Tiger AI Research
Evidence-Governed Harness Engineering

Mechanical Gates over Model Consensus

Evidence-Governed Harness Engineering for Agentic Software Development

Vibe coding creates applications; harness engineering makes them governable.

For regulated teams that need evidence, auditability, and rollback.

Working Paper · v3.4 · DOI 10.5281/zenodo.21390753
Why it matters

AI can build software faster than we can govern it

Code opacity

AI-generated native code is often a black box — unreadable to the business operators and IT reviewers expected to audit and maintain it.

AI-verifier risk

When the AI that verifies shares the producer's context or bias, "all tests green" can verify nothing — a correlated shared-context false pass.

Regulated audit gap

In banking and government, internal audit and control cannot govern what they cannot read — turning AI-built apps into unmanaged shadow IT.

Core contribution

Govern with evidence, not consensus

Mechanical gates over model consensus

At release gates, privilege executable evidence — mutation testing, property-based testing, spec invariants, real execution — over "several models agreed."

Shared-context false pass hypothesis

A named and situated failure mode: the AI verifying the AI can pass tests while the specification is never truly checked. Not solved by adding more models.

Skill capitalization

Each delivered project becomes a reusable, testable, governable Skill with a named-state lifecycle — so quality compounds instead of decaying.

Field observation

Regulated teams govern what they can see

In banking and public-sector settings under internal-audit and internal-control mandates, business units increasingly build their own applications by vibe coding — but the native code is opaque to the very functions expected to review it. Re-expressing the repeatable, judgment-bearing steps as inspectable workflow graphs lets governance attach at the workflow layer, and — the property auditors valued most — a non-engineer auditor can visually follow a transaction directly on the graph.

Preliminary field observation — not a validated comparison
How it works

From opaque code to an audit trail

Vibe-coded code
Fast to create, opaque to review
Skill verification
Efficiency · security · permissions · data-exfiltration, via mechanical gates
Workflow-native governance
Identity · RBAC · secrets · human approval · on-prem
Audit trail
Visually followable · traceable · reversible

Creation stays fast; the repeatable, judgment-bearing steps become controllable and auditable.

Research status

Working Paper

Conceptual framework + preliminary field observation

Controlled studies (EXP-001 / a comparative case study) are planned, not yet reported.

This is not peer-reviewed and contains no validated empirical results yet. Produced with a multi-engine AI workflow assisting drafting, critique, and verification; the named human author set the research questions, reviewed the evidence, and accepts responsibility — AI systems are not authors. A DOI certifies permanent archiving, not peer review.

Citation & author

Cite this work

Lu, Y.-H. (2026). Mechanical Gates over Model Consensus: Evidence-Governed Harness Engineering for Agentic Software Development (v3.4, Working Paper). Zenodo. DOI: 10.5281/zenodo.21390753. ORCID: 0009-0006-5373-0586. License: CC BY 4.0.
ML
Yeh-Hsing (Morris) Lu 盧業興
CEO, Tiger AI Tech Co., Ltd. · n8n Taipei Ambassador