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

arXiv: https://arxiv.org/abs/2606.08867 · HTML: https://mlsanity.com/paper/2606.08867/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [Evaluation and Benchmarking of LLM Agents: A Survey](https://mlsanity.com/paper/2507.21504/) (2025)
- [Reinforcement Learning for Long-Horizon Interactive LLM Agents](https://mlsanity.com/paper/2502.01600/) (2025)
- [An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability](https://mlsanity.com/paper/2506.13639/) (2025)
- [A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment](https://mlsanity.com/paper/2504.12408/) (2025)
- [LLM-Friendly Knowledge Representation for Customer Support](https://mlsanity.com/paper/2510.10331/) (2025)
- [Schema-Guided User Satisfaction Modeling for Task-Oriented Dialogues](https://mlsanity.com/paper/2305.16798/) (2023)
- [Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support](https://mlsanity.com/paper/2302.03222/) (2023)
- [NatCS: Eliciting Natural Customer Support Dialogues](https://mlsanity.com/paper/2305.03007/) (2023)
- [Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants](https://mlsanity.com/paper/2301.06544/) (2023)

## Built on by (most cited first, 3 of 3)

- [Don't Offer What Can't Be Done: Deterministic Executability Gating for LLM Skill Selection at Scale](https://mlsanity.com/paper/2608.01050/) (2026)
- [Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale](https://mlsanity.com/paper/2609.30137/) (2026)
- [Designing Reliable LLM-as-a-Judge Measurement Systems for Multi-Turn Business Agents](https://mlsanity.com/paper/2609.33955/) (2026)

## Abstract (arXiv)

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.