Загрузка видео...

Не удалось загрузить видео

На главную

Logging your work shouldn’t take longer than doing it. PerfectTed Energy has thousands of stockists. After each store visit, their field team sends Claude a voice note: what sold, what they restocked, what’s new. Claude updates the right account in Notion via MCP… and everything’s up to date before...

24,157 просмотров • 6 дней назад •via X (Twitter)

Комментарии: 10

Фото профиля James
James6 дней назад

@perfecttednrg love @perfecttednrg 🍵

Фото профиля Skyler Birk-Stachon
Skyler Birk-Stachon6 дней назад

@perfecttednrg We love @perfecttednrg!!! Our favorite clients ever and our favorite matcha legends 🫶

Фото профиля Ali Lari
Ali Lari6 дней назад

@perfecttednrg this is the kind of ai automation that actually matters because nobody wants to spend the evening converting a store visit into crm admin

Фото профиля Rex MacMillan
Rex MacMillan6 дней назад

This demo seems so simple and straightforward, yet it's exactly how we run our business at @greenirony. Notion isn't the only system that supports our business functions, but it's a huge piece of our context and memory layer, and its flexibility with structured and unstructured data makes it a perfect fit to plug in with any harness or model.

Фото профиля CalenDue
CalenDue6 дней назад

@perfecttednrg the student version of this: 40 minutes typing 60 syllabus dates into a calendar for a class you attend 3 hours a week. the logging really does outrun the work

Фото профиля Maksim Danilov
Maksim Danilov6 дней назад

@perfecttednrg Why has the model picker disappeared in "chat" mode?

Фото профиля Eason
Eason6 дней назад

@perfecttednrg This is what good AI UX should feel like. Give Claude the context, let the plumbing disappear. I keep thinking public links should work the same way.

Фото профиля maxi.me
maxi.me6 дней назад

@perfecttednrg I’m starting to think the best use of AI in Notion is making Notion require less work. Voice note in. Context gets updated. Next action is ready when I need it. That’s the kind of workflow I need.

Фото профиля MASA
MASA6 дней назад

@perfecttednrg Does it ever get tripped up by background noise?

Фото профиля RenXDev
RenXDev6 дней назад

@perfecttednrg Voice notes are a good input surface here because the structured update remains visible in Notion. The agent should keep uncertain fields unresolved rather than inventing them.

Похожие видео

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

Tal Raviv

57,910 просмотров • 8 месяцев назад