People are really enjoying our full workshops showing end to end walkthroughs of real production wor...
TL;DR · AI 摘要
这是一条宣传性推文，预告AI Engineer与Braintrust联合举办的实操工作坊，聚焦Trainline生产级AI工程实践，但未提供具体技术细节或深度分析。
核心要点
- 工作坊展示真实生产中LLM调用分阶段拆解（如分流、策略审查、回复生成）
- 强调端到端追踪延迟、Token消耗与成本监控，以及黄金测试集识别故障模式
- 提出Prompt与评分函数版本化、非技术人员可配置参数等工程化落地方法
结构提纲
按章节快速跳转。
- §活动预告
介绍AI Engineer与Braintrust联合举办的工作坊及其核心亮点。
简述The Trainline作为欧洲头部铁路App的业务规模与AI工程需求。
列出工作坊涵盖的关键AI工程方法：分阶段LLM调用、可观测性追踪、黄金测试集等。
说明如何支持非技术人员参与模型参数调整及Prompt版本控制。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- AI工程工作坊：Trainline实战
- 架构演进
- 单体LLM调用 → 多阶段专业化流水线
- 本地开发 → 可版本化管理环境
- 可观测性
- 端到端延迟/Token/成本追踪
- 黄金测试集驱动故障识别
- 协作机制
- 非技术人员更新模型参数
- 持续回归检测与定向修复
金句 / Highlights
值得收藏与分享的关键句。
break down monolithic LLM calls into specialized stages (e.g., triage, policy review, and reply generation)
how to monitor latency, token usage, and costs effectively with end-to-end tracing of agentic flows
using 'golden sets' (a curated set of test inputs) to identify failure modes
how to move from local development to a managed environment where prompts and scoring functions are version-controlled
This is a rare double header with @braintrust's Giran Moodley and @OussamaHaff walking though the real life AI engineering behind @thetrainline, Europe's #1 most https://t.co/E7bynd8Bap" / X
AI Engineer on X: "People are really enjoying our full workshops showing end to end walkthroughs of real production workflows! This is a rare double header with @braintrust's Giran Moodley and @OussamaHaff walking though the real life AI engineering behind @thetrainline, Europe's #1 most https://t.co/E7bynd8Bap" / X
Don’t miss what’s happening
People are really enjoying our full workshops showing end to end walkthroughs of real production workflows! This is a rare double header with
's Giran Moodley and
walking though the real life AI engineering behind
, Europe's #1 most downloaded rail app with 27m MAU and £5.3B in ticket sales! the workshop bundles several important lessons: - break down monolithic LLM calls into specialized stages (e.g., triage, policy review, and reply generation) - how to monitor latency, token usage, and costs effectively with end-to-end tracing of agentic flows - using "golden sets" (a curated set of test inputs) to identify failure modes - how to move from local development to a managed environment where prompts and scoring functions are version-controlled - how to allow non-technical team members to collaborate and update model parameters without code changes - how to identify production regressions, replay failures, and apply targeted fixes to improve system reliability continuously enjoy!
Quote
Braintrust
@braintrust
·
15h
Replying to @braintrust
Watch here → https://braintrustdata.link/AI-engineer-se ssion…
·
2
5
50
22