Q001 — Self-Audit¶


Research	R0021 — Prompt engineering definitions
Run	2026-03-25
Query	Q001

ROBIS 4-Domain Audit¶

Domain 1: Eligibility Criteria¶

Rating: Low risk

Criterion	Assessment
Criteria defined before searching	Yes — sought formal definitions from named professional bodies
Criteria stable during research	Yes — no shifting of what counts as a "formal definition"
Criteria appropriate to query	Yes — accreditation criteria and professional body publications are the right sources

Notes: The eligibility criteria were well-defined by the query itself (ABET, IEEE, NSPE, and other professional bodies).

Domain 2: Search Comprehensiveness¶

Rating: Some concerns

Criterion	Assessment
Multiple search strategies used	Yes — two separate searches targeting different organizations
Searches designed to test each hypothesis	Partially — searches focused on finding definitions rather than testing H2 (absence of definitions)
All results dispositioned	Yes — 17 results across two searches, all dispositioned
Source diversity achieved	Partially — three US-based bodies. International bodies not searched.

Notes: The search was comprehensive for US professional bodies but did not extend to international organizations (UK ICE, European FEANI, etc.). This is appropriate given the query's focus but limits the generalizability of the finding.

Domain 3: Evaluation Consistency¶

Rating: Low risk

Criterion	Assessment
All sources scored using same framework	Yes
Evidence typed consistently	Yes — all typed as Factual
ACH matrix applied	Yes
Diagnosticity analysis performed	Yes

Notes: Consistent application across all three sources.

Domain 4: Synthesis Fairness¶

Rating: Low risk

Criterion	Assessment
All hypotheses given fair hearing	Yes — H2 tested and eliminated on evidence; H3 acknowledged as partially supported
Contradictory evidence surfaced	No contradictory evidence found; absence noted
Confidence calibrated to evidence	Yes — high confidence justified by primary sources
Gaps acknowledged	Yes — NSPE definition gap and international scope limitation documented

Notes: The high agreement across sources could mask potential differences in international definitions or historical evolution.

Overall Assessment¶

Overall risk of bias: Low risk

The research process was straightforward for this query — the definitions exist in publicly available documents from the organizations named in the query. The primary limitation is the US-centric scope, which is appropriate given the query but should be noted.

Researcher Bias Check¶

Confirmation bias risk: The researcher's article series argues against "prompt engineering" as real engineering. This could bias toward finding clear, restrictive definitions. Mitigated by quoting definitions verbatim rather than paraphrasing.
Selection bias risk: Low — the organizations were named in the query, limiting discretion in source selection.
Anchoring bias risk: The ECPD definition, being the most well-known, could anchor the analysis. Mitigated by independently sourcing ABET's current criteria.