Fredrik Wisløff

2.8K posts

Fredrik Wisløff banner
Fredrik Wisløff

Fredrik Wisløff

@frewis

CEO & Co-founder, Findable | “The people who are crazy enough to think they can change the world are the ones who do.” — Steve Jobs

Oslo, Norway Katılım Mayıs 2009
696 Takip Edilen506 Takipçiler
Fredrik Wisløff
Fredrik Wisløff@frewis·
Interesting how everyone is building meeting notes apps these days ;) OpenOats, Minutes, Notion+++
Mat Silverstein@MatSilverstein

Now paying Granola $18/mo to upload my meeting audio to their servers. So I built my own thing. It's 7 MB. Everything runs locally. Works with @tobi's QMD for super fast search, PARA method second brain setup for organized people, projects, entities, @obisidan, CLI, claude code, codex, Claude Desktop. Before a call with Biff it pulls your last 12 conversations, shows you pricing came up 5 times in 2 weeks, and reminds you that you owe Biff a doc from Friday. After the call it asks if you got what you came for. You just ask "what did Biff say about pricing last week" and it pulls from your transcripts. No API key needed, use your existing subs. The meeting prep feature came from messing around with @garrytan's gstack skills. His /office-hours pattern forces you to be specific instead of accepting vague answers. I stole that idea and applied it to meeting prep and post-meeting debrief. It's called Minutes. Rust, whisper.cpp, Tauri. MIT licensed. First real release on github.

English
1
0
1
68
Fredrik Wisløff
Fredrik Wisløff@frewis·
@jainarvind Thanks for sharing! Very much agree: 1. Context access (basic problem for most verticals) 2. Context quality We’re building this for real estate.
English
0
0
0
109
Arvind Jain
Arvind Jain@jainarvind·
Doing this well requires more than just querying a database. Historically we relied on the expertise of the data owner to know which metric to pull. Now it requires an agent understanding which metrics actually matter and selecting the right ones as they evolve over time. At Glean, when we analyze structured data from systems like Salesforce or Databricks, we look at usage patterns, who produced the metric, and how it’s already being used to infer the likely canonical metric. After all, this is fundamentally a search problem. That said, I think one thing missing from the discussion is that the "data agent" is usually just one component of a larger workflow. Take a prompt like: “Analyze my sales pipeline to understand what’s at risk.” Yes, some of that analysis comes from structured data in systems like Databricks or Snowflake. But a large part of understanding “risk” actually lives in unstructured data. Things like team conversations, comments on documents or spreadsheets, and notes from forecasting review meetings. That's why the context layer can’t just operate on structured data. Context graphs are rising in importance because they recognize that agents need a new kind of data structure to understand how work actually happens and how decisions get made. That's what we're working on here at Glean too.
Jason Cui@JasonSCui

x.com/i/article/2031…

English
9
11
115
32K
clem 🤗
clem 🤗@ClementDelangue·
One underrated benefit of six weeks on paternity leave: by the time you’re back, almost an entire AI hype cycle has come and gone, and fads like OpenClaw are already dead
English
38
13
477
54.5K
Christoph Janz 🕊
Christoph Janz 🕊@chrija·
Excited for the OpenClaw Meet & Build event that we're hosting in Berlin on Friday! If you've signed up and haven't heard back yet: We're sorry. We have capacity for 250 people and we're at 500+ signups and counting. We’re doing our best to put together a diverse group of builders and will confirm spots as soon as possible. luma.com/ek5cb0vq
English
4
3
13
3.9K
Fredrik Wisløff
Fredrik Wisløff@frewis·
Feeding my Tamagotchi (aka. @openclaw) 🐣 Remember the Tamagotchi? That little egg-shaped anxiety device you had to check every four hours or it would die and you'd have to explain to your parents why you were crying over a keychain? That's what building my AI agent in OpenClaw feels like right now. Discover a new skill on X. Feed it. Connect a tool. Feed it again. Tweak a prompt. Hover anxiously waiting to see if it evolved. The original Tamagotchi never did anything useful. It just beeped, demanded attention, and died if you got busy. This one drafts my contracts, analyzes 12 months of sales calls, and hands engineering fully-formed feature prototypes. Like one of my favourite prompts so far: "From everything you know about me and my workflows, what tools or automations am I missing that would measurably improve how I operate?" Nobody tells you that an AI agent is a commitment. Most people expect: install, configure, done, revolutionary -- Nope. It's a Tamagotchi. Except this one actually earns its keep. Back to feeding. 🦞
Fredrik Wisløff tweet media
English
1
0
0
51
Peter Yang
Peter Yang@petergyang·
Here's what I want: 1. All my personal OS docs in the cloud so I can access them from multiple computers securely. 2. Can update the docs either via the AI or manually editing them. Managing context is key. 3. Can easily talk to and update my personal OS on my phone without having to submit a bunch of PRs. Can probably figure out a janky solution with Google Docs + Claude Code + OpenClaw.
Peter Yang@petergyang

Friday night dilemma is whether to set up personal OS on Claude Code or in OpenClaw

English
36
1
107
35.7K
Fredrik Wisløff retweetledi
Declaration of Memes
Declaration of Memes@LibertyCappy·
I laughed so hard my sides hurt! 😭😭😭
English
270
3.5K
18.5K
821.2K