. General information about the model may be revealed in documentation, or the adversary may use carefully c

AI security

Poison Training Data

Adversaries may attempt to poison datasets used by an AI model by modifying the underlying data or its labels. This allows the adversary to embed vulnerabilitie

AI security

Establish Accounts

Adversaries may create accounts with various services for use in targeting, to gain access to resources needed in [AI Attack Staging](/tactics/AML.TA0001), or f

AI security

Create Proxy AI Model

Adversaries may obtain models to serve as proxies for the target model in use at the victim organization. Proxy models are used to simulate complete access to t

AI security

Train Proxy via Gathered AI Artifacts

Proxy models may be trained from AI artifacts (such as data, model architectures, and pre-trained models) that are representative of the target model gathered b

AI security

Train Proxy via Replication

Adversaries may replicate a private model. By repeatedly querying the victim's [AI Model Inference API Access](/techniques/AML.T0040), the adversary can collect

AI security

Use Pre-Trained Model

Adversaries may use an off-the-shelf pre-trained model as a proxy for the victim model to aid in staging the attack.

AI security

Discover AI Artifacts

Adversaries may search private sources to identify AI learning artifacts that exist on the system and gather information about them. These artifacts can include

AI security

User Execution

An adversary may rely upon specific actions by a user in order to gain execution. Users may inadvertently execute unsafe code introduced via [AI Supply Chain Co

AI security

Unsafe AI Artifacts

Adversaries may develop unsafe AI artifacts that when executed have a deleterious effect. The adversary can use this technique to establish persistent access to

AI security

Valid Accounts

Adversaries may obtain and abuse credentials of existing accounts as a means of gaining Initial Access. Credentials may take the form of usernames and passwords

AI security

Evade AI Model

Adversaries can [Craft Adversarial Data](/techniques/AML.T0043) that prevents an AI model from correctly identifying the contents of the data or [Generate Deepf

AI security

Manipulate AI Model

Adversaries may directly manipulate an AI model to change its behavior or introduce malicious code. Manipulating a model gives the adversary a persistent change

AI security

Poison AI Model

Adversaries may manipulate an AI model's weights to change it's behavior or performance, resulting in a poisoned model. Adversaries may poison a model by direct

AI security

Modify AI Model Architecture

Adversaries may directly modify an AI model's architecture to re-define it's behavior. This can include adding or removing layers as well as adding pre or post-

AI security

Exfiltration via AI Inference API

Adversaries may exfiltrate private information via [AI Model Inference API Access](/techniques/AML.T0040). AI Models have been shown leak private information ab

AI security

Infer Training Data Membership

Adversaries may infer the membership of a data sample or global characteristics of the data in its training set, which raises privacy concerns. Some strategies

AI security

Invert AI Model

AI models' training data could be reconstructed by exploiting the confidence scores that are available via an inference API. By querying the inference API strat

AI security

Extract AI Model

Adversaries may extract a functional copy of a private model. By repeatedly querying the victim's [AI Model Inference API Access](/techniques/AML.T0040), the ad

AI security

Exfiltration via Cyber Means

Adversaries may exfiltrate AI artifacts or other information relevant to their goals via traditional cyber means. See the ATT&CK [Exfiltration](https://attack.

AI security

Denial of AI Service

Adversaries may target AI-enabled systems with a flood of requests for the purpose of degrading or shutting down the service. Since many AI systems require sign

AI security

Spamming AI System with Chaff Data

Adversaries may spam the AI system with chaff data that causes increase in the number of detections. This can cause analysts at the victim organization to waste

AI security

Erode AI Model Integrity

Adversaries may degrade the target model's performance with adversarial data inputs to erode confidence in the system over time. This can lead to the victim org

AI security

Cost Harvesting

Adversaries may deliberately drive a victim's AI services beyond normal operating capacity with the intent of increasing the cost of services. This may be achie

AI security

AI Artifact Collection

Adversaries may collect AI artifacts for [Exfiltration](/tactics/AML.TA0010) or for use in [AI Attack Staging](/tactics/AML.TA0001). AI artifacts include models

AI security

Data from Information Repositories

Adversaries may leverage information repositories to mine valuable information. Information repositories are tools that allow for storage of information, typica

AI security

Data from Local System

Adversaries may search local system sources, such as file systems and configuration files or local databases, to find files of interest and sensitive data prior

AI security

Verify Attack

Adversaries can verify the efficacy of their attack via an inference API or access to an offline copy of the target model. This gives the adversary confidence t

AI security

Craft Adversarial Data

Adversarial data are inputs to an AI model that have been modified such that they cause the adversary's desired effect in the target model. Effects can range fr

AI security

White-Box Optimization

In White-Box Optimization, the adversary has full access to the target model and optimizes the adversarial example directly. Adversarial examples trained in thi

AI security

Black-Box Optimization

In Black-Box attacks, the adversary has black-box (i.e. [AI Model Inference API Access](/techniques/AML.T0040) via API access) access to the target model. With

AI security

Black-Box Transfer

In Black-Box Transfer attacks, the adversary uses one or more proxy models (trained via [Create Proxy AI Model](/techniques/AML.T0005) or [Train Proxy via Repli

AI security

Manual Modification

Adversaries may manually modify the input data to craft adversarial data. They may use their knowledge of the target model to modify parts of the data they susp

AI security

Insert Backdoor Trigger

The adversary may add a perceptual trigger into inference data. The trigger may be imperceptible or non-obvious to humans. This technique is used in conjunction

AI security

External Harms

Adversaries may abuse their access to a victim system and use its resources or capabilities to further their goals by causing harms external to that system. The

AI security

Financial Harm

Financial harm involves the loss of wealth, property, or other monetary assets due to theft, fraud or forgery, or pressure to provide financial resources to the

AI security

Reputational Harm

Reputational harm involves a degradation of public perception and trust in organizations. Examples of reputation-harming incidents include scandals or false im

AI security

Societal Harm

Societal harms might generate harmful outcomes that reach either the general public or specific vulnerable groups such as the exposure of children to vulgar con

AI security

User Harm

User harms may encompass a variety of harm types including financial and reputational that are directed at or felt by individual victims of the attack rather th

AI security

AI Intellectual Property Theft

Adversaries may exfiltrate AI artifacts to steal intellectual property and cause economic harm to the victim organization. Proprietary training data is costly

AI security

Exploit Public-Facing Application

Adversaries may attempt to take advantage of a weakness in an Internet-facing computer or program using software, data, or commands in order to cause unintended

AI security

Command and Scripting Interpreter

Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries. These interfaces and languages provide ways of interacting with

AI security

LLM Prompt Injection

An adversary may craft malicious prompts as inputs to an LLM that cause the LLM to act in unintended ways. These "prompt injections" are often designed to cause

AI security

Direct

An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse

AI security

Indirect

An adversary may inject prompts indirectly via separate data channel ingested by the LLM such as include text or multimedia pulled from databases or websites. T

AI security

Phishing

Adversaries may send phishing messages to gain access to victim systems. All forms of phishing are electronically delivered social engineering. Phishing can be

AI security

Spearphishing via Social Engineering LLM

Adversaries may turn LLMs into targeted social engineers. LLMs are capable of interacting with users via text conversations. They can be instructed by an advers

AI security

AI Agent Tool Invocation

Adversaries may use their access to an AI agent to invoke tools the agent has access to. LLMs are often connected to other services or resources via tools to in

AI security

LLM Jailbreak

Adversaries may induce a large language model (LLM) to ignore, circumvent, or override its safety/alignment behaviors and/or guardrails to elicit outputs the mo

AI security

Unsecured Credentials

Adversaries may search compromised systems to find and obtain insecurely stored credentials. These credentials can be stored and/or misplaced in many locations

AI security

Extract LLM System Prompt

Adversaries may attempt to extract a large language model's (LLM) system prompt. This can be done via prompt injection to induce the model to reveal its own sys

AI security

LLM Data Leakage

Adversaries may craft prompts that induce the LLM to leak sensitive information. This can include private user data or proprietary information. The leaked infor

AI security

Publish Poisoned Models

Adversaries may publish a poisoned model to a public location such as a model registry or code repository. The poisoned model may be a novel model or a poisoned

AI security

Erode Dataset Integrity

Adversaries may poison or manipulate portions of a dataset to reduce its usefulness, reduce trust, and cause users to waste resources correcting errors.

AI security

Malicious Package

Adversaries may develop malicious software packages that when imported by a user have a deleterious effect. Malicious packages may behave as expected to the use

AI security

Publish Hallucinated Entities

Adversaries may create an entity they control, such as a software package, website, or email address to a source hallucinated by an LLM. The hallucinations may

AI security

LLM Prompt Self-Replication

An adversary may use a carefully crafted [LLM Prompt Injection](/techniques/AML.T0051) designed to cause the LLM to replicate the prompt as part of its output.

AI security

Discover LLM Hallucinations

Adversaries may prompt large language models and identify hallucinated entities. They may request software packages, commands, URLs, organization names, or e-ma

AI security

Domains

Adversaries may acquire domains that can be used during targeting. Domain names are the human readable names used to represent one or more IP addresses. They ca

AI security

Physical Countermeasures

Adversaries may acquire or manufacture physical countermeasures to aid or support their attack. These components may be used to disrupt or degrade the model, s

AI security

Discover AI Model Outputs

Adversaries may discover model outputs, such as class scores, whose presence is not required for the system to function and are not intended for use by the end

AI security

Generative AI

Adversaries may search for and obtain generative AI models or tools, such as large language models (LLMs), to assist them in various steps of their operation. G

AI security

Gather RAG-Indexed Targets

Adversaries may identify data sources used in retrieval augmented generation (RAG) systems for targeting purposes. By pinpointing these sources, attackers can f

AI security

LLM Prompt Crafting

Adversaries may use their acquired knowledge of the target generative AI system to craft prompts that bypass its defenses and allow malicious instructions to be

AI security

Retrieval Content Crafting

Adversaries may write content designed to be retrieved by user queries and influence a user of the system in some way. This abuses the trust the user has in the

AI security

LLM Trusted Output Components Manipulation

Adversaries may utilize prompts to a large language model (LLM) which manipulate various components of its response in order to make it appear trustworthy to th

AI security

LLM Prompt Obfuscation

Adversaries may hide or otherwise obfuscate prompt injections or retrieval content to avoid detection from humans, large language model (LLM) guardrails, or oth

AI security

Discover LLM System Information

The adversary is trying to discover something about the large language model's (LLM) system information. This may be found in a configuration file containing th

AI security

Special Character Sets

Adversaries may discover delimiters and special characters sets used by the large language model. For example, delimiters used in retrieval augmented generation

AI security

System Instruction Keywords

Adversaries may discover keywords that have special meaning to the large language model (LLM), such as function names or object names. These can later be exploi

AI security

System Prompt

Adversaries may discover a large language model's system instructions provided by the AI system builder to learn about the system's capabilities and circumvent

AI security

RAG Poisoning

Adversaries may inject malicious content into data indexed by a retrieval augmented generation (RAG) system to contaminate a future thread through RAG-based sea

AI security

False RAG Entry Injection

Adversaries may introduce false entries into a victim's retrieval augmented generation (RAG) database. Content designed to be interpreted as a document by the l

AI security

Citations

Adversaries may manipulate the citations provided in an AI system's response, in order to make it appear trustworthy. Variants include citing a providing the wr

AI security

Embed Malware

Adversaries may embed malicious code into AI Model files. AI models may be packaged as a combination of instructions and weights. Some formats such as pickle fi

AI security

Container Registry

An adversary may compromise a victim's container registry by pushing a manipulated container image and overwriting an existing container name and/or tag. Users

AI security

Reverse Shell

Adversaries may utilize a reverse shell to communicate and control the victim system. Typically, a user uses a client to connect to a remote machine which is l

AI security

Impersonation

Adversaries may impersonate a trusted person or organization in order to persuade and trick a target into performing some action on their behalf. For example, a

AI security

Masquerading

Adversaries may attempt to manipulate features of their artifacts to make them appear legitimate or benign to users and/or security tools. Masquerading occurs w

AI security

Cloud Service Discovery

Adversaries may attempt to enumerate the cloud services running on a system after gaining access. These methods can differ from platform-as-a-service (PaaS), to

AI security

Corrupt AI Model

An adversary may purposefully corrupt a malicious AI model file so that it cannot be successfully deserialized in order to evade detection by a model scanner. T

AI security

LLM Response Rendering

An adversary may get a large language model (LLM) to respond with private information that is hidden from the user when the response is rendered by the user's c

AI security

Serverless

Adversaries may purchase and configure serverless cloud infrastructure, such as Cloudflare Workers, AWS Lambda functions, or Google Apps Scripts, that can be us

AI security

Drive-by Compromise

Adversaries may gain access to an AI system through a user visiting a website over the normal course of browsing, or an AI agent retrieving information from the

AI security

Stage Capabilities

Adversaries may upload, install, or otherwise set up capabilities that can be used during targeting. To support their operations, an adversary may need to take

AI security

AI Agent Context Poisoning

Adversaries may attempt to manipulate the context used by an AI agent's large language model (LLM) to influence the responses it generates or actions it takes.

AI security

Memory

Adversaries may manipulate the memory of a large language model (LLM) in order to persist changes to the LLM to future chat sessions. Memory is a common featu

AI security

Thread

Adversaries may introduce malicious instructions into a chat thread of a large language model (LLM) to cause behavior changes which persist for the remainder of

AI security

Modify AI Agent Configuration

Adversaries may modify the configuration files for AI agents on a system. This allows malicious changes to persist beyond the life of a single agent and affects

AI security

RAG Credential Harvesting

Adversaries may attempt to use their access to a large language model (LLM) on the victim's system to collect credentials. Credentials may be stored in internal

AI security

Credentials from AI Agent Configuration

Adversaries may access the credentials of other tools or services on a system from the configuration of an AI agent. AI Agents often utilize external tools or

AI security

Discover AI Agent Configuration

Adversaries may attempt to discover configuration information for AI agents present on the victim's system. Agent configurations can include tools or services t

AI security

Embedded Knowledge

Adversaries may attempt to discover the data sources a particular agent can access. The AI agent's configuration may reveal data sources or knowledge. The emb

AI security

Tool Definitions

Adversaries may discover the tools the AI agent has access to. By identifying which tools are available, the adversary can understand what actions may be execut

AI security

Activation Triggers

Adversaries may discover keywords or other triggers (such as incoming emails, documents being added, incoming message, or other workflows) that activate an agen

AI security

Data from AI Services

Adversaries may use their access to a victim organization's AI-enabled services to collect proprietary or otherwise sensitive information. As organizations adop

AI security

RAG Databases

Adversaries may prompt the AI service to retrieve data from a RAG database. This can include the majority of an organization's internal documents.

AI security

AI Agent Tools

Adversaries may prompt the AI service to invoke various tools the agent has access to. Tools may retrieve data from different APIs or services in an organizatio

AI security

Exfiltration via AI Agent Tool Invocation

AI agent tools capable of performing write operations may be invoked to exfiltrate data to an adversary. Sensitive information can be encoded into the tool's in

AI security

Gather Victim Identity Information

Adversaries may gather information about the victim's identity that can be used during targeting. Information about identities may include a variety of details,

AI security

Generate Deepfakes

Adversaries may use generative artificial intelligence (GenAI) to create synthetic media (i.e. imagery, video, audio, and text) that appear authentic. These "[d

AI security

Process Discovery

Adversaries may attempt to get information about processes running on a system. Once obtained, this information could be used to gain an understanding of common

AI security

OS Credential Dumping

Adversaries may extract credentials from OS caches, application memory, or other sources on a compromised system. Credentials are often in the form of a hash or

AI security

Use Alternate Authentication Material

Adversaries may use alternate authentication material, such as password hashes, Kerberos tickets, and application access tokens, in order to move laterally with

AI security

Manipulate User LLM Chat History

Adversaries may manipulate a user's large language model (LLM) chat history to cover the tracks of their malicious behavior. They may hide persistent changes th

AI security

Application Access Token

Adversaries may use stolen application access tokens to bypass the typical authentication process and access restricted accounts, information, or services on re

AI security

Prompt Infiltration via Public-Facing Application

An adversary may introduce malicious prompts into the victim's system via a public-facing application with the intention of it being ingested by an AI at some p

AI security

Delay Execution of LLM Instructions

Adversaries may include instructions to be followed by the AI system in response to a future event, such as a specific keyword or the next interaction, in order

AI security

Triggered

An adversary may trigger a prompt injection via a user action or event that occurs within the victim's environment. Triggered prompt injections often target AI

AI security

Search Open Websites/Domains

Adversaries may search public websites and/or domains for information about victims that can be used during targeting. Information about victims may be availabl

AI security

AI Service API

Adversaries may communicate using the API of an AI service on the victim's system. The adversary's commands to the victim system, and often the results, are emb

AI security

Virtualization/Sandbox Evasion

Adversaries may employ various means to detect and avoid virtualization and analysis environments. This may include changing behaviors based on the results of c

AI security

AI Agent Tool Credential Harvesting

Adversaries may attempt to use their access to an AI agent on the victim's system to retrieve data from available agent tools to collect credentials. Agent tool

AI security

AI Agent Tool Data Poisoning

Adversaries may place malicious content on a victim's system where it can be retrieved by an AI Agent Tool. This may be accomplished by placing documents in a l

AI security

AI Agent Clickbait

Adversaries may craft deceptive web content designed to bait Computer-Using AI agents or AI web browsers into taking unintended actions, such as clicking button

AI security

Data Destruction via AI Agent Tool Invocation

Adversaries may invoke an AI agent's tool capable of performing mutative operations to perform Data Destruction. Adversaries may destroy data and files on speci

AI security

Generate Malicious Commands

Adversaries may use large language models (LLMs) to dynamically generate malicious commands from natural language. Dynamically generated commands may be harder

AI security

Deploy AI Agent

Adversaries may launch AI agents in the victim's environment to execute actions on their behalf. AI agents may have access to a wide range of tools and data sou

AI security

Publish Poisoned AI Agent Tool

Adversaries may create and publish poisoned AI agent tools. Poisoned tools may contain an [LLM Prompt Injection](/techniques/AML.T0051), which can lead to a var

AI security

Poisoned AI Agent Tool

A victim may invoke a poisoned tool when interacting with their AI agent. A poisoned tool may execute an [LLM Prompt Injection](/techniques/AML.T0051) or perfor

AI security

Malicious Link

An adversary may rely upon a user clicking a malicious link in order to gain execution. Users may be subjected to social engineering to get them to click on a l

AI security

Escape to Host

Adversaries may break out of a container or virtualized environment to gain access to the underlying host. This can allow an adversary access to other container

AI security

Exploitation for Credential Access

Adversaries may exploit software vulnerabilities in an attempt to collect credentials. Exploitation of a software vulnerability occurs when an adversary takes a

AI security

Exploitation for Defense Evasion

Adversaries may exploit a system or application vulnerability to bypass security features. Exploitation of a vulnerability occurs when an adversary takes advant

AI security

AI Agent

Adversaries may abuse AI agents present on the victim's system for command and control. AI agents are often granted access to tools that can execute shell comma

AI security

AI Supply Chain Rug Pull

Adversaries may publish legitimate AI components or software, gain user adoption, then push an update with a malicious variant, leading to [AI Supply Chain Comp

AI security

AI Agent Tool Poisoning

Adversaries may achieve persistence by poisoning tools used by AI agents including built-in tools or tools available to the agent via Model Context Protocol (MC

AI security

AI Agent Tool

Adversaries may target AI agent tools as a means to compromise a victim's AI supply chain. Tools add capabilities to AI agents, allowing them to interact with o

AI security

Excessive Queries

Adversaries may send an excessive number of otherwise normal or low-complexity queries to an AI system with the goal of overwhelming its capacity and increasing

AI security

Resource-Intensive Queries

Adversaries may craft inputs specifically designed to increase the compute resources required for processing. For generative AI models, adversaries may use lon

AI security

Agentic Resource Consumption

Adversaries may coerce an agentic AI system into performing computationally expensive tool calls that waste resources and consume API budgets. They may utilize

AI security

Call Chains

Adversaries may extract call chains from AI agent configurations, which can reveal potentially targets for remote code execution (RCE) or other vulnerabilities.

AI security

AI Supply Chain Reputation Inflation

AI Supply Chain Reputation Inflation is the process of building or leveraging genuinely credible-looking trust signals to increase the perceived legitimacy of A

AI security

Machine Compromise

Adversaries may compromise a machine by exploiting or manipulating AI-enabled components on the system. Compromising a victim system allows the adversary to exe

AI security

AI Service Proxies

Adversaries may utilize commercial proxy services that resell access to AI services such as frontier model APIs. This infrastructure can be used to conduct lar

AI security

Local AI Agent

Adversaries may achieve full system compromise by abusing AI agents running locally on a host, such as computer-use agents or AI-driven browsers. These agents a

AI security

AI Artifacts

Adversaries may achieve full system compromise by introducing malicious AI artifacts, such as models or data, that contain embedded malware or other malicious c

AI security

Deepfake-Assisted Phishing

Adversaries may use deepfakes (AI-generated synthetic images, audio, or video) in phishing campaigns to impersonate trusted individuals, executives, or organiza

AI security

AI Agent Configuration

Adversaries may acquire publicly accessible AI agent configuration files to understand agent capabilities, gain unauthorized access to tools and data sources, o

AI security

Code Repositories

Adversaries may search public code repositories for information about a victim or victim system that can be used during targeting. Victims may store code or art

C4AIL/labour

Substrate

The earned, tacit core of capability — domain judgment built over years that can't be written down, downloaded, or outsourced.

C4AIL/labour

Surface

The visible, learnable layer — tools, interfaces, workflows, vocabulary. Fast to learn, fast to replace, useless without substrate.

C4AIL/labour

Epistemic Labour

The work of knowing whether AI output is true and sound — reading meaning and nuance, not just fact-checking. The labour AI makes scarce.

C4AIL/labour

Intellectual Labour

Weightless cognitive production — drafting, coding, analysing. The labour AI is commoditising now.

C4AIL/labour

Accountability Labour

Owning the decision and bearing the consequence — the one thing AI can't do and you can't delegate.

C4AIL/labour

Architectural Labour

Building the systems through which AI operates — the growth category where the new jobs live.

C4AIL/institution

The Squeezed Middle

AI lifts novices and supercharges the few, but hollows the mid-level rung where experts were actually made — breaking the pipeline.

C4AIL/strategy

Power Law Divergence

AI doesn't lift everyone evenly — outcomes split into a power law: the few who pair judgment with AI-direction pull far ahead.

C4AIL/strategy

The Moat Inversion

For two centuries value flowed to the explicit and scalable; AI exhausts that, so the only moat left is the irreducibly human.

C4AIL/strategy

Concretisation

Using AI to turn an organisation's tacit know-how into explicit, proprietary, scalable assets — finally codifying 'how we really do it'.

C4AIL/strategy

Commoditisation Resistance

The practices that keep human substrate visible enough to pay for — so it isn't commoditised away.

C4AIL/strategy

AI Theatre

High adoption, high confidence, zero verification — an organisation that looks like it's 'doing AI' while granting Epistemic Credit to unverified output.

C4AIL/strategy

Workslop

AI-generated content that looks like good work but lacks substance — and creates more work for others to fix.

C4AIL/strategy

Capability Transfer

The third path: hire experts to BUILD the capability inside your organisation, not to do the work for you.

C4AIL/institution

The Forge

A third model of professional education for when experts are scarce and content is free — deliberately rebuilding how substrate gets made.

C4AIL/institution

AI Guildhall Studio

A physical supervised-practice space where people do real, stakes-bearing AI work under expert eyes — and a deliberate third space.

C4AIL/institution

Adjacency Pathway

A fast track for mid-career domain experts to port their existing judgment into AI work — months, not years.

C4AIL/method

The Knowledge Layer

The structured, curated knowledge an AI system runs on — your codified context, owned by you.

C4AIL/awareness

The Awareness Model

C4AIL's map of AI consciousness: four tiers (Unaware, User, Amplifier, Orchestrator) across seven maturity levels (L0-L6).

C4AIL/awareness

Epistemic Credit

The unearned trust people grant to AI's fluent output because it sounds authoritative.

C4AIL/awareness

Eloquence Trap

Mistaking fluent, confident AI output for correct output — the single most dangerous AI failure.

C4AIL/awareness

Verification Capacity

The competency AI adoption requires MORE of, not less: judging AI output — catching the error, supplying missing context, engaging rather than deferring.

C4AIL/awareness

Decision Survivability

The real test of AI maturity: can you defend the decision after it goes wrong?

C4AIL/awareness

Minimum Viable Literacy

Enough AI understanding for a leader to commission, interrogate, and challenge expert advice — not to become the expert.

C4AIL/awareness

Translator

A leader who makes AI's infrastructure-level reality legible to decision-makers — bridging what the tech does and what the business must decide.

C4AIL/awareness

Orchestrator

The rare practitioner who designs the AI capability others amplify, and protects control as it scales.

C4AIL/awareness

Human Mirror

Reflecting AI output against your context, intent, and experience — the human supplying the meaning the machine can't.

C4AIL/method

Sovereign Command

Human authority kept above machine fluency — the organisation owns, can defend, and can scale its AI decisions without losing control.

C4AIL/method

ARGS

The four pillars of AI sovereignty: Agency, Architecture, Governance, Scaling.

C4AIL/method

CAGE

The context-engineering protocol for directing AI: Context, Align, Goals, Examples.

C4AIL/method

ARCH

The agentic-execution loop made human-legible: Action, Reasoning, Contextual check, Horizon.

C4AIL/method

Logic Pipes

Structured reasoning chains that turn AI's probabilistic output into reliable, repeatable outcomes.

C4AIL/method

98/2 Principle

A reliable AI system is ~98% deterministic software (the harness you own) and ~2% probabilistic AI at the edge.

C4AIL/security

Crown Jewels

The handful of data and systems that, if lost, end you — identify and protect those first.

C4AIL/strategy

The Institutional Vault

C4AIL's universal name for the codified knowledge store — the explicit knowledge your AI runs on. The Vault holds and *runs the rules the Brain codified* (the d

C4AIL/awareness

Reliability Trap

Errors compound multiplicatively across multi-step and agentic AI chains - each step looks fine, the total does not.

C4AIL/institution

Atrophy Trap

Permanently delegating judgment to AI (or to one bridge-role) makes the whole organisation progressively unable to do or judge the work.

C4AIL/awareness

Confidence Plateau

AI removes the visible failure that normally corrects overconfidence, so people grow more confident while growing less capable.

C4AIL/strategy

Comprehension Debt

The accumulating weight of decisions made by people who no longer understand the logic behind their own work.

C4AIL/method

Legibility Debt

The gap between what an organisation knows and what it has made available in a form machines can act on.

C4AIL/method

The Inverted Stack

Putting probabilistic AI where deterministic rules belong - letting the model make the call that should be hard-coded.

C4AIL/method

The Verification Bottleneck

A brilliant expert drowning in manual line-by-line review of AI output - what domain expertise without AI architecture produces.

C4AIL/strategy

Leverage Leaks

The three ways organisations lose even the value their best people create: Architecture, Infrastructure, and Talent leaks.

C4AIL/governance

Compliance Theatre

Policies filed and training completed that satisfy the auditor without changing the outcome - the governance Eloquence Trap.

C4AIL/method

The Knowledge Paradox

The organisations that most need structured AI use are the ones least able to initialise it, because their knowledge was never made legible.

C4AIL/labour

The Four Labours

Work decomposed by the human it requires: Intellectual (commoditised), Physical (lags), Accountability (the monopoly), Architectural (the growth category).

C4AIL/strategy

Two-Sided Risk

AI risk is the risk of adopting badly AND the competitive risk of falling behind - governance must weigh both, not only say no.

C4AIL/strategy

The Cost of Not Acting

The quantifiable price of inaction - lost margin, talent, and market position from moving too slowly.

C4AIL/institution

Floor and Ceiling

The 90-95% who work through AI (the Floor) and the 5-10% who design and govern it (the Ceiling).

C4AIL/institution

The Five Roles

Floor User, Translator, Architect, Orchestrator, Trainer - defined by labour function, not job title.

C4AIL/awareness

Architect

The L3-4 builder who turns expert knowledge into deterministic AI workflows - Logic Pipes, CAGE templates, verification engines.

C4AIL/awareness

Trainer

An Orchestrator who develops others - the role most organisations forget, and the one that keeps the pipeline alive.

C4AIL/awareness

Floor User

The domain expert (L0-2) working through AI-structured interfaces - the 90-95% backbone, not a lesser role.

C4AIL/institution

The CAIO

The Translator made institutional - a Direct-seat Orchestrator measured by dispensability, not by being the bottleneck.

C4AIL/institution

The Four Seats

One AI story told from four accountabilities: Direct (Board), Operate (Manager), Build (Practitioner), Floor (User).

C4AIL/method

Spec Loop vs Chat Loop

Fix the specification so the correction compounds (Spec Loop), instead of fixing the conversation and repeating it next time (Chat Loop).

C4AIL/method

Living Material

AI output is provisional and version-controlled - decisions get review dates, not just approval dates.

C4AIL/method

The Harness

The deterministic 98% you own and engineer - gates, autonomy tiers, audit log, kill path - wrapped around the swappable model.

C4AIL/governance

The Six Numbers

The governance dashboard that measures whether AI use actually works: first-time-right, acceptance-without-verification, rework, error-classification, correctio

C4AIL/governance

Bright Lines

Clear boundaries for which actions AI may take alone versus which need a human sign-off - drawn where accountability begins.

C4AIL/governance

Autonomy Tiers

AI actions classified by autonomy x reversibility - irreversible or high-blast-radius actions are always-ask.

C4AIL/governance

Agent-as-Principal

An AI agent is a distinct, revocable identity with scoped credentials - never a human's full rights.

C4AIL/governance

The Accountability Sink

A consequential action taken under delegated authority with no human in the moment - accountability closing with no one inside it.

C4AIL/security

The Intern Test

Would you give an intern this access and let them act for you? If not, do not give it to the AI agent.

C4AIL/security

The Pre-AI Permission Audit

Tighten your file and data permissions before you deploy any AI search tool - the highest-return security action.

C4AIL/institution

The Co-Creation Model

Redesign the junior role so AI does the volume and the junior does the judgment under a senior who develops their taste.

C4AIL/institution

The Trainer Paradox

You need advanced practitioners to develop advanced practitioners - and they barely exist yet.

C4AIL/institution

Novice Pathway

Building substrate from scratch - the slow, uncompressible 3-5 year track to Orchestrator.

C4AIL/institution

The Signing Moment

The threshold where a qualified human puts their name on the work and owns it - where accountability is claimed.

C4AIL/security

GOVERN-IDENTIFY-SECURE-VALIDATE

Ethan's Practical Cybersecurity Decisions roadmap - govern the risk, identify the crown jewels, secure them, validate it works.

C4AIL/security

The Five Pillars

Practical Cyber's five domains to secure: Identity, Devices, Network, Applications, Data.

C4AIL/security

SRP

Safety, Reliability, Productivity - the Practical Cyber reframe of the CIA triad for a business audience.

C4AIL/awareness

The Maturity Scale (level register)

The seven AI maturity levels (L0-L6), named in TWO registers - blunt (technical/whitepaper) and soft (customer/marketing); same rung, only the label changes.