Vocabulary

Agentic engineering picked up its own words fast. Some are settled across the industry, some come from one blog post, and some are forum slang. This page lists the ones worth knowing: what each means, who named it, and how settled it is. Use the right word, and follow the link when you want the original. Every entry links to its source. Each one was checked against that source in October 2026.

Label	Meaning
Standard	Several independent companies or authors use it with the same meaning. Safe to use as is.
Emerging	Two or three credible uses. Fine to use, best with credit (“Breunig’s context clash”).
One source	One company or author. Worth knowing; say where it comes from.
Slang	Forum talk with no defined source. Say what you mean instead.

The context window

Everything the agent knows when it acts sits in its context window. Most of the named problems are about what goes into that window and how it decays.

What goes wrong

Term	What happens	Named by	How settled
Context rot	The more tokens in the context, the worse the model recalls and reasons. More context is not automatically better.	A Hacker News comment (June 2025), measured by Chroma, defined by Anthropic	Standard
Lost in the middle	Facts at the start or end of a long input get used; facts in the middle get missed.	Liu et al., 2023	Standard
Context poisoning	A wrong fact or hallucination gets into the context, and the model keeps building on it.	Gemini 2.5 report; Drew Breunig, 2025	Emerging
Context distraction	The context grows so long that the model leans on it and neglects what it learned in training.	Drew Breunig, 2025	Emerging
Context confusion	Extra content, most often too many tool definitions, drags the answer down.	Drew Breunig, 2025	Emerging
Context clash	New information conflicts with what is already in the context.	Drew Breunig, 2025	Emerging
Lost in conversation	One wrong turn early in a multi-turn chat and the model rarely recovers. The study measured a 39% average drop versus one complete prompt.	Laban et al. (Microsoft), 2025	Emerging
Context pollution	Irrelevant or stale content, such as failed attempts and unrelated tasks, piles up and degrades the output.	No single author; used by Anthropic	Emerging
Attention budget	The model has a limited budget of attention, and every token spends some of it.	Anthropic, 2025	Emerging
Context anxiety	A model that knows its window size rushes or wraps up early, believing it is near the end when it isn’t.	Cognition (Devin), 2025	Emerging
Dumb zone	Past a certain fill level, the agent’s decisions get noticeably worse.	Dex Horthy (HumanLayer), 2025	Emerging
Goal drift	Over a long run, the agent wanders away from its original objective.	Arike et al., 2025	Emerging
Context collapse	Summarising a context again and again erodes the details until little useful is left.	Zhang et al. (ACE paper), 2025	One source
Kitchen sink session	One chat for unrelated tasks, so each task’s leftovers crowd the next.	Anthropic, Claude Code docs	One source

The moves that fix it

Term	What you do	Named by	How settled
Context engineering	The umbrella: choose and maintain the right tokens in the window for each step.	No single author (2025)	Standard
Compaction	Summarise the conversation near the limit and continue in a fresh window from the summary.	Defined by Anthropic	Standard
Sub-agents (context isolation)	Hand a focused task to a sub-agent with its own clean window; only a short summary comes back.	Anthropic; “context quarantine” is Breunig’s name	Standard
RAG	Fetch only the relevant information into the context instead of loading everything.	Lewis et al., 2020	Standard
Progressive disclosure	Keep a short version always loaded and open the detail only when it is needed. The design idea behind Agent Skills.	From UX design; Anthropic for agents	Emerging
Just-in-time retrieval	Keep pointers (file paths, queries, links) and load the content at the moment it is needed.	Anthropic, 2025	Emerging
Write, select, compress, isolate	Four groups of moves: write context outside the window, select what goes in, compress it, split it up.	Lance Martin (LangChain), 2025	Emerging
Context pruning	Remove what the task no longer needs.	Drew Breunig, 2025	Emerging
Context offloading	Store information outside the context, such as in files or notes, and read it back when needed.	Drew Breunig, 2025	Emerging
Recitation	Keep rewriting a `todo.md` so the plan stays at the end of the context, where attention is strongest.	Manus, 2025	Emerging
Tool loadout	Load only the tool definitions this task needs.	Drew Breunig, 2025	One source
Tool search	Let the agent search for tools on demand instead of loading them all up front.	Anthropic, 2025	One source
Intentional compaction	Before the window fills, have the agent write the work so far into a file you can review, then continue from that.	Dex Horthy (HumanLayer), 2025	One source
Context reset (handoff)	Clear the window entirely and start a fresh agent, with a written handoff of state and next steps.	Anthropic, 2025	One source
Structured note-taking	The agent writes notes outside the window and reads them back later.	Anthropic, 2025	One source

If you see this, reach for that

You notice	Reach for
The agent gets worse as the chat gets long (context rot, dumb zone)	Compaction, or a context reset with a handoff file
The agent keeps building on a wrong idea (context poisoning)	A fresh chat with a corrected prompt, not more arguing in the same one
Too many tools, and it picks the wrong one (context confusion)	Tool loadout or tool search
Instructions contradict each other (context clash)	One rule in one place; prune the rest
Exploration output floods the chat (context pollution)	A sub-agent that returns only the summary
The instructions file keeps growing	Progressive disclosure: a short root file that points to detail

Prompts and instructions

Term	What it means	Named by	How settled
Sycophancy	The model tells you what you want to hear instead of what is true.	Research term; Sharma et al., 2023	Standard
Prompt bloat	The prompt or instructions file grows so big that important rules get lost. Anthropic calls one form “the over-specified CLAUDE.md”.	Anthropic and others	Emerging
Prompt debt	Quick fixes pile up in a prompt until nobody dares touch it.	Drew Breunig, 2026	Emerging
Prompt overfitting	A prompt tuned on a few cases scores well there and worse everywhere else.	Borrowed from machine learning	Emerging
Aggressive prompt language	”CRITICAL: you MUST…”. Newer models follow the system prompt more closely, so shouting makes them over-trigger.	Anthropic docs	Emerging
Pink Elephant problem	Telling a model not to mention something tends to bring it up.	Castricato et al., 2024	Emerging
Overeagerness	The agent goes beyond the task: extra files, extra abstractions, changes nobody asked for.	Anthropic docs	Emerging
Prompt drift	The same prompt behaves differently over time. People mean three things by it: the model changed, your own edits regressed it, or it fades over a long chat.	The Prompt Report	Emerging
Whack-a-mole	Each prompt patch for one failure causes another somewhere else, and progress stalls.	Storf et al., 2026	One source
Fighting the weights	Asking for something the model’s training pulls against; repeating it louder doesn’t help.	Drew Breunig, 2025	One source
Right altitude	The fix side: write instructions between brittle hard-coded rules and vague guidance.	Anthropic, 2025	One source

Checking the work

Term	What it means	Named by	How settled
Reward hacking	The model games the score instead of doing the task.	AI safety research, 2016	Standard
Special-casing tests	The agent hard-codes the expected test values instead of writing the real logic.	Anthropic	Emerging
Declaring done too early	The agent marks the task done without testing it end to end.	Anthropic	One source
Doom loop	Going round in circles asking the agent to fix something it can’t.	No known author	Emerging
Package hallucination	The agent imports a package that doesn’t exist.	Lanyado (Vulcan Cyber), 2023	Emerging
Evals	Tests for AI behaviour: an input, the output, and grading logic.	No single author	Standard
LLM-as-a-judge	A strong model grades another model’s or agent’s output.	Zheng et al., 2023	Standard
Error analysis	Read real traces, note each failure, group the notes into categories and count them, so you know which evals are worth writing.	Hamel Husain and Shreya Shankar	One source
Plan mode	The agent researches and proposes a plan, and nothing is edited until you approve it.	Cline, Claude Code, Cursor	Standard
Spec-driven development	Write a structured spec first and treat it as the source of truth for you and the agent. The meaning is still loose.	Kiro, GitHub Spec Kit, Böckeler	Standard
TDD with agents	The agent writes failing tests first, then works until they pass.	Kent Beck, Simon Willison	Emerging
Generator and evaluator	A second, sceptical agent grades the first agent’s work.	Anthropic, 2024	Emerging
Backpressure	Builds, types, linters and tests that let the agent catch its own mistakes before you have to.	Geoffrey Huntley; Moss, 2026	Emerging

Running agents safely

Term	What it means	Named by	How settled
Prompt injection	Untrusted text in the prompt makes the model follow the attacker instead of you.	Simon Willison, 2022	Standard
Lethal trifecta	An agent with private data, untrusted content and a way to send data out can be tricked into leaking it.	Simon Willison, 2025	Standard
Slopsquatting	Attackers register package names that models tend to hallucinate.	Seth Larson, 2025	Emerging
Agent harness	Everything around the model: tools, instructions, hooks, loop. “Agent = model + harness.”	No single author	Standard
Harness engineering	Every time the agent makes a mistake, add a rule, tool or check so it can’t happen again.	Mitchell Hashimoto, 2026	Standard
Agent loop	A model running tools in a loop until a goal is met.	No single author	Standard
Hooks	Commands that run at fixed points in the agent’s lifecycle. They are deterministic, so use them for rules that must always hold.	Claude Code	Standard
Guardrails	Runtime checks around an AI app. Vague across vendors: name the mechanism when it matters.	NVIDIA NeMo, OpenAI and others	Standard
Sandboxing	The agent runs inside fixed walls (files, network) so it can work freely without harm.	Security term; Anthropic, Willison for agents	Standard
Least privilege	Give the agent only the access the task needs.	Saltzer, 1974; OWASP for agents	Standard
Human in the loop	A person approves consequential actions before they happen. “On the loop”: a person watches and can stop it.	Older term	Standard
Agents Rule of Two	In one session, an agent may have at most two of three: untrusted input, sensitive access, outside actions.	Meta, 2025	Emerging
YOLO mode	Everything approved by default. Every source says: only inside a sandbox.	Cursor feature name, 2024	Emerging
Ralph loop	Feed the same prompt to a coding agent again and again. Each round does one task in a fresh context; progress lives in files and git.	Geoffrey Huntley, 2025	Emerging

The person using the agent

Term	What it means	Named by	How settled
Vibe coding	Accept everything, don’t read the diffs, paste errors back and see what works.	Andrej Karpathy, 2025	Standard
AI slop	Unreviewed AI output pushed on people who didn’t ask for it.	Popularised by Simon Willison, 2024	Standard
Automation bias	Trusting the machine’s answer over better information you already have.	Aviation research, 1990s	Standard
Comprehension debt	The team ships code faster than it can understand it.	Jason Gorman, 2025	Emerging
Skill atrophy	Skills fade because the thinking is always delegated.	Addy Osmani, 2025	Emerging
Approval fatigue	After many permission prompts, people stop reading what they approve.	Anthropic, 2025	Emerging
70% problem	AI gets non-engineers 70% of the way fast; the last 30% turns into diminishing returns.	Addy Osmani, 2024	One source
Agentic engineering	The professional version: the agent implements, the engineer owns architecture, quality and correctness.	Andrej Karpathy, 2026	Emerging

Where the experts disagree

These are open questions. Know both sides before you pick one.

Keep failed attempts in the context, or clear them? Manus keeps errors in so the model learns from them. Anthropic says that after two failed corrections you should /clear and write a better prompt.
Remove tools, or hide them? Manus never adds or removes tools mid-task; it blocks the ones not allowed at decoding time. Tool loadout and Anthropic’s tool search load fewer tools instead.
Sub-agents, or one agent? Anthropic recommends sub-agents to keep context clean. Cognition argues “Don’t build multi-agents”: keep one thread that sees the full history.
Compact, or hand off? Amp dropped compaction for handoffs in late 2025, then brought it back in 2026.

Words with more than one meaning

Harness: the agent harness (everything around the model), an eval harness, or a test harness. Say which.
Plan mode: a product mode (plan, approve, then edit), “plan-then-execute” (a security pattern), or LangChain’s planner-and-executor agents.
Hooks: lifecycle scripts in Claude Code, event automations in Kiro, middleware in LangChain.
Compaction: usually summarising the chat. Manus uses it for swapping tool results for file pointers.
Context confusion: Breunig’s meaning is too much irrelevant content, usually too many tools. It does not mean the agent mixing up which task it is on.

Slang you’ll hear

You hear	What people mean	Say instead
”It got lobotomized”	Either the agent forgot your rules after auto-compaction, or a new model release feels dumber.	Context rot or context collapse for the first; name the release and the behaviour for the second.
”Babysitting the agent”	Spending your time watching and correcting it instead of building.	Missing backpressure: add the checks that let it catch its own mistakes.
”Boxing the agent”	AI boxing is an AI-safety idea about containing a superintelligence. It is not a prompting term.	Sandboxing, least privilege.

Level Up

Mindset

Setup

Quick Reference

The context window

What goes wrong

The moves that fix it

If you see this, reach for that

Prompts and instructions

Checking the work

Running agents safely

The person using the agent

Where the experts disagree

Words with more than one meaning

Slang you’ll hear

​The context window

​What goes wrong

​The moves that fix it

​If you see this, reach for that

​Prompts and instructions

​Checking the work

​Running agents safely

​The person using the agent

​Where the experts disagree

​Words with more than one meaning

​Slang you’ll hear

The context window

What goes wrong

The moves that fix it

If you see this, reach for that

Prompts and instructions

Checking the work

Running agents safely

The person using the agent

Where the experts disagree

Words with more than one meaning

Slang you’ll hear