OBSIDIAN + CLAUDE OPUS 4.8 = THE $6,000 SYSTEM YOU ARE MISSING
most databases just store data. this setup actively maps connections between notes and gets smarter without you doing anything
the algorithm:
> Obsidian - local storage for raw files and notes
> Сlaude Opus 4.8 - semantic engine to find hidden patterns
> python script - background runner that feeds the graph on every edit
they loaded all their sales logs, the system identified a pattern they missed for months, and one tweak to the workflow brought in an extra $6,000 last week
obsidian would never find that pattern for you
full guide on how to build a knowledge agent that actually thinks 👇
Deleting this in 48 hours.
I'm finally giving away the exact 17 B2B outbound skills I use to run my entire outreach stack without re-explaining my ICP, persona, or value props every session.
Comment "Outreach" and I'll DM you the full plugin for FREE.
Hands down the absolute best Claude Cowork tutorial you’ll watch in under 25 minutes!
Made by Tina Huang (@hellotinah), former Meta data scientist turned content creator 👇
Claude can now sell for you 🤯
Meet Autosales
An AI Employee that sells your Product FOR You 24/7
Just Paste your website URL and watch it sell.
Trained on Brain data of a $1.2M/year Sales Guy
Comment "Auto" for Exclusive Invite.
Cisco cutting 4k jobs on record revenue is another beat in a very familiar wall street tune: cut jobs and bet AI will make up the slack and reap the reward on the Street today.
I'd ask if they have back-office automation KPIs that actually justify those numbers or if it's smoke and mirrors
THIS GUY BUILT A CLIPPING HERMES AGENT INSIDE HIS TELEGRAM
Hermes agent handles his entire content pipeline through DMs.
Hermes Agent can now:
- analyze YouTube videos
- clip up viral segments
- face track different speakers
- add hooking captions
- schedule and post
(p.s he is using https://t.co/qRDa2sYLFR)
The 2 things Google pays AI engineers $400k to know.
Stanford just taught it for free in one lecture.
No tuition, no application, no waitlist, no $15,000 bootcamp that teaches you half of this in 6 months.
Just a lecture on Diffusion and Vision Model Architectures sitting freely available right now, waiting for someone to actually watch it.
The same foundations that separate an $80k engineer from a $400k one are free, have always been free, most people just never looked.
Watch it now, bookmark it for later, send it to someone who needs it.
This is the kind of lecture that changes how you think about AI architecture permanently.
GOOGLE JUST SHIPPED ITS ENTIRE 2026 ROADMAP IN ONE KEYNOTE
Gemini 3.5 Flash → new flagship. frontier brain, agentic, beats 3.1 pro, 4x faster
Gemini 3.5 Pro → the bigger one, drops next month
Gemini Omni → any input in, editable VIDEO out
Gemini Spark → a personal agent that actually DOES things across your apps
Daily Brief → your morning, pre-read from gmail, calendar and tasks
Neural Expressive → the gemini app got a full redesign
Universal Cart → one agentic cart across gemini, youtube and gmail
Information Agents → search that monitors the web 24/7 FOR you
Intelligent Search Box → expands as you type for real conversations
Search Mini Apps → build your own dashboards inside search
AI Mode → now fully running on gemini 3.5 flash
Gmail Live → talk to your inbox
Docs Live → write and edit docs by voice
AI Inbox → gmail, organized by ai
Google Keep → speak freely, it cleans it into notes
Google Pics → a brand new ai image and design app
Ask YouTube → search the ENTIRE youtube catalogue with answers
Android XR Glasses → "intelligent eyewear," audio glasses this fall
Android Halo → a live strip showing what your agent is doing
Antigravity 2.0 → the agent-first dev platform, upgraded
Flow + Flow Music → now standalone mobile apps