←
Boris56 posts
Boris avatar

Boris

@Boris_web

@teableio 联合创始人 & 技术负责人|AI 出海创业中 Focus表格产品,占职业生涯 90%|开源 2.2 万 ⭐ 分享 AI Agent 工程、数据库和出海踩坑

◷ Joined March 2021
Boris avatar
Boris@Boris_web·Nov 17

我是 Boris,一个把表格做了 N 年的工程师。 职业生涯 90% 的时间都在做同一类产品:多维表格。现在是 @teableio 联合创始人,负责技术。 很多人觉得表格是个早就做完的东西。我做了这么多年,反而觉得它现在才刚开始。 Teable 一开始是个开源的多维表格,底层直接用 Postgres,GitHub 上现在 2.2 万 ⭐。这两年转成了 AI 产品:你把业务讲清楚,它把数据库、应用和自动化搭出来。 我们主要做海外市场,也就是大家说的 AI 出海,只不过我是从技术这头看的。 【这里会写什么】 · AI Agent 工程:沙箱、计费、防盗刷,这些没人写但躲不掉的事 · 数据库:Postgres 性能,和几次线上事故的完整复盘 · 出海:一个技术负责人看到的真实过程,包括做错的决定 不讲大道理,只写我自己踩过的。做 AI 产品、做出海,或者也在跟数据库较劲的,可以关注一下。

Boris avatar
Boris@Boris_web·7h

总结:还是Fable 5.2好用,缺点就是太贵了 6.2 Astra 和 opus 5.5会给人一种不省心的感觉,会要我花费很多精力去review他们的工作,但是用fable完全就没事,减少人类心智负担🤠

I took this to heart and spent the last few hours doing another deep dive on GPT-6.2 Astra tl;dr - things are better than when I tested, but IMO still "directionally, very bad" I'm going to keep using the same example I've hyperfixated on since the start: "why is creating a worktree so slow?" I had a long thread trying to diagnose perf issues while using t3 code on a particular VPS. 2 of the 3 were fast, 1 was really slow. I asked astra outright "why is this so slow?", and it said a bunch of gibberish. I followed up with "I feel like I'm going insane, can you just tell me the cause of the slowness?" I'll give you the answer upfront: this VPS uses a virtual disk that is slow as shit, my other VPSs have physical NVME drives that are faster. Image 1 is from before the fixes Tibo mentioned. It shows an unnecessary graph, focuses too much on pnpm and file systems, bolds irrelevant text, and brings up ram just as much as it (subtly) mentions drive speed. Image 2 is of Opus asked same thing. It opened with the important part in bold: "Slow disk, made worse by VDO". Ideal! Image 3 is 6.2 Astra post-fixes Tibo mentioned. Better? Absolutely. Much more concise. Sadly, it still focuses way too much on second-order problems that are a small % of the cause. "XFS over a compression and deduplication layer on a virtual disk." - so close, but still a miss. I think this perfectly encapsulates the problem I have with 6.2 Astra. It doesn't miss anything. It's SO thorough. But in it's thoroughness, I find it misses the most important thing: the actual point. It wants to know everything, and then it wants to share everything. It doesn't understand what is and isn't important. Did it say anything wrong in my screenshots? Not really. But IMO, it still entirely failed to miss the point of my question, and gave an answer that was too focused on accuracy and not enough on clarity. In the wise words of Michael Seibel: "Most aim for 100% accuracy, and they end up with 50% clarity. Aim for 100% clarity, 80% accuracy". Silly way of putting it, but I genuinely wish OpenAI models would lie to me a LITTLE more so I could better understand the vibe, instead of having my time wasted by all these useless details.

Post attachmentPost attachmentPost attachment
Boris avatar
Boris@Boris_web·7h

我觉得 Teable 最有意思的地方不是建表,而是连接。 GitHub、Jira、Gmail、Slack、公司内部 API,数据都能往里聚集和管理。把散落的管理注意力放到一个地方

SaaS is dead. Internal tools go first. Introducing Your agent × Teable Teable = Supabase + Vercel + Zapier + Airtable + Clay We handle database, auth, hosting, automations, integrations, data sources. Try it: tell your agent "install teableio/agent-skills for me"

1:02
Boris avatar
Boris@Boris_web·9h

来聊点 AI 安全。 AI 越自由就越危险,限制越多用起来就越麻烦。最近一直在想,写代码、做运维的时候,这个度到底该怎么把握。 AI 越来越强,介入工作越来越深,安全问题也越来越多。现在连 Vercel、Notion、Cursor 这些大厂都出了比较严重的安全事件 最近也一直在做对应的调整策略,改变团队以前过于free的方式的同时不那么麻烦。等后续实践顺畅了再分享出来。 想问问大家:你们在实际工作中是怎么平衡的?给 AI 放多大权限?哪些东西坚决不让它碰?

Boris avatar
Boris@Boris_web·Nov 17

100 个 AI 沙箱跑 1 小时,我们这边大概只要 $0.30。 我看到 Agent37 发了一组对比:给 100 个 coding agent 各开一个沙箱写应用,按 CPU 只有 5% 时间在干活来算,每小时费用是: Vercel:$9.75 E2B:$16.56 Daytona:$16.56 Agent37:$0.68 按同样的算法,@teableio 的成本大约是 Agent37 标价的一半。怎么做到的: 1. 之前用 Vercel Sandbox,看到账单后决定自建,现在用的是 k8s + OpenSandbox 2. 最开始恐惧要运维部署那么多东西,没有经验,结果发现claude code完全能够支撑这个工作 3. 便宜的原因一部分是云厂商折扣,剩下的是按自己的负载调的:我们的 agent 吃内存远多于吃 CPU 所以我们是占了便宜的,而且策略会定期根据我们线上用量进行调整,保证稳定性和成本取舍。 Agent37 能做到这个价还是很厉害,好奇这个价格他们能不能赚钱。 顺便说一句:用户已经在这套设施上搭了 1 万多个团队应用。

At @teableio we used Vercel Sandbox until we saw the bill, and built our own on k8s with OpenSandbox. We expected running it ourselves to be painful, but Claude Code handled most of the Terraform and k8s work. Same 100-sandbox math comes out to about $0.30/hr for us, roughly half of Agent37's list price. Part of that is a discount from our cloud provider. The rest is tuning for our own load: our agents need memory far more than CPU. Given those advantages on our side, what Agent37 has pulled off is still impressive. Curious if they can turn a profit at that price. Btw: Our users have built 10k+ team apps on this infra so far.

Boris avatar
Boris@Boris_web·Sep 26

😮 这周被opus 5.5游戏包围

Yo Opus, build me League of Legends in 3rd person with action combat, AAA quality, and make no mistakes!

Post attachment
Teable avatar
⟳ Boris retweeted
Teable@teableai·Jul 23

🎉 Introducing Teable 3.0 — The AI Spreadsheet for Business. Teams can build 100% business-fit AI workflows and custom apps, while connecting and migrating any data into one place. ✨Whether you’re a small business or an enterprise, Teable helps your team become truly AI-native. 🙌 Teable is live on Product Hunt! If you like what we’re building, your support would mean a lot to us: producthunt.com/products/tea…

3:17
Teable avatar
⟳ Boris retweeted
Teable@teableai·Jul 8

Call a Skill. Or create your own in Teable AI Chat. 📎 Built-in Skills help with files like XLSX, PDF, DOCX, and PPTX 🛠️ Skill Creator turns repeatable workflows into reusable Skills ⚡ Call any Skill later with / See it in action 👇

0:51
Teable avatar
⟳ Boris retweeted
Teable@teableai·16 Sep 2025

Introducing Teable 2.0: The AI Database Agent 1️⃣ From the best open-source no-code DB → now the first AI Database Agent 2️⃣ Transform all your data into action: organize, analyze, automate, batch-generate — all in seconds 3️⃣ Make data work effortless & smart — for everyone

3:09
Vercel avatar
⟳ Boris retweeted
Vercel@vercel·8 Jul 2025

At Vercel Ship 2025, @cramforce shared a no-nonsense approach to building AI agents. Learn how to build and secure AI agents that automate complex workflows, and understand the product and business impact behind them.

30:25
tldraw avatar
⟳ Boris retweeted
tldraw@tldraw·19 Jun 2024

be careful not to mess up @tylerangert's drawing

0:30
tldraw avatar
⟳ Boris retweeted
tldraw@tldraw·20 Jun 2024

prefer physical whiteboards? no problem

0:31