Socratic Questioning Agent

also known as Dialog-Driven Agent, Socratic/対話駆動エージェント, SocraticAI

Drive the agent toward its goal by asking the user a sequence of strategic, open-ended questions that surface the user's own latent knowledge, goal, or context — rather than producing an answer directly.

Context

The agent operates in a domain where the user holds the ground truth or has to discover it for themselves: tutoring, requirements elicitation, coaching, self-knowledge, code review walkthroughs, therapy-adjacent tools. A direct answer would either be wrong (the agent does not know the user's situation) or actively unhelpful (the user needs to construct the understanding themselves).

Problem

Default agent shape — receive prompt, return answer — fits poorly when the answer must come from the user's own context or learning process. Princeton NLP's SocraticAI demonstration and Anthropic-style tutoring evaluations both find that a question-first agent produces materially better outcomes than a fact-first agent on these workloads. But the shape is not just 'ask a question' (that is disambiguation) and not 'ask yourself' (that is self-ask): it is a deliberately staged sequence of probing questions, calibrated to the user's responses, that ends in the user articulating the answer.

Forces

Direct answers are faster but wrong-shaped when the goal is user learning or user-context surfacing.
A bad question is worse than a bad answer — it can mislead or frustrate; the question sequence is itself a design surface.
Users sometimes want answers, not questions; the agent must read when to switch modes.
Question-driven dialogs are longer and more expensive in tokens than direct answers; the cost only pays off in workloads where understanding is the actual goal.

Example

A self-knowledge assistant takes the user through a weekly reflection. Instead of summarizing the user's notes, it opens with 'Which moment this week did you feel most yourself?' Based on the user's answer it picks the next question: 'What was different about that moment from how you usually spend that time?' The agent maintains an internal store of open tensions ('user said X about work but Y about energy') and selects questions targeting the largest tension. After 4–6 turns the user articulates a pattern the assistant could not have produced cold. The session ends with the user, not the agent, writing the conclusion.

Diagram

flowchart TD U[User turn] --> A[Agent reads response] A --> S[Update open-questions store / tension map] S --> Q{User articulated answer?} Q -- not yet --> Sel[Select next strategic question] Sel --> Ask[Ask user] Ask --> U Q -- yes --> Synth[Synthesize / hand back to user] Q -- user wants direct answer --> Direct[Switch to direct-answer mode]

Solution

Therefore:

Structure the agent loop around question selection: at each turn, choose a question that (a) targets the largest remaining uncertainty about the user's goal/context, (b) is answerable by the user with what they already know or can introspect, (c) advances toward a user-articulated conclusion. Maintain an explicit 'open questions' store. Switch modes to direct-answer when the user signals they want one or when the user has articulated enough that synthesis is now low-risk. Pair with frozen-rubric reflection so the agent does not slide into rote question templates.

What this pattern forbids. Forbids the agent from producing direct answers when the goal is user understanding or context-surfacing. Restricts the LLM's freedom to assert, requiring it to interrogate instead.

The smaller patterns that complete this one —

usesOpen-Question Tension Store★— Persist the agent's unresolved questions as a typed ledger so they drive its next inquiry instead of dissolving when the prompt ends.

And the patterns that stand alongside it, or against it —

complementsDisambiguation★★— Have the agent ask a clarifying question before acting on an ambiguous request.
complementsSelf-Ask★★— Have the model emit explicit follow-up sub-questions, answer them (optionally via search), then compose the final answer.
complementsFrozen Rubric Reflection★— Constrain reflection to a fixed, hand-authored rubric of criteria so the reviewer cannot invent new ones each run.
complementsHuman-in-the-Loop★★— Require explicit human approval at defined points before the agent performs an action.
alternative-toPassive Goal Creator★— Analyse the user's articulated prompts and accompanying context to derive a precise, actionable goal before any planning or tool use begins.