Glossary

65 terms from "Delegating to an AI agent: a practical introduction." Look them up when you get stuck; the first mention in the text carries a hover definition.

TermDefinitionSource
agent taskA request with a produced deliverable, a bounded scope, and a way to check completion, which is what makes it worth delegating rather than just asking.Anthropic: Building Effective AI Agents
chat questionA request whose output is an answer you read and judge by understanding, with no fixed deliverable and no criteria to check it against.OpenAI Academy: AI Foundations
delegable taskA request you can hand off because someone other than the agent can tell whether it succeeded.OpenAI Academy: Agents and Workflows
temp workerThe course's image for an agent: a helper who can leave the desk, look things up, draft, and return, and who will guess when the instructions are vague.Anthropic: Building Effective AI Agents
chatbotAn AI that answers turn by turn without taking actions for you, so a mistake stays a wrong answer rather than becoming a wrong action.Anthropic: Building Effective AI Agents
clear goalOne sentence in the ask that states what finished looks like.Anthropic: Building Effective AI Agents
bounded scopeA stated limit on what the agent should not do, given at the same time as the goal.NimbleBrain: AI Agent Failure Modes
verification methodThe checklist you plan to compare the result against, decided before the agent starts.OpenAI Academy: Agents and Workflows
verifiable resultAn output whose correctness a human can settle by comparison, without asking the agent again.OpenAI Academy: Agents and Workflows
bounded output formatA stated shape for the deliverable — rows, columns, length, allowed values — that lets you check completeness by counting.OpenAI API: Prompt Engineering
finish lineThe point stated in the ask at which the job is over, which a chat-style request never supplies.OpenAI Academy: AI Foundations
single deliverableThe one artifact an agent task returns, so that checking has a definite object.OpenAI Academy: Agents and Workflows
clear askA structured request carrying task, requirements, boundaries, and acceptance criteria.OpenAI API: Prompt Engineering
four-part askThe template of task, then requirements, then boundaries, then acceptance criteria, written in that order.Claude Platform: Prompting Best Practices
one actionThe single operation named in the task line, with no hidden steps folded in.OpenAI API: Prompt Engineering
requirementsThe properties the output must have: format, length, tone, sources, structure.Claude Platform: Prompting Best Practices
boundariesThe part of the ask stating what the agent must not do, which heads off unwanted side trips.NimbleBrain: AI Agent Failure Modes
four pieces of informationThe lesson's framing of what an agent actually needs — as opposed to more words.OpenAI API: Prompt Engineering
vague wishA request like "make my résumé better" that names a direction but no action, shape, limit, or standard.OpenAI API: Prompt Engineering
do not read mindsThe lesson's reminder that an agent has only your prompt, not your intent.OpenAI API: Prompt Engineering
most common patternWhat an agent falls back on when the prompt leaves a gap: the interpretation seen most often in training, not your case.OpenAI API: Prompt Engineering
fence off unwanted behaviorWhat the boundaries step does: closing off actions before the agent has a chance to choose them.NimbleBrain: AI Agent Failure Modes
measurable outcomeA property of a rewritten output that can be confirmed by looking, such as a number appearing in a bullet.Claude Platform: Prompting Best Practices
optimize for the wrong goalWhat happens when the checklist appears before the task, so the agent aims at the criteria instead of the job.Claude Platform: Prompting Best Practices
verificationChecking each acceptance criterion against evidence, as opposed to reading the output.OpenAI Academy: Agents and Workflows
verification tableA three-column record of criterion, evidence, and pass or fail, used to check a deliverable.OpenAI Academy: Agents and Workflows
verification checklistThe short list of criteria, each specific enough to be checked without guessing, that you take into a review.OpenAI Academy: Agents and Workflows
acceptance criteriaThe conditions the output must meet, written before the agent starts and reused as the test afterwards.OpenAI Academy: Agents and Workflows
acceptance criterionA single condition from the checklist, checked on its own against its own evidence.OpenAI Academy: Agents and Workflows
criterion, evidence, and pass or failThe three columns of the verification table, naming the standard, where you looked, and the verdict.OpenAI Academy: Agents and Workflows
Reading is passiveThe course's contrast between reading an output and verifying it: reading takes what is offered, verification asks a question of it.OpenAI Academy: Agents and Workflows
confident toneThe assured delivery an agent uses regardless of whether the content is right, which is why tone carries no information about correctness.Anthropic: Building Effective AI Agents
looks about rightThe second trap in checking: moving on because the shape of the output matches what you expected.OpenAI Academy: Agents and Workflows
not a reliable judgeThe reason asking the agent whether it followed your instructions does not count as a check.Claude Platform: Prompting Best Practices
calendar dateThe countable form a deadline criterion demands, as opposed to a relative phrase like "ASAP" or "next sprint".OpenAI Academy: Agents and Workflows
specific ownerThe criterion that an action item names a person, not a team.OpenAI Academy: Agents and Workflows
countable propertyA criterion restated so it can be settled by inspection, replacing a subjective one.OpenAI Academy: Agents and Workflows
hallucinationAn invented fact, name, date, citation, or action produced with the same confidence as correct output.AI/TLDR: Common AI Agent Failure Modes
stale factInformation that was true once but is no longer current, because the agent's knowledge has a cutoff date.AIToolsUsageGuide: Why AI Gives Wrong Answers
scope shrinkWhen an agent quietly does less than you asked, narrows the request, or swaps in an easier task without telling you.AI/TLDR: Common AI Agent Failure Modes
non-answerA response that looks full — background, definitions, general advice — but never addresses the question asked.AI/TLDR: Common AI Agent Failure Modes
scope creepWhen an agent expands past its mandate and adds work you did not request — the opposite direction from scope shrink.NimbleBrain: AI Agent Failure Modes
four mistake typesThe course's checking framework: hallucination, stale facts, scope shrink, and non-answer, each with a different tell.AI/TLDR: Common AI Agent Failure Modes
plausible-looking continuationWhat the model actually produces at every step, which is why a hallucination is not a special malfunction.AI/TLDR: Common AI Agent Failure Modes
made-up citationA source, section, or quotation the agent produces that does not exist in the material.AI/TLDR: Common AI Agent Failure Modes
invented detailA fact the agent supplies that you never gave and no source contains, such as a time added to a party post.AI/TLDR: Common AI Agent Failure Modes
cutoff dateThe point past which the agent's training knowledge stops, which is what makes prices, policies, and versions go stale.AIToolsUsageGuide: Why AI Gives Wrong Answers
live sourceA current reference you require in the ask so a time-sensitive claim can be checked against the world rather than memory.AIToolsUsageGuide: Why AI Gives Wrong Answers
compare the claim against the sourceThe quick check for hallucination: locating the claim in the material rather than judging it by how it reads.AI/TLDR: Common AI Agent Failure Modes
quietly narrows the taskHow scope shrink presents: the agent answers one of three questions, summarizes instead of categorizing, or drops a boundary, without flagging it.NimbleBrain: AI Agent Failure Modes
easier neighboring questionThe question an agent answers instead of yours when yours is hard, producing a non-answer.AI/TLDR: Common AI Agent Failure Modes
different fingerprintThe reason the four types are worth separating: each leaves its own trace and needs its own check.AIToolsUsageGuide: Why AI Gives Wrong Answers
feedback loopThe designed-in cycle of reviewing output, saying what to fix, and checking the next draft against the same criteria.Anthropic: Building Effective AI Agents
correction loopThe four-step cycle: compare the output to the criteria, describe the failure specifically, let the agent revise, verify the new output against the same criteria.Anthropic: Building Effective AI Agents
mistake logA record of the original ask, the mistake type, how you spotted it, and the corrected result.Anthropic: Building Effective AI Agents
specific correctionA correction that names the location, the error, and the standard, so the agent can revise without guessing.Anthropic: Building Effective AI Agents
vague correctionA correction like "fix this" that leaves the agent room to guess again, lengthening the loop.Anthropic: Building Effective AI Agents
please do betterThe lesson's example of a correction that carries no information about what to change.Anthropic: Building Effective AI Agents
the location, the error, and the standardThe three things a correction must carry: where it is wrong, what is wrong, and what right looks like.Anthropic: Building Effective AI Agents
spot, report, revise, verifyThe four moves of the loop that make delegation reliable.Anthropic: Building Effective AI Agents
human feedbackThe input you supply at checkpoints, which is what keeps an autonomous agent from drifting off course.Anthropic: Building Effective AI Agents
checkpointsThe points where you stop the work and review it, rather than waiting for the agent to finish everything.Anthropic: Building Effective AI Agents
ground truthVerifiable information from the environment that an agent checks against at each step instead of assuming its plan worked.Anthropic: Building Effective AI Agents
revised outputThe draft that comes back after a correction, which goes through the same criteria rather than straight to use.Anthropic: Building Effective AI Agents
first mistake-log entryThe course's closing exercise: delegate a small real task, check it, and record the mistake type, how you spotted it, and the corrected result.Anthropic: Building Effective AI Agents