Core Concepts#

Foundational building blocks of the agent ecosystem: the structural components of an agent, the capabilities that drive its behavior, and the platform-level mechanisms that shape how it operates and interacts.


abstraction#

Definition: label and/or concept that bundles together a set of underlying components or capabilities; streamlines communication by hiding implementation details

Purpose: lets agents, teams, and platforms reason about complex systems at a higher level without tracking every internal part; understanding what an abstraction hides is often necessary for diagnosing unexpected behavior

Example: “agent” is an abstraction for a collection of distinct parts

Related Terms: agent, automation, harness, spec


agent#

Definition: autonomous system that perceives its environment, makes decisions, and takes actions to achieve goals; typically LLM-based, able to use tools, maintain memory, and execute multi-step tasks

Purpose: converts raw LLM capability into goal-directed, self-directed task execution; distinct from chatbots, process automation, and workflow engines through autonomy

Example: an agent that retrieves a file, edits it, and runs a command to complete a request without step-by-step human instruction

Related Terms: abstraction, automation, memory, planning, self-reflection


assistant message#

Definition: output generated by an agent or LLM during a conversational turn; paired with user messages to form the back-and-forth history the agent uses as context

Purpose: represents the agent’s side of an exchange and contributes to the accumulated conversation history that informs subsequent responses

Related Terms: turn, user message


automation#

Definition: use of technology to perform tasks with minimal human intervention; can range from basic rule-based systems to complex machine learning models

Purpose: in an AI context, delegates decision-making or execution to algorithms, robots, or automated agents to reduce manual effort and increase consistency

Related Terms: abstraction, agent, harness


context window#

Definition: total amount of text, measured in tokens, an LLM can process at once; includes system prompt, conversation history, and any injected context

Purpose: bounds what information is directly available to the LLM during a given interaction; content outside the window is not directly accessible

Related Terms: /SKILL, context window management, memory, system prompt, temperature


context window management#

Definition: agent platform strategies to handle conversations that approach or exceed the context window limit; determine what gets retained, compressed, or dropped as conversations grow long

Purpose: avoids failures and quality loss from extended interactions; the quality of the strategy affects whether an agent may “forget” earlier instructions

Example: summarizing earlier turns or selectively truncating old messages to keep the conversation within bounds

Related Terms: context window, memory, system prompt


gate#

Definition: prompt condition that must be satisfied before a work sequence continues; provides objectively evaluable agentic checkpoints — thing happens → condition → proceed

Purpose: enforces deterministic progression that an LLM cannot loophole; contrasts with rules, which an LLM can interpret, bypass, or rationalize around, and with hooks, which are triggered by events in the harness

Related Terms: hook, rule


hallucination#

Definition: type of AI output that’s false, fabricated, or unsupported information; appears plausible but isn’t grounded in training data or provided context

Purpose: a critical quality-control concern in AI systems; understanding hallucination helps diagnose failures and informs evaluation of truthfulness and robustness

Related Terms: agent, evaluation, memory, observability, self-reflection, SimpleQA


harness#

Definition: platform layer that wraps around an LLM; provides configuration, permission settings, system prompts, and tools

Purpose: shapes agent behavior independently of the underlying LLM; agents sharing the same LLM can behave very differently depending on their harness configuration

Example: code search, file operations, shell execution, web access, content management strategy, and temperature settings

Related Terms: abstraction, automation, gate, hook, MCP server, permission and safety systems, temperature


heuristic#

Definition: practical problem-solving approach that uses shortcuts or rules of thumb to find satisfactory solutions; differs from algorithms that guarantee optimal solutions

Purpose: trades optimality for speed and feasibility when exhaustive search is impractical; in agent systems, guides decision-making when perfect information or unlimited computation is unavailable

Example: A* search, greedy algorithms, hand-crafted evaluation functions

Related Terms: planning, self-reflection


hook#

Definition: script or callback that runs automatically in response to a specific event in the agent’s environment; fires deterministically based on triggers, such as a file being edited, without going through the LLM’s interpretation loop

Purpose: enforces constraints reliably without relying on the agent to remember them; contrasts with gates, which block progression on a condition, and with rules, which an LLM applies at its own discretion

Related Terms: /SKILL, gate, rule, slash command


LLM#

Definition: abbreviation for Large Language Model; model trained on vast amounts of text data to understand and generate human language; also known as “the agent’s brain”

Purpose: not all AI is LLM-based - computer vision models and recommendation systems are common non-LLM examples; the LLM is the reasoning component an agent’s harness wraps around

Example: GPT - Generative Pre-trained Transformer, Claude, and Llama

Related Terms: agent, harness, temperature


MCP server#

Definition: acronym for Model Context Protocol server; external server that exposes capabilities to an agent - tools, resources, and/or prompts

Purpose: lets agents interact with databases, APIs, cloud services, or custom systems the server is built to access; facilitates portable behavior across agent platforms because implementation lives in the server rather than the harness

Related Terms: harness


memory#

Definition: in an agent context, ability to store and retrieve information across interactions and tasks; enables agents to maintain context, learn from experience, and reference past actions

Purpose: critical for multi-step reasoning and adapting behavior based on history; types include short-term - current task, long-term - across sessions, and episodic - specific events

Related Terms: context window, context window management, planning, self-reflection


permission and safety systems#

Definition: platform-level rules that define what actions an agent is allowed to take; conceptual authorization and/or guardrails

Purpose: shape agent behavior independently of the underlying LLM and enforce safety boundaries on what an agent may execute

Example: requiring confirmation before running shell commands, restricting file access to specific directories, or blocking certain categories of action entirely

Related Terms: harness, observability, rule


observability#

Definition: formal framework within which agent evaluation is conducted; involves tracking, logging, and monitoring an agent’s behavior, decisions, and intermediate actions

Purpose: enables inspection of function calls, API responses, and retrieval steps to diagnose failures and understand what the agent actually did

Related Terms: permission and safety systems, self-reflection


planning#

Definition: agent capability to decompose complex goals into sequences of executable actions; fundamental building block for autonomous task execution

Purpose: involves reasoning about future states, choosing strategies, and organizing steps; ranges from basic linear plans to complex multi-step reasoning with contingencies

Related Terms: agent, memory, self-reflection


prompt#

Definition: input text or instructions given to an LLM to guide its response; quality and specificity of prompts significantly affect output quality

Purpose: is interpreted by the LLM (unlike direct commands) and is distinct from traditional search queries; related to the system prompt

Related Terms: /SKILL, system prompt, user message


RLHF#

Definition: acronym for reinforcement learning from human feedback; training methodology in which human evaluators rate LLM outputs and the ratings fine-tune the LLM toward preferred behaviors

Purpose: creates a strong instruction-following bias; LLMs trained with RLHF tend to prioritize explicit user instructions, sometimes at the expense of broader context

Related Terms: LLM, sycophancy, system prompt


rule#

Definition: prompt instruction an LLM interprets and applies at its own discretion; has an implicit opt-out path through which the LLM can rationalize skipping it

Purpose: guides behavior flexibly through LLM interpretation; contrasts with gates, which block progression until a condition is met, and with hooks, which fire deterministically from the harness regardless of LLM interpretation

Related Terms: gate, hook, permission and safety systems


self-reflection#

Definition: agent capability to evaluate its own reasoning, actions, and outputs; involves identifying errors, assessing performance, and adjusting strategy

Purpose: enables learning from mistakes and iterative improvement without external feedback; distinguishes more sophisticated agents from basic reactive systems

Related Terms: agent, memory, planning


/SKILL#

Definition: bundle of instructions and reference material that gives an agent just-in-time context for a specific domain or task

Purpose: works through LLM interpretation rather than deterministic execution, so it is subject to the same context window attention dynamics as other injected content; distinct from hooks and slash commands

Related Terms: context window, hook, prompt, slash command, system prompt


slash command#

Definition: direct command typed into a chat interface, such as /compact or /init; triggers specific agent behavior without going through the LLM’s interpretation loop

Purpose: provides more predictable and consistent action execution than natural language prompts; contrasts with prompts, which the LLM interprets and may execute differently across runs

Related Terms: /SKILL, hook, prompt


spec#

Definition: abbreviation for specification; implementation guide that informs everyone building on a format exactly what to expect

Purpose: documents which fields exist, what values are valid, how files should be structured, and what behavior is required versus optional

Related Terms: abstraction, harness, MCP server


sycophancy#

Definition: tendency in LLMs to agree with, validate, or comply with user input rather than reasoning independently; known limitation of RLHF-trained LLMs and an active area of research

Purpose: amplified by detailed or specific prompts, which push the LLM into “execution mode”; understanding sycophancy helps distinguish an agent’s genuine reasoning from compliance bias

Related Terms: hallucination, RLHF, self-reflection


system prompt#

Definition: set of instructions provided to the LLM by the platform before any user interaction begins; sits at the beginning of the context window, giving it strong positional attention weight

Purpose: typically not visible to the user, yet profoundly shapes the agent’s personality, default behaviors, and constraints

Related Terms: /SKILL, context window, prompt, temperature


temperature#

Definition: parameter that controls the degree of randomness in an LLM’s outputs; set by the platform and sometimes adjustable by the user

Purpose: affects agent behavior independently of the LLM itself - low temperature produces more focused, predictable responses; high temperature produces more varied, creative ones

Related Terms: context window, harness, system prompt


training data#

Definition: dataset used to teach an LLM patterns, relationships, and knowledge; the LLM learns by processing examples and adjusting internal parameters

Purpose: quality and composition of training data directly affects LLM capabilities and biases

Related Terms: context window, LLM


turn#

Definition: single exchange in a conversation: one user message and one assistant message; the agent considers the full turn history when generating a response

Purpose: provides the unit structure of a conversation that the agent references for context

Related Terms: assistant message, context window, user message


user message#

Definition: input sent by a human or automated system to an agent during a conversational turn; interpreted by the LLM rather than executed as a direct command

Purpose: receives strong positional attention as the most recent content in the context window, heavily influencing the agent’s response

Related Terms: assistant message, prompt, turn