Prober.ai¶
Product or Programme · All products and programmes
Evidence · 4 claims (4 for) · 2 studies (2 design),q2· 0 of 2 report an effect size · 4 claims rest on one study
Description¶
Prober.ai is a research-logging software platform that records consented participant sessions, events, drafts, challenges, unlocks, and reflection-coaching interactions for studying learning behavior.
Components¶
- Prober.ai research-logging pipeline: Prober.ai ships with a research-logging pipeline that "captures the full interaction without altering the student experience." An optional Study Setup mode records participant, session, condition, and prompt identifiers with a consent flag, and dedicated endpoints append newline-delimited JSON to six logs (sessions, events, drafts, challenges, unlocks, reflection-coaching). Fine-grained timestamped events let a researcher reconstruct each student's revision trajectory and the {question, defense, score, revision} tuples the reflection gate produces; each model call carries a hashed, privacy-preserving safety_identifier. (Ran Bi et al. (2026))
Claims¶
- Explicit API interception from a pilot cohort of 19 students yielded 1,880 events over about 57 active student-hours [+W]
- Macro-level behavioral metrics flagged anomalies consistent with automated workflows and off-platform AI code synthesis [+W]
- The deterministic reflection gate reliably distinguished low-effort defenses from substantive ones during validation, coaching filler answers rather than unlocking [+W]
- Schema-constrained Structured Outputs eliminated parse failures: every /challenge and /unlock call returned a valid, fully-typed object during development testing [+W]
Related Products and Programmes¶
-
Key Sources¶
- Ran Bi, Shiyao Wei, Yuanyiyi Zhou. (2026). Prober.ai: Gated Inquiry-Based Feedback via LLM-Constrained Personas for Argumentative Writing Development. https://arxiv.org/abs/2605.05598
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
proberai |
title |
Prober.ai |
description |
Prober.ai is a research-logging software platform that records consented participant sessions, events, drafts, challenges, unlocks, and reflection-coaching interactions for studying learning behavior. |
status |
review |
product_kind |
software |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.