Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJun 22, 2026

Nexus-Gov

Cristopher Euan, Manuel Alejandro Ortega Blanco, Luis Enrique Ramos Diaz, Noe Euan Herrera · Team The Monkey's

Submitted to Global South AI Safety Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Nexus-Gov

Open in a new tab (opens in new tab)
Share

Nexus Gov is an AI governance platform that audits prompts, source code, and AI-generated responses to identify security, compliance, and reliability risks. By providing risk scores, compliance metrics, deployment decisions, and audit evidence, Nexus Gov helps organizations improve transparency, accountability, and oversight in AI-enabled systems.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. Read this twice. The three-module approach—Prompt Auditor for injection detection (OWASP LLM01), Code Auditor for vulnerabilities, Response Auditor for overconfidence—is clean and deployable. What struck me is the real incident case (NG-RESP-2026-F2EC52A0) showing this isn't theoretical. I'd push you on the baseline comparison though. You measure against a "baseline workflow without governance controls," but I want to see how you stack against existing prompt injection detectors or code scanners. That eval is doing a lot of work. The governance metrics (0-100 scores with compliance gates) feel practical for orgs. What's next week: document the detection precision/recall on your test set.

  2. 2 / 3 / 3

    Clear and practical tool. It works as a basic governance layer, but the approach is not very new because it mostly uses simple rule-based checks.

  3. Applying established security paradigms like SAST to LLM input and output is a practical approach to operational governance. The separation of the system into Prompt, Code, and Response Auditors successfully generates compliance-oriented reporting without requiring modifications to the underlying language model. While rule-based engines are reliable and cost-efficient, they lack semantic depth and are inherently brittle against adaptive adversaries. The necessary next step for future work is integrating semantic or embedding-based analysis to move beyond keyword and regex pattern matching.

Cite this project

@misc{euan2026nexusgov,
  title = {{Nexus-Gov}},
  author = {Cristopher Euan and Manuel Alejandro Ortega Blanco and Luis Enrique Ramos Diaz and Noe Euan Herrera},
  year = {2026},
  month = jun,
  note = {Submitted to Global South AI Safety Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/nexusgov-hiew}},
  url = {https://apartresearch.com/sprints/projects/nexusgov-hiew}
}

More from Global South AI Safety Hackathon

All 216 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026