发布 HN:Bloomy(YC S26)– 面向 K-12 的 AI 驱动的掌握学习平台

17作者: alexsouthmayd1 天前原帖
嗨,HN,我是Alex Southmayd,Bloomy的创始人(<a href="https://bloomylearning.com">https://bloomylearning.com</a>)——一个为K-12学生提供AI驱动的掌握学习平台。Bloomy为学生提供AI辅导和适应性课程(目前包括数学、英语语言艺术和写作)。 <p>它是如何运作的:我们诊断学生的技能差距,为他们制定个性化学习路径,并提供符合标准的课程和一个苏格拉底式的AI辅导,帮助他们学习,而不是直接给出答案。 <p>我们的目标是用AI解决Bloom的2-σ问题(<a href="https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem" rel="nofollow">https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem</a>)。 <p>简短的启动视频:<a href="https://tinyurl.com/bloomylearning" rel="nofollow">https://tinyurl.com/bloomylearning</a> <p>更长的产品演示:<a href="https://youtu.be/XHvoKt6qMeo" rel="nofollow">https://youtu.be/XHvoKt6qMeo</a> <p>家庭访问Bloomy:<a href="https://bloomylearning.com/families">https://bloomylearning.com/families</a> <p>我最初是一名教师。我在Teach For America教授七年级的英语和写作,每天都在努力为30名有着不同需求的学生提供差异化教学。有些学生需要补救,有些需要加速,还有许多学生需要一个辅导员在旁边帮助他们理清下一步的思路。 本杰明·布鲁姆的2-σ结果——一对一辅导可以产生比传统课堂教学更好的结果——对我来说总是直观上是正确的。困难在于如何让这种关注变得负担得起,并让每个孩子都能享受到。 <p>然后,AI改变了成本曲线。当我看到像Alpha这样的学校围绕掌握而不是上课时间来组织学术时,这个模型让我恍然大悟。如果你听说过Alpha学校,那就是我们受到启发的学习模型。但我一直在思考已经存在的家庭和学校:家庭教育、微型学校、混合学校,以及大多数孩子今天所在的普通教室。 <p>大多数学生和教师在错误的分辨率上看到学习差距。他们得到一个成绩、百分位、基准分数或广泛的标准——而不是“这个学生应该学习的下一个技能”。现有的个性化学习产品往往感觉像数字工作表:它们提供大量练习,但缺乏诊断或教学。很少有产品配备AI辅导提供核心教学。 <p>Bloomy从诊断开始——我们与第三方评估集成并提供自己的评估——为每个学生创建学习路径。学生一次专注于一个技能,接受简短的课程,在适应性难度下进行练习,并在展示至少90%的掌握后才能继续前进。学习路径会根据学生的表现和我们与Learning Commons / Chan Zuckerberg Initiative合作构建的技能前提知识图谱进行更新。 <p>每个技能有三个阶段。基础营教授概念和示例。攀登阶段提供指导练习和苏格拉底式支持。顶峰阶段是一个独立的十题掌握评估,没有提示或AI协助。学生需要在顶峰阶段达到90%的分数才能晋级。如果他们遇到太多困难,将被引导到更适合他们水平的其他技能。 <p>BloomyBot不是一个空白的聊天窗口,而是一个实时、互动和观察的数字辅导员。在练习过程中,它接收活动段落或问题、问题、学生的尝试、作者的解释和相关的误解背景。它遵循一个逐步辅导的阶梯:首先询问学生尝试了什么,然后指向概念,建议策略,一起解决一个步骤,只有在学生遇到困难后才提供更重的支撑,适应并从学生身上学习。学生可以打断它,我们已经开始推出西班牙语、法语和一些其他小众语言的多语言支持。 <p>我们目前使用各种Anthropic和OpenAI模型为BloomyBot提供服务。辅导员仅限于当前课程,重定向不相关的问题,限制对话长度,并在掌握评估期间不可用。语言模型不选择课程或决定学生是否掌握某项技能。 <p>这种分离很重要。常规的“有帮助”的AI回应可能是一个糟糕的辅导回应:如果它直接给出答案,学生完成了任务但可能没有学到任何东西。我们的目标不是建立一个回答家庭作业的聊天机器人,而是将AI放入一个结构化的诊断、教学、练习、反馈和独立掌握的循环中。 <p>大型语言模型仍然可能出错,我们并不声称我们的限制消除了这一点。我们通过将BloomyBot基于已编写的课程内容、保持主题一致、记录对话以及将其从评估中移除来减少表面风险。教师和家长可以查看辅导活动,学生可以报告问题,安全信号会触发人工警报和备份审计。 <p>我们也不认为Bloomy可以替代教师、家长或人类辅导员。优秀的人类辅导员更好。我们正在测试的更狭窄的问题是,在一个有限的学习会话中,学生已经在进行的情况下,一个具有上下文意识的辅导员是否能够提供比静态的“正确/错误”反馈更好的帮助。从长远来看,问题变成了学生在某些课程方面是否能在一对一的AI辅导下表现得更好,而不是在中等或大型课堂中接受多人授课。 <p>Bloomy目前在多个环境中使用:传统学区、特许学校、混合学校、微型学校、家庭教育以及寻求额外学术支持的家庭。在马萨诸塞州的一所特许学校的早期试点中,服务于约150名6到8年级的学生,学生的平均冬季到春季NWEA MAP增长约为预期的1.8倍。这是一个观察性试点,而不是随机研究,因此我们将其视为一个鼓舞人心的信号,而不是Bloomy造成差异的证明。 <p>家长和教师可以看到学生掌握了什么,正在进行什么,以及在哪些方面可能需要支持。我们发现成年人通常不想要另一个通用分数;他们想知道本周哪些少数技能值得关注。 <p>Bloomy通过家庭订阅和学校许可盈利。英语语言艺术的费用为每位学习者每月39美元或每年279美元,写作工作室的费用为每位学习者每月19美元或每年139美元。数学计划于7月31日以与英语语言艺术相同的价格推出。学校和微型学校按学生收费,价格因学科覆盖、注册、名单管理和实施需求而异。 <p>由于儿童使用Bloomy,我们收集学习反应、进展数据和辅导对话。我们不出售个人信息,不将儿童数据用于行为广告,也不允许模型提供商在Bloomy发送的可识别儿童数据上训练通用模型。我们与Anthropic和OpenAI签署了零数据保留协议。家长和学校可以根据适用的账户或学校协议请求访问、导出、修正或删除数据。 <p>关于我的更多背景:在Teach For America之后,我为Manhattan Prep / Kaplan教授和设计GMAT和GRE课程,领导了Lyft新英格兰市场的司机招募团队,完成了斯坦福大学的MBA,并在麦肯锡领导了AI转型项目(因此当模型在今年一月终于足够好以实现我在Bloomy追求的目标时,我正好在合适的时间和地点开始构建)。Bloomy将我职业生涯中最关心的不同部分结合在一起:教育成果、学习设计、产品构建,以及将有用的技术带入人们手中。 <p>我特别希望得到家长、教师、从事儿童面向AI的工程师,以及那些构建辅导、评估或适应性学习系统的人的反馈。引导AI帮助与独立掌握之间的分离是否合理?你认为AI在教育中最大的潜力在哪里?我们的安全措施在哪些方面不足?你需要什么证据或产品行为才能信任这样的系统与学生互动? <p>当然,我们也必须警惕许多危险和陷阱,但我相信如果我们负责任和智能地使用AI,我们可以在K-12教育中真正推动变革(这是很久以来的第一次)。
查看原文
Hi HN, I’m Alex Southmayd, the founder of Bloomy (<a href="https:&#x2F;&#x2F;bloomylearning.com">https:&#x2F;&#x2F;bloomylearning.com</a>) – an AI-powered mastery-learning platform for K-12 students. Bloomy provides students with an AI tutor alongside adaptive curriculum (right now Math, English Language Arts, and Writing).<p>How it works: we diagnose students’ skill gaps, place them on personalized learning paths, and give them standards-aligned lessons and a Socratic AI tutor that scaffolds their learning without just giving away the answer.<p>The goal is to solve the Bloom 2-sigma problem (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Bloom%27s_2_sigma_problem" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Bloom%27s_2_sigma_problem</a>) with AI.<p>Short launch video: <a href="https:&#x2F;&#x2F;tinyurl.com&#x2F;bloomylearning" rel="nofollow">https:&#x2F;&#x2F;tinyurl.com&#x2F;bloomylearning</a><p>Longer product demo: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;XHvoKt6qMeo" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;XHvoKt6qMeo</a><p>Families access for Bloomy: <a href="https:&#x2F;&#x2F;bloomylearning.com&#x2F;families">https:&#x2F;&#x2F;bloomylearning.com&#x2F;families</a><p>I started as a teacher. I taught 7th-grade English and writing with Teach For America, and every day I struggled to deliver differentiated instruction to 30 students with 30 different sets of needs. Some students needed remediation, some needed acceleration, and many needed a tutor sitting next to them helping them reason through the next step. Benjamin Bloom’s two-sigma result—that one-on-one tutoring can produce much better outcomes than conventional classroom instruction—always felt intuitively true to me. The hard part was making that kind of attention affordable and available to every child.<p>Then AI changed the cost curve. When I saw schools such as Alpha organize academics around mastery rather than seat time, the model clicked. If you’ve heard of Alpha School, that is directionally the kind of learning model that inspired us. But I kept thinking about the families and schools that already exist: homeschool families, microschools, hybrid schools, and regular classrooms where most children are today.<p>Most students and teachers see learning gaps at the wrong resolution. They get a grade, percentile, benchmark score, or broad standard—not “this is the next skill this student should learn.” Existing personalized-learning products often feel like digital worksheets: they provide plenty of practice, but not much diagnosis or teaching. Very few have AI tutors providing the core instruction. Bloomy starts with a diagnostic—we integrate with third-party assessments and provide our own—and creates a learning path for each student. Students work one skill at a time, receive a short lesson, practice at an adaptive difficulty, and only move forward after demonstrating at least 90% mastery. The learning path updates as the student works, based on their performance and our knowledge graph of skill prerequisites (built in collaboration with Learning Commons &#x2F; Chan Zuckerberg Initiative).<p>Each skill has three stages. Base Camp teaches the concept with worked examples. Climb provides guided practice and Socratic support. Summit is an independent ten-question mastery assessment with no hints or AI assistance. Students need to achieve 90% on the Summit to advance. If they struggle too much, they’ll be routed to a different skill better suited for their level.<p>BloomyBot is not a blank chat window but rather a live, interactive, and observant digital tutor. During practice, it receives the active passage or problem, the question, the student’s attempt, an authored explanation, and relevant misconception context. It follows a scaffolded tutoring ladder: first asking what the student tried, then pointing toward the concept, suggesting a strategy, working through one step together, and only providing heavier scaffolding after the student has struggled, adapting to and learning from the student along the way. Students can interrupt it, and we’ve begun to roll out multilingual support for Spanish, French, and a few other more niche languages that customers have asked for.<p>We currently use a variety of Anthropic and OpenAI models for BloomyBot. The tutor is restricted to the current lesson, redirects unrelated questions, limits conversation length, and is unavailable during mastery assessments. The language model does not choose the curriculum or decide whether a student has mastered a skill.<p>That separation is important. A conventionally “helpful” AI response can be a bad tutoring response: if it gives away the answer, the student completes the task but may not learn anything. Our goal is not to build a homework-answering chatbot. It is to put AI inside a structured loop of diagnosis, instruction, practice, feedback, and independent mastery.<p>LLMs can still be wrong, and we do not claim our constraints eliminate that. We reduce the surface area by grounding BloomyBot in authored lesson content, keeping it on topic, logging conversations, and removing it from assessments. Teachers and parents can review tutoring activity, students can report problems, and safety signals trigger human alerts and a backup audit. We also do not see Bloomy as a replacement for teachers, parents, or human tutors. A good human tutor is better. The narrower question we are testing is whether, during a bounded learning session a student would already be doing, a context-aware tutor can provide better help than static “correct&#x2F;incorrect” feedback. Longer term, the question becomes more whether a student would perform better with one-on-one AI tutoring (at least in certain aspects of the curriculum) than with many-to-one instruction in a medium- or large-sized classroom.<p>Bloomy is now being used across several settings: traditional districts, charter schools, hybrid schools, microschools, homeschools, and families looking for additional academic support. In an early pilot at a charter school in Massachusetts serving ~150 students in grades 6 through 8, students averaged roughly 1.8 times the expected winter-to-spring NWEA MAP growth. This was an observational pilot, not a randomized study, so we treat it as an encouraging signal rather than proof that Bloomy caused the difference.<p>Parents and teachers can see what a student has mastered, what is in progress, and where support may be needed. We have found that adults generally do not want another generic score; they want to know which small number of skills deserve attention this week.<p>Bloomy makes money through family subscriptions and school licensing. ELA costs $39&#x2F;month or $279&#x2F;year per learner, and Writing Studio costs $19&#x2F;month or $139&#x2F;year. Math is scheduled to launch July 31 at the same price as ELA. Schools and microschools pay per student, with pricing varying by subject coverage, enrollment, rostering, and implementation needs.<p>Because children use Bloomy, we collect learning responses, progress data, and tutoring conversations. We do not sell personal information, use child data for behavioral advertising, or permit model providers to train general-purpose models on identifiable child data sent by Bloomy. We have Zero Data Retention agreements with both Anthropic and OpenAI. Parents and schools can request access, export, correction, or deletion under the applicable account or school agreement.<p>More background on me: after Teach For America, I taught and designed GMAT and GRE curriculum for Manhattan Prep &#x2F; Kaplan, led the driver acquisition team for Lyft’s New England markets, completed an MBA at Stanford, and led AI transformation projects at McKinsey (so when models finally became good enough this past January to achieve the kinds of things I am pursuing with Bloomy, I was in the right place at the right time to begin building). Bloomy brings together the different parts of my career that I care most about: educational outcomes, learning design, building products, and getting useful technology into people’s hands.<p>I’d especially value feedback from parents, teachers, engineers working on child-facing AI, and people who have built tutoring, assessment, or adaptive-learning systems. Does the separation between guided AI help and independent mastery make sense? Where do you see the greatest potential with AI in education? Where are our safeguards insufficient? What evidence or product behavior would you need to trust something like this with a student?<p>Certainly there are many dangers and pitfalls we must beware of, too, but I believe we can really move the needle in K-12 (for the first time in a long time) if we use AI responsibly and intelligently.