Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework

• URL: http://arxiv.org/abs/2606.08867v2
• Date: Sat, 13 Jun 2026 05:21:25 GMT
• Title: Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework
• Abstract summary: We present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank.<n>A central insight is that evaluation-pipeline quality directly determines iteration velocity.<n>On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.
• Score: 2.29541210878158
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid rise in LLM capabilities has made AI agents increasingly viable across a broad range of tasks. Among the most promising applications is building production-ready customer-facing agents, a challenge that demands coordinated excellence in evaluation methodology, context engineering, training, and online measurement. Yet these critical pillars are typically developed in isolation, creating blind spots that only surface after deployment. In this paper, we present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank, a company with 100M+ users. Our approach integrates several key components: (1) structured context engineering tailored to customer support agents, (2) systematic human-in-the-loop prompt iteration, (3) rigorous LLM judge evaluation with measured inter-rater agreement and GEPA optimization for consistency, and (4) ideation-to-production validation. A central insight is that evaluation-pipeline quality directly determines iteration velocity. We present results from five production deployments spanning distinct domains: card delivery, debt management, credit-limit support, card management, and product explanation. These deployments deliver consistent customer-satisfaction gains while substantially accelerating iteration. In our card-delivery deployment, large-scale A/B testing yields a 37 percentage-point improvement in AI transactional Net Promoter Score and a 29 percentage-point gain in self-service rate over prior agent variants, alongside a strong correlation between offline simulation metrics and online outcomes, demonstrating that eval-driven development reliably predicts production impact. On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.

Related papers

• StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows [63.57092302641323]
  We introduce textbfStartupBench, an E2E agent benchmark grounded in market-validated AI startup products.<n>We study AI products with demonstrated adoption, together with their product and users, to identify real-world tasks for which AI has established practical demand.<n>Our results reveal that many market-validated agents remain beyond the reliable capabilities of current general-purpose agents.
  arXiv  Detail & Related papers  (2026-08-18T14:01:32Z)
• Designing Agent-Ready Websites for AI Web Agents: A Framework for Machine Readability, Actionability, and Decision Reliability [0.0]
  This paper introduces the agent-ready website, a design framework for enhancing the readability, interpretability, verifiability, and actionability of e-commerce platforms for AI agents.<n>The framework is evaluated through a controlled experiment comparing a human-oriented baseline and an agent-ready version of an identical website prototype.
  arXiv  Detail & Related papers  (2026-07-13T18:16:58Z)
• The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? [80.24951682268332]
  We introduce the Meta-Agent Challenge (MAC), an evaluation framework designed to test the capacity of frontier models for autonomous agent development.<n>To ensure evaluation integrity, this framework is secured by multi-layer defenses against reward hacking.<n>We demonstrate that meta-agents rarely match human-engineered baseline policies, and the few that do are dominated by proprietary frontier models.
  arXiv  Detail & Related papers  (2026-06-03T04:58:17Z)
• ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning [88.87305027895657]
  This work investigates Reinforcement Learning-based optimization for shopping agents in real-world scenarios.<n>Agents must simultaneously satisfy multiple interdependent objectives spanning objective metrics (product correctness), subjective qualities (persuasiveness), outcome rewards (final response quality), and process rewards (tool efficiency)<n>Experiments demonstrate that our RL-trained agent, ChatShopBuddy, consistently outperforms larger models relying on generic reasoning.
  arXiv  Detail & Related papers  (2026-03-06T09:18:51Z)
• LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering [90.84806758077536]
  We introduce textbfLoCoBench-Agent, a comprehensive evaluation framework specifically designed to assess large language models (LLMs) agents in realistic, long-context software engineering.<n>Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations.<n>Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens.
  arXiv  Detail & Related papers  (2025-11-17T23:57:24Z)
• Continuous Benchmark Generation for Evaluating Enterprise-scale LLM Agents [23.277131100190086]
  We propose a process of benchmark generation that helps evolve the benchmarks as the requirements change and perform robust evaluation of evolving AI agents.<n>Our approach relies on semi-structured documents where developers express the high-level intent, and uses state-of-the-art LLMs to generate benchmarks from just a small number of such documents.
  arXiv  Detail & Related papers  (2025-11-13T07:48:22Z)
• AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress [71.02263260394261]
  Large language models (LLMs) still encounter challenges in multi-turn decision-making tasks.<n>We build process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process.<n>AgentPRM captures both the interdependence between sequential decisions and their contribution to the final goal.
  arXiv  Detail & Related papers  (2025-11-11T14:57:54Z)
• Towards Outcome-Oriented, Task-Agnostic Evaluation of AI Agents [1.0305173936249623]
  This white paper proposes a novel framework of eleven outcome-based, task-agnostic performance metrics for AI agents.<n>We introduce metrics such as Goal Completion Rate (GCR), Autonomy Index (AIx), Multi-Step Task Resilience (MTR), and Business Impact Efficiency (BIE)<n>Our results reveal significant performance trade-offs between different agent designs, highlighting the Hybrid Agent as the most consistently high-performing model.
  arXiv  Detail & Related papers  (2025-11-11T13:40:46Z)
• How can we assess human-agent interactions? Case studies in software agent design [52.953425368394306]
  We make two major steps towards the rigorous assessment of human-agent interactions.<n>We propose PULSE, a framework for more efficient human-centric evaluation of agent designs.<n>We deploy the framework on a large-scale web platform built around the open-source software agent OpenHands.
  arXiv  Detail & Related papers  (2025-10-10T19:04:28Z)
• The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective [3.0868637098088403]
  Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning.<n>This paper presents the first comprehensive system-level analysis of AI agents, quantifying their resource usage, latency behavior, energy consumption, and test-time scaling strategies.<n>Our findings reveal that while agents improve accuracy with increased compute, they suffer from rapidly diminishing returns, widening latency variance, and unsustainable infrastructure costs.
  arXiv  Detail & Related papers  (2025-06-04T14:37:54Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.