Choco automates food distribution with AI agents

Choco 利用 AI 智能体实现食品分销自动化

Choco automates food distribution with AI agents

Using OpenAI APIs, Choco processes millions of orders, reducing manual work and enabling always-on operations across global food supply chains.

Choco 利用 OpenAI API 处理数百万份订单，减少了人工工作量，并实现了全球食品供应链的全天候运营。

Rebuilding food distribution for the AI era

为 AI 时代重构食品分销

Choco is an AI-powered platform modernizing food and beverage distribution, serving over 21,000 distributors and 100,000 buyers across the US, UK, Europe, and the GCC. By connecting restaurants, suppliers, and distributors into a unified system, Choco streamlines ordering, sales, and customer management across the food supply chain.

Choco 是一个由 AI 驱动的平台，致力于实现食品和饮料分销的现代化，为美国、英国、欧洲和海湾合作委员会（GCC）地区的 21,000 多家分销商和 100,000 多名买家提供服务。通过将餐厅、供应商和分销商连接到一个统一的系统中，Choco 简化了整个食品供应链的订购、销售和客户管理流程。

As order volumes grew, Choco hit a major bottleneck: orders still arrived through emails, texts, voicemails, images, and even handwritten notes. Teams manually translated those inputs into structured ERP orders—a slow, error-prone process that limited scale and created constant operational friction.

随着订单量的增长，Choco 遇到了一个主要瓶颈：订单仍然通过电子邮件、短信、语音留言、图片甚至手写笔记的形式涌入。团队需要手动将这些输入转化为结构化的 ERP 订单——这是一个缓慢且容易出错的过程，限制了规模化发展，并造成了持续的运营摩擦。

“Processing those inputs was the first barrier, but not the hardest one. The real problem was implicit context: customer-specific SKU mappings, unit preferences, delivery patterns. That knowledge lived in the heads of order desk reps, and we needed to encode it into inference layers that resolve ambiguity at the point of order capture.”—Narbeh Mirzaei, VP Engineering

“处理这些输入只是第一道障碍，但并非最难的。真正的问题在于隐含的背景信息：特定于客户的 SKU 映射、单位偏好、配送模式。这些知识原本存在于订单处理人员的脑海中，我们需要将其编码到推理层中，以便在订单捕获时解决歧义。”——工程副总裁 Narbeh Mirzaei

With the emergence of production-ready LLMs, Choco saw an opportunity to move beyond workflow software and build AI systems capable of executing work directly. OpenAI APIs became central to that transformation.

随着生产级大语言模型（LLM）的出现，Choco 看到了超越工作流软件、构建能够直接执行工作的 AI 系统的机会。OpenAI API 成为了这一转型的核心。

Inside the rollout

部署过程

Choco embedded OpenAI APIs at the core of its platform to power a new generation of AI-native products. The company introduced OrderAgent, which processes multimodal inputs—including emails, SMS, images, and documents—and converts them into structured, ERP-ready orders.

Choco 将 OpenAI API 嵌入其平台核心，以驱动新一代 AI 原生产品。该公司推出了 OrderAgent，它能够处理包括电子邮件、短信、图片和文档在内的多模态输入，并将其转换为结构化、可直接导入 ERP 的订单。

“The transcription and extraction capabilities gave us a strong foundation. The real engineering challenge was building dynamic in-context learning infrastructure, so the system resolves ambiguity against each customer’s ordering history and catalog. That’s what separates automation from intelligence.”—Narbeh Mirzaei, VP Engineering

“转录和提取能力为我们奠定了坚实的基础。真正的工程挑战在于构建动态的上下文学习基础设施，使系统能够根据每个客户的订购历史和目录来解决歧义。这就是自动化与智能的区别所在。”——工程副总裁 Narbeh Mirzaei

Choco has also built VoiceAgent, powered by OpenAI’s Realtime API, enabling customers to place orders naturally over the phone with sub-second latency—even outside business hours.

Choco 还构建了由 OpenAI Realtime API 驱动的 VoiceAgent，使客户能够通过电话以亚秒级的延迟自然地进行下单，即使在非工作时间也能实现。

OpenAI was selected for its model performance, multimodal capabilities, structured outputs, and production reliability at scale. The ability to handle text, vision, and audio within a single ecosystem allowed Choco to unify previously disconnected workflows into one intelligent system.

Choco 选择 OpenAI 是因为其模型性能、多模态能力、结构化输出以及大规模生产的可靠性。在单一生态系统中处理文本、视觉和音频的能力，使 Choco 能够将此前相互割裂的工作流统一为一个智能系统。

Implementation was fast and scalable. Using OpenAI’s SDKs and APIs, Choco rapidly integrated capabilities like speech-to-text, embeddings, and function calling into its infrastructure. The team also built a rigorous evaluation framework with ground-truth datasets, continuous monitoring, and A/B testing to ensure accuracy and performance in production.

实施过程既快速又具备可扩展性。利用 OpenAI 的 SDK 和 API，Choco 迅速将语音转文字、嵌入（embeddings）和函数调用等功能集成到其基础设施中。团队还构建了一个严谨的评估框架，结合真实数据集、持续监控和 A/B 测试，以确保生产环境中的准确性和性能。

Adoption was driven by seamless integration across the entire ordering workflow. Customers didn’t need to change how they ordered—whether by phone, text, or email, the system adapted to them.

系统的普及得益于其在整个订购工作流中的无缝集成。客户无需改变他们的订购方式——无论是通过电话、短信还是电子邮件，系统都能自动适应。

Results at a glance

成果概览

Processes over 8.8 million orders annually, eliminating millions of manual workflows. 每年处理超过 880 万份订单，消除了数百万次人工工作流。
Achieves up to 50% reduction in manual order entry, freeing teams for higher-value work. 手动订单录入减少高达 50%，使团队能够专注于更高价值的工作。
Enables 2x productivity gains, allowing teams to scale without additional headcount. 生产力提升 2 倍，使团队无需增加人手即可实现规模化扩展。
Maintains error rates below 1–5% with configurable automation thresholds. 通过可配置的自动化阈值，将错误率保持在 1–5% 以下。
Supports 24/7 order intake, eliminating delays from nights and weekends. 支持 24/7 全天候订单接收，消除了夜间和周末造成的延迟。

Leadership lessons

领导力经验

Start with evaluation from day one: Even a small ground-truth dataset (10–20 examples) enables teams to measure progress, validate improvements, and iterate with confidence. 从第一天起就开始评估： 即使是一个很小的真实数据集（10-20 个示例），也能让团队衡量进展、验证改进并自信地进行迭代。
Invest in AI-native observability: Debugging AI systems requires more than traditional logs—capturing model inputs, outputs, and reasoning traces is essential to understand and improve performance. 投资于 AI 原生可观测性： 调试 AI 系统需要的不仅仅是传统的日志——捕获模型的输入、输出和推理轨迹对于理解和提升性能至关重要。
Set the right expectations early: Unlike deterministic software, LLMs are probabilistic. Educating teams and users on this difference is key to building trust and avoiding friction during adoption. 尽早设定正确的预期： 与确定性软件不同，大语言模型是概率性的。让团队和用户了解这种差异，是建立信任并避免采用过程中摩擦的关键。

What’s next

未来展望

Choco is continuing to expand its AI capabilities across the food distribution ecosystem, deepening the role of agents in executing complex operational workflows. As AI systems take on more responsibility, the company is enabling a new class of users—non-engineers who act as “agent orchestrators,” designing and managing intelligent systems that drive business outcomes.

Choco 正在继续扩展其在食品分销生态系统中的 AI 能力，深化智能体在执行复杂运营工作流中的作用。随着 AI 系统承担更多责任，该公司正在赋能一类新的用户——非工程师背景的“智能体编排者”，他们负责设计和管理驱动业务成果的智能系统。

Looking ahead, Choco plans to further scale its use of OpenAI APIs to power more autonomous, context-aware systems across sales, commerce, and supply chain operations—continuing its shift from workflow software to AI-powered execution infrastructure.

展望未来，Choco 计划进一步扩大 OpenAI API 的使用规模，为销售、商业和供应链运营提供更具自主性、更具上下文感知能力的系统，继续从工作流软件向 AI 驱动的执行基础设施转型。