LesenForschungRadarAnlageframework
Anmelden / Registrieren
← Zurück zur Lektüre
NewsThema · ElevenLabsWesentlich2 Min. LesezeitDisconfirmAI Redaktion

Jake Tennant of ElevenLabs on Product and Growth Directions: Removing Fields Improves Retrieval Agent Accuracy More Than Prompt Tuning

ElevenLabs' internal operations team shared engineering experiences using the ElevenAgents agent. The core finding is that for retrieval agents, reducing redundant fields in the data schema yields greater accuracy improvements than any prompt tuning they have attempted. The author also introduces two specific practices: Salesforce picklist type injection and task verification.

2026-10-29 20:00 GMT+8

Jake Tennant, who works on product and growth at ElevenLabs, introduced the company's operational experience with its internal ElevenAgents in a blog post. These agents cover sales, support, engineering, and product marketing teams; the company reports saving over 1,200 hours monthly and answering more than 5,000 questions while creating over 150 tickets.

However, what truly warrants attention from peers is not these numbers, but the engineering judgment provided by the author in the 'What We Learned' section. Tennant wrote that the greatest improvement in answer quality for their retrieval agents came from removing fields rather than adjusting system prompts. Every extra column or object field gave the model another opportunity to guess incorrectly; trimming the data schema down to a critical subset improved accuracy more than any prompt changes they had tried.

This finding creates tension with current mainstream prompt engineering approaches. Many teams default to fine-tuning at the prompt level, but Tennant's experience suggests that when agents rely on external data retrieval, the data structure fed into the model itself becomes a larger quality bottleneck. Fewer fields mean less room for the model to guess.

The author provides a specific implementation example: fields such as deal stage or account type in Salesforce are picklists, meaning a fixed set of valid values. If left to generate freely, the model might create a plausible-sounding option that does not exist in Salesforce. ElevenLabs' approach is to fetch the list of valid values at startup and inject them into the MCP tool's type definitions, ensuring the model can only choose from real options.

Anmelden / Registrieren
LesenForschungRadarAnlageframework

Additionally, they added a task verification step after ticket creation: after the agent creates a Linear ticket, it checks whether the fields are correct and if the ticket was assigned to the right team. Tennant stated this has reduced occasional hallucinations and misassignments.

It should be noted that this is an account from ElevenLabs regarding its own products. The 1,200 hours saved lacks a methodological explanation, and the engineering experience may be tied to their specific tech stack and internal data scale. However, these specific practices—prioritizing field removal over prompt tuning, using type constraints instead of free generation, and verifying after creation—are directly testable for other teams within their own environments.

Quellen

  • elevenlabs.ioElevenLabs↗
Thema

ElevenLabs

ElevenLabs 内部运营团队披露,其基于 ElevenAgents 构建的智能体每月为公司节省超过 1,200 小时。核心工程发现是:对于检索型智能体,精简数据模式中的冗余字段比调优提示词更能提升准确率。这一结论挑战了当前主流依赖提示…

2 Schritte1 BeiträgeAktualisiert 2026-10-31 09:33

Wie es dazu kam

  1. 2026-10-29ElevenLabs 产品与增长负责人 Jake Tennant 发布博客,介绍内部使用 ElevenAgents 的经验,指出删减数据模式字段带来的准确率提升超过了任何提示词调优尝试。elevenlabs.io ↗
  2. 2026-10-29文章披露具体实施细节:在 Salesforce 集成中,通过启动时获取有效值并注入 MCP 工具类型定义,防止模型生成不存在的选项;同时引入任务验证机制以纠正工单分配错误。disconfirmai.com ↗

Was noch ungeklärt ist

  • 该“模式优于提示”的结论是否适用于非结构化知识检索场景?
  • ElevenLabs 未公开具体的准确率提升百分比数值,仅定性描述为“最大增益”。
Vollständiges Thema lesen →
Recherche fortsetzen →