I just gave a workshop at @aiDotEngineer in London on building real multi-agent systems. The best part was hearing people laugh, interrupt us with questions.. You could feel they were following, thinking, and pushing on the ideas with us. Even better, a lot of people came to
AUTOMATION
-
Perplexity Computer Launches Financial AI Rivaling Bloomberg Terminal
By
–
A Bloomberg Terminal costs $30,000/yr and still can't do a fraction of what Perplexity Computer just launched today π»
— Josh Kale (@JoshKale) 9 avril 2026
It now connects directly to your bank accounts, credit cards, loans, and brokerage accounts through Plaid. Your full financial picture, from monthly spending toβ¦ https://t.co/DDsv47oAUk pic.twitter.com/91BEbDL2BMA Bloomberg Terminal costs $30,000/yr and still can't do a fraction of what Perplexity Computer just launched today π» It now connects directly to your bank accounts, credit cards, loans, and brokerage accounts through Plaid. Your full financial picture, from monthly spending to net worth to individual stock positions, sitting on top of 40+ live finance data sources including SEC filings, FactSet, S&P Global, and Coinbase. Every dollar you earn, spend, owe, and invest, cross-referenced against institutional-grade data in real time. You can walk up to this thing and say: β Run a risk analysis on my portfolio against the current tariff environment β Show me where my spending spiked last month and what's driving it β Build a net worth dashboard that tracks everything in one place β Flag any holdings that overlap with what insiders have been selling this quarter And it just does it. Pulls from your linked accounts, cross-references SEC filings, builds the output, and delivers a finished product. The system running underneath is Perplexity Computer. It orchestrates 19 models simultaneously, breaks any goal into subtasks, spins up specialized agents for each one, and keeps working after you walk away. One model handles the reasoning. Another does the research. Another writes the code. Another builds the visualization. All coordinated automatically. Last month they launched with brokerage data only and someone built a Bloomberg Terminal clone in a single afternoon. That post did 7.5 million views. Now they've expanded to your entire financial life: checking, savings, credit cards, loans, and investments all in one place. Wall Street pays $30K a year for a terminal with 30,000 function commands built over four decades. It won't replace Bloomberg for institutional traders executing billion-dollar orders. But for everyone else, the gap just got a lot smaller. Perplexity (@perplexity_ai) Computer now connects with Plaid to link bank accounts, credit cards, and loans. Track spending in detail, build custom budget tools, and visualize your net worth alongside your investment portfolio. β https://nitter.net/perplexity_ai/status/2042256932397019368#m
β View original post on X β @aravsrinivas, 2026-04-09 18:01 UTC
-
AI Workflow for Building VR on the Web Without Code
By
–
We shipped a fully integrated AI workflow for building VR on the web.
— Meta Horizon Developers (@MetaHorizonDevs) 9 avril 2026
Just describe what you want. AI builds it, tests it, and fixes bugs without you touching the code.
Try it yourself here π https://t.co/wMkVEjWT6V
Discover how it works π§΅π pic.twitter.com/GYHZqtk6LdWe shipped a fully integrated AI workflow for building VR on the web. Just describe what you want. AI builds it, tests it, and fixes bugs without you touching the code. Try it yourself here π bit.ly/4czvxUT Discover how it works π§΅π
β View original post on X β @scobleizer, 2026-04-09 17:51 UTC
-

Claude CASH Agent Automates Growth Experimentation Lifecycle
By
–
Claude is now automating it's own growth.
— Lenny Rachitsky (@lennysan) 9 avril 2026
Their team built an agent called CASH (Claude Accelerates Sustainable Hypergrowth), which works across the full lifecycle of growth experimentation: (1) identifying opportunities, (2) building the feature, (3) running the test, and (4)β¦ pic.twitter.com/9LeKJ30FcvClaude is now automating it's own growth. Their team built an agent called CASH (Claude Accelerates Sustainable Hypergrowth), which works across the full lifecycle of growth experimentation: (1) identifying opportunities, (2) building the feature, (3) running the test, and (4)
-

Karpathy’s Second Brain in 10 Minutes
By
–
Karpathy built his second brain with hacky Python scripts over months. I built a prompt that gives you the same system in under 10 minutes. Drop your sources in, point Claude at them, and let it compile your knowledge base. Here's the prompt:
-
Using AI to Monitor and Manage Comprehensive Lists Effectively
By
–
Yup. I understand. My lists go for completeness. And now that I have AI to watch them all they are highly useful:
-
AI Monitoring Agent Built to Track AI Community on X
By
–
Nice list. Mine are far far far more complete: https://
x.com/scobleizer/lis
ts
β¦ And I built an AI to watch everyone in AI here on X: -
Enable Cloud Agents Feature for Pull Requests in Cursor Dashboard
By
–
Enable this feature in the Cursor dashboard: http://
cursor.com/dashboard/clou
d-agents#my-pull-requests
β¦ -
Cursor Adds Demos and Screenshots to GitHub PRs for Cloud Agent Work
By
–
Cursor can now attach demos and screenshots of its work to PRs it opens.
— Cursor (@cursor_ai) 9 avril 2026
Your team can review artifacts created by cloud agents directly in GitHub. pic.twitter.com/qVXyfxPhWYCursor can now attach demos and screenshots of its work to PRs it opens. Your team can review artifacts created by cloud agents directly in GitHub.
-
IIoT Machine Health Statistics Drive Production Revenue Growth
By
–
To see the true value of IIoT, look at the revenue. Sundeep Ahluwalia, CPO at TDK SensEI, notes that providing customers with machine health statistics allows them to fix assets before they fail, keeping production healthy and consistent. Partner content with TDK. #tdk_iiot pic.twitter.com/cqwhxuuIqd
— Lucian Fogoros (@fogoros) 9 avril 2026To see the true value of IIoT, look at the revenue. Sundeep Ahluwalia, CPO at TDK SensEI, notes that providing customers with machine health statistics allows them to fix assets before they fail, keeping production healthy and consistent. Partner content with TDK. #tdk_iiot