I was sick in bed yesterday, scrolling through my feed, and found Felix Kraus’s post about his OpenClaw automation setup. One idea stuck: nightly knowledge extraction from conversations and notes.

The problem is familiar to anyone who takes notes. You write things down throughout the day — meeting notes, project updates, random insights — and most of it slowly rots in place. The useful bits get buried under the noise.

The setup

I already had the pieces:

I bookmark a lot on Twitter. Tech threads, SRE war stories, product launches, random gems — they pile up fast and I rarely go back to review them.

So I automated it.

The Setup

Every morning at 5:45 AM, my AI assistant Jax fetches my latest Twitter bookmarks, picks the most interesting ones, writes a short summary for each in Russian, and posts the digest to a public Telegram channel.

The whole pipeline:

I can’t imagine using a terminal any other way: every Ctrl keybinding remapped to Cmd.

Think about it. Ctrl lives in the corner of your keyboard. Your pinky stretches to reach it, and then contorts into whatever combination you need. Cmd sits right under your thumbs — the strongest, most naturally resting fingers on the keyboard. Why wouldn’t you use it?

The readline connection

In Unix-like systems, the readline library provides Emacs-style navigation in shells like bash and zsh. These keybindings are everywhere:

I never managed to keep a work journal. Tried paper, Obsidian daily notes, time trackers — they all lasted about a week before I stopped bothering. Then I realized I already had one. Every Claude Code and Gemini CLI session logs every prompt I type.

Those transcripts are sitting on your disk right now. They record what you actually worked on, not what you planned to work on. That’s more honest than any journal I’ve kept.

Peter Steinberger, the creator of OpenClaw, said something on a podcast recently that stuck with me: he reviews prompts more carefully than code. He asks contributors to attach their prompts to pull requests. He finds more signal in the prompt than in the diff.

I manage an SRE team at Billie. We use Claude Code and Gemini CLI daily. And I’ve noticed a pattern: everyone’s figured out their own way of working with AI, but nobody talks about it. One person has a brilliant technique for debugging Terraform. Another figured out how to use browser snapshots for visual regression. But these tricks stay locked in individual heads.

Obsidian 1.12 shipped a CLI. Buried in a changelog full of CSS tweaks and file explorer fixes, this is the feature I care about most.

I have about 400 notes in my Obsidian vault, synced via Syncthing to a Linux box where AI agents run against it daily. Claude Code, OpenClaw, custom scripts. They search for context, check what links where, pull facts out of my daily notes. And until this week, all of that happened through grep and reading files one at a time.

I refactored some components in our internal admin panel last week. The code looked fine. Tests passed. I shipped it.

Then someone opened it on a phone. Half the layout was broken.

This is the oldest story in frontend development. You change something, it looks fine on your screen, and it’s broken somewhere else. The feedback loop between “I changed the code” and “I can see what happened” has a gap in it.

I got an email from Google this morning about a new OTLP endpoint. Buried in the usual “no action required” corporate-speak was something I’ve been waiting for: telemetry.googleapis.com — a single endpoint that accepts native OpenTelemetry Protocol for logs, traces, and metrics.

It goes live March 23, 2026.

The old way was annoying

If you wanted to send OTel data to GCP before, you needed GCP-specific exporters. Your pipeline looked like this:

I’ve tried GTD, bullet journals, Notion, Roam, and probably a dozen apps I’ve already forgotten. They all failed for me. Not because they’re bad tools, but because I’d always find excuses not to open them.

Obsidian stuck. It’s local-first, plain markdown, fast. But even with Obsidian, I kept abandoning my daily notes. The friction of “open app → find today’s file → remember the format → actually write something” was enough to break the habit.

In case you think the environment full of distraction and context switching introduces such negative effects as reduction of ability to stay focused on a single task for long enough, you’re not alone. No time for long reads, shorter interactions, anxiety and fear of missing out. Yeah, it’s real.

I’d like to share results of my current ongoing experiment highly inspired by this video, which I definitely recommend for watching