Governance-as-Code: Managing Agentic AI with a Distributed Dual Proxy Gateway
Bibliographic record
Abstract
The rapid adoption of large-language models (LLMs) has shifted enterprise AI from model-centric experimentation to production-scale, policy-constrained deployments. Traditional “LLM-as-a-service” governance breaks down when LLMs are embedded in agentic execution loops that plan, act, observe, and adapt while calling external tools. This paper traces the architectural evolution from embedded wrappers and sidecar proxies to a multi-plane, dual-proxy gateway, in which lightweight edge proxies and heavyweight core proxies cooperate to provide low-latency guardrails, global policy enforcement, and verifiable attestation chains. We introduce a governance-as-code approach that compiles compliance workflows into WebAssembly (Wasm) modules. Edge proxies execute these modules, obtain cryptographic signatures from specialized microservices, and forward only fully attested prompts to the core proxy, which ultimately forwards them to the LLM. Micro-benchmarks show that Wasm-mediated validation adds ≤ 20 ns overhead for CPU-bound tasks and ≈ 120 ns when serializing complex data types negligible relative to LLM inference times. The design achieves auditable, decentralized governance with good performance, laying the groundwork for high-assurance, tool-using agentic AI in the enterprise.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".