LectureRechercheRadar
Cadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésSujet · EpsilonPrise rapide2 min de lectureRédaction DisconfirmAI

Epsilon (Publicis Groupe Data Technology Company) Platform Team: AI Test Trajectory Replay Skips Redundant Model Inference

The Agentic Platform team at Epsilon delivers AI-driven UI testing as a multi-tenant platform capability to various product teams. Its core cost mechanism is trajectory replay: during the exploration phase, Nova Act calls large language models to infer steps, and once successful, the trajectory is saved; during the execution phase, the saved trajectory is deterministically replayed, skipping redundant model reasoning, thereby reducing latency and cost for repeated runs to fixed lookups. The team reports a 100% pass rate for trajectory replay based on internal benchmarks, but this figure only describes the deterministic re-execution of verified trajectories and does not prove Nova Act's adaptability to interface changes.

2026-10-30 02:20 GMT+8

When UI testing is delivered as a managed platform capability to multiple product teams, each team performs high-frequency repeated executions of the same set of test workflows. If every execution relies on large language models for step-by-step reasoning, latency and costs grow linearly with execution frequency, making the economic viability of platform delivery difficult to sustain. The Agentic Platform team at Epsilon (50 engineers, part of Epsilon, a data and marketing technology company under Publicis Groupe) described their solution in an AWS blog post, built on Amazon Nova Act and the Amazon Bedrock AgentCore Browser Tool, where the trajectory replay mechanism is the key design that makes this model economically feasible.

Trajectory replay divides the testing lifecycle into two states. In the draft state, Nova Act calls large language models to reason through each natural language step, determining how to perform actions in the browser; after typically four to five rounds of prompt iteration, a successful trajectory is saved. In the active state, the system no longer calls large language models to reason, but instead replays the saved trajectory directly as a deterministic sequence of operations. Epsilon reports that saved trajectories achieve a 100% pass rate during repeated executions—this is its internal benchmark data, published in an AWS customer case study blog post, and has not been independently reproduced.

The applicability conditions of this mechanism need to be clarified. The 100% pass rate describes the deterministic re-execution of stable workflows that have already been successfully explored, rather than Nova Act's ability to handle new scenarios or interface changes. If the target page undergoes structural changes, the saved trajectory may no longer match, requiring a return to the draft state for exploration. Therefore, trajectory replay reduces the cost of regression-style repeated executions, not the cost of adaptive testing. For products with frequently changing interfaces, the model inference overhead during the exploration phase will still occur periodically.

Trajectory replay becomes a necessary component of the platform architecture due to Epsilon's multi-tenant delivery model. Product teams consume UI testing capabilities through a unified API interface, with each team running tests under scope-limited IAM roles within their respective AWS accounts, while the platform team does not own the browser infrastructure. In this model, if every execution triggers a complete model inference loop, the platform-side inference costs will accumulate with the number of teams and execution frequency. Trajectory replay reduces the cost of repeated executions from model inference to trajectory lookup and deterministic operations, enabling economic feasibility for the multi-tenant platform at scale.

Sources

  • aws.amazon.comAmazon Web Services↗
Sujet

Epsilon

【背景】Epsilon是法国阳狮集团(Publicis Groupe)旗下的全球数据与技术公司,拥有数亿消费者档案。其Agentic Platform团队近期部署了基于Amazon Nova Act的多租户UI测试服务,旨在通过“意图驱动”…

2 étapes1 piècesMis à jour 2026-10-31 14:32

Comment on en est arrivé là

  1. 2026-10-29AWS机器学习博客发布案例研究,介绍Epsilon如何利用Amazon Nova Act和Bedrock AgentCore Browser Tool构建多租户UI测试平台,强调自然语言步骤和托管浏览器会话的优势。aws.amazon.com ↗
  2. 2026-10-29Dataphoenix报道指出,尽管Epsilon声称轨迹回放达到100%通过率,但案例研究未披露基准测试的样本大小、重放次数或失败分布,且未说明对界面变更的适应性。dataphoenix.info ↗

Ce qui reste non résolu

  • Epsilon的“轨迹回放”机制在UI发生实质性结构变更时,能否自动适应或需要重新探索?
  • 多租户架构下,各产品团队的跨账户IAM角色权限隔离是否经过独立安全审计?
  • 100%的轨迹重放通过率是否掩盖了初始探索阶段的高失败率或高成本?
Lire le sujet complet →
Continuer la recherche →
Connexion / Inscription
LectureRechercheRadarCadre d'investissement