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.
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.