Files

aszerW f571b20598 feat(skills): add deep-research skill

Copy deep-research skill from local Qoder installation to config repo for version control

2026-06-06 13:22:55 +08:00

6.9 KiB

Raw Permalink Blame History

Example: Exploratory Research — Full Pipeline

User Request

Research the impact of AI on higher education quality assurance

Phase 1: SCOPING

research_question_agent Output

Topic Area: Artificial intelligence applications in higher education quality assurance

Primary Research Question:

How are artificial intelligence technologies being integrated into higher education quality assurance processes, and what are the emerging benefits, risks, and institutional implications?

FINER Assessment:

Criterion	Score	Justification
Feasible	4/5	Growing literature base; accessible through academic databases
Interesting	5/5	Rapidly evolving area at intersection of two major sectors
Novel	4/5	Few comprehensive reviews exist; most studies are case-specific
Ethical	4/5	Raises important AI ethics questions but not inherently harmful
Relevant	5/5	Directly informs QA agency strategy and policy
Average	4.4/5

Scope Boundaries:

In scope: AI/ML applications in institutional/program accreditation, learning analytics for QA, automated assessment, AI in self-evaluation
Out of scope: AI in teaching/learning (unless directly connected to QA), AI plagiarism detection (separate literature), specific vendor products
Key assumptions: Focus on post-secondary education; "quality assurance" includes both internal QA and external accreditation

Sub-questions:

What AI technologies are currently being applied or piloted in HE quality assurance?
What benefits and risks do stakeholders report from AI integration in QA?
What institutional and policy implications arise from AI-augmented QA processes?

research_architect_agent Output

Research Paradigm: Pragmatist (mixed evidence types, applied orientation) Method: Systematic literature review with thematic synthesis Data Strategy: Secondary data (academic literature + grey literature from QA agencies) Analytical Framework: Thematic analysis organized by sub-questions Validity Criteria: Comprehensive search, transparent inclusion criteria, PRISMA reporting

devils_advocate_agent — CHECKPOINT 1

Verdict: PASS (with minor notes)

Minor: RQ is broad — consider whether "emerging" limits to recent literature only
Minor: Define "quality assurance" explicitly (internal vs. external, process vs. outcome)
Observation: Fast-moving field means any review may be quickly outdated

Phase 2: INVESTIGATION

bibliography_agent Output

Search Strategy: 4 databases (Scopus, Web of Science, ERIC, Google Scholar), keywords: "artificial intelligence" AND "quality assurance" AND "higher education", date range: 2019-2025, English and Chinese languages.

PRISMA Flow: 847 identified -> 612 after dedup -> 89 screened -> 31 full-text -> 22 included

Annotated Bibliography (excerpt):

Zawacki-Richter, O., et al. (2019). Systematic review of research on artificial intelligence applications in higher education. International Journal of Educational Technology in Higher Education, 16(1), 39. https://doi.org/10.1186/s41239-019-0171-0
- Relevance: Foundational mapping of AI in HE
- Key Findings: AI predominantly used in profiling/prediction, assessment, adaptive learning
- Quality: Level V (systematic review of descriptive studies)
Sanchez-Prieto, J.C., et al. (2024). AI-enhanced quality assurance: A framework for European higher education. Quality in Higher Education, 30(1), 45-62.
- Relevance: Directly addresses AI+QA intersection
- Key Findings: Proposed framework with 4 dimensions; stakeholder acceptance varies
- Quality: Level VI (framework paper with case illustrations)

[... 20 more sources ...]

source_verification_agent Output

Sources Reviewed: 22 | Verified: 20 | Flagged: 2 | Rejected: 0

Flagged:

Source #14 — Moderate COI (author is CTO of an AI-QA startup)
Source #19 — Currency concern (2019 review may not reflect post-GPT developments)

Phase 3: ANALYSIS

synthesis_agent Output

Key Themes:

AI Application Typology (Strong evidence, 15 sources): Categorization, analytics, automation, prediction
Benefits: Efficiency & Scale (Moderate evidence, 9 sources): Reduced reviewer burden, faster turnaround, larger data processing
Risks: Bias & Transparency (Moderate evidence, 8 sources): Algorithmic bias, black-box decisions, accountability gaps
Institutional Readiness (Emerging evidence, 5 sources): Capacity building, infrastructure, cultural resistance
Policy Frameworks (Emerging evidence, 4 sources): Regulation, standards, governance models

Key Contradiction: Sources disagree on whether AI reduces or amplifies bias in QA — resolution depends on implementation design and oversight mechanisms.

Knowledge Gaps: Limited evidence from Global South; few longitudinal studies; no studies on student perception of AI in QA.

devils_advocate_agent — CHECKPOINT 2

Verdict: PASS

Minor: Technology-positive framing detected — ensure risks are given equal weight
Observation: Most evidence comes from European/North American contexts

Phase 4: COMPOSITION

report_compiler_agent Output

[Full APA 7.0 report, ~5,200 words]

Title: Artificial Intelligence in Higher Education Quality Assurance: A Systematic Review of Applications, Benefits, Risks, and Institutional Implications

[Abstract, Introduction, Literature Review, Methodology, Findings (organized by 5 themes), Discussion, Limitations, Conclusion, References (22 sources)]

Phase 5: REVIEW

editor_in_chief_agent Output

Verdict: Minor Revision (Score: 3.7/5.0)

Strength: Comprehensive search, well-organized themes
Major: Discussion section needs stronger connection between findings and existing QA theory
Minor: Some inconsistency in citation format (3 references)
Minor: Abstract exceeds 250-word limit

ethics_review_agent Output

Verdict: CLEARED

AI disclosure present and accurate
All references spot-checked (5/22 = 23%) — all verified
Dual-use risk: Low
Fair representation: Adequate (noted geographic limitation)

devils_advocate_agent — CHECKPOINT 3