Enterprise AI agents in production often need to be bounded, stateful, observable, and governable rather than fully autonomous. We present PinSieve, a production case study in a large-scale content-quality pipeline. Its deployed component is a selective vision-language-model (VLM) Serving Agent that operates only on the grey-zone slice left unresolved by lightweight upstream models, exposes a scalar routing score online, and preserves controlled human escalation. On this slice, the deployed system filters 2.05x more non-actionable items than the previous production module while slightly reducing estimated miss rate; after promotion, it improves review productivity by 25.7%, reduces normalized operating cost by 16.2%, and moves signal delivery from next-day to same-day. We then study maintenance through a governed memory flywheel under selective feedback, where escalated items are reviewed by default and auto-passed items are labeled mainly through audit sampling. Feedback Memory records routing traces, observation paths, audit propensities, and replay metadata for evaluation and debugging. The Data Curation Agent uses a bounded proposal-verifier loop over representative, uncertainty, recency, and fresh-review replay, with positive-rate and score-bin guardrails before batch acceptance. In chained monthly refresh over six months of production data, this design reduces average FNR@50% from 17.73% under representative random replay to 13.29%. A Reasoning Review Agent audits teacher-generated rationales and supports keep/repair/drop decisions. Production claims are attributed only to the deployed Serving Agent; replay and rationale-review results are offline or sampled-governance evidence. The same serving-agent recipe has been adopted to several additional internal signals, suggesting transferability beyond one task.
Selective prediction lets models answer only when sufficiently reliable, trading coverage for lower error through abstention, referral, or extra evidence gathering.
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallible LLM judges. We report on AGO AI Quality Gate (AGO), an evidence-first quality-gate framework deployed in industrial RAG assessment engagements. AGO integrates four key components: a four-state decision model that treats missing data and judge errors as explicit outcomes; layered scoring combining deterministic checks, local guardrails, and structured LLM evaluation; a stratified beta-binomial gate that quantifies regression risk probabilistically; and a mandatory meta-evaluation protocol to validate the LLM judge before it influences decisions. Since engagement data is proprietary, we evaluate the judge layer on RAGBench, a public benchmark of 100k annotated RAG traces across 12 datasets. On identical stratified test samples (N=1200 per judge), a low-cost judge (gpt-4.1-nano) detects non-adherent answers barely above chance (AUROC 0.603 [0.570, 0.634]), despite producing flawless protocol output, while gpt-4o reaches 0.783 [0.756, 0.807] -- yet its per-domain performance still ranges from 0.62 to 0.88. A fixed-seed gate study spanning regression, no change, and improvement quantifies unsafe promotion, false-alarm cost, and improvement throughput. Under regression, the decision-grade profile reduces unsafe promotion to 22.2%-35.1%, against 29.3%-41.8% for a naive gate. These results support the design choices that judge quality must be measured per engagement and that point estimates alone are not a release decision.
Giulio Zeloni, Enrico Lo Conte, Salvatore Rionero +3
Designing service systems requires selecting among alternative configurations -- choosing the best chatbot variant, the optimal routing policy, or the most effective quality control procedure. In many service systems, the primary evidence of performance quality is textual -- customer support transcripts, complaint narratives, compliance review reports -- rather than the scalar measurements assumed by classical optimization methods. Large language models (LLMs) can read such textual evidence and produce standardized quality scores, but these automated judges exhibit systematic biases that vary across alternatives and evaluation instances. Human expert review remains accurate but costly. We study how to identify the best service configuration with high confidence while minimizing expensive human audits, given that automated evaluation is cheap but biased. We formalize this as a sequential decision problem where a biased proxy score is observed for every evaluation, and a verified outcome can be acquired selectively at additional cost. We prove that LLM-only selection fails under arm-dependent bias, and that naive selective-audit estimators can be asymptotically biased. We develop an estimator combining proxy scores with inverse-propensity-weighted residuals and construct anytime-valid confidence sequences. Our algorithm, PP-LUCB, jointly decides which alternatives to evaluate and whether to request human audits, concentrating reviews where the LLM judge is least reliable. We prove correctness and establish instance-dependent cost bounds showing near-optimal efficiency. On a customer support ticket classification task, our algorithm correctly identifies the best model in 40/40 trials while achieving 90% audit cost reduction.
Ruicheng Ao, Hongyu Chen, Siyang Gao +2
Institute for Data, Systems, and Society, Massachusetts Institute of Technology. · School of Data Science, City University of Hong Kong. · Department of Decision Analytics and Operations, City University of Hong Kong.
Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that are usually addressed through prompt-tuning or retraining, and fundamentally cannot course-correct the agent in real time. To close this gap, we move evaluation into the execution loop at inference time: a specialized reviewer agent evaluates provisional tool calls prior to execution, shifting the paradigm from post-hoc recovery to proactive evaluation and error mitigation. In practice, this architecture establishes a clear separation of concerns between the primary execution agent and a secondary review agent. As with any multi-agent system, the reviewer can introduce new errors while correcting others, yet no prior work to our knowledge has systematically measured this tradeoff. To quantify this tradeoff, we introduce Helpfulness-Harmfulness metrics: helpfulness measures the percentage of base agent errors that feedback corrects; harmfulness measures the percentage of correct responses that feedback degrades. These metrics directly inform reviewer design by revealing whether a given model or prompt provides net positive value. We evaluate our approach on BFCL (single-turn) and Tau2-Bench (multi-turn stateful scenarios), achieving +5.5% on irrelevance detection and +7.1% on multi-turn tasks. Our metrics reveal that reviewer model choice is critical: the reasoning model o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o. Automated prompt optimization via GEPA provides an additional +1.5-2.8%. Together, these results demonstrate a core advantage of separating execution and review: the reviewer can be systematically improved through model selection and prompt optimization, without retraining the base agent.