In partnership with
You Already Have a Take on What AI Does Next
OpenAI or Anthropic? Which model leads the next benchmark? Which company ships the next major breakthrough?
If you follow AI closely, you already have opinions on where the industry is headed. Kalshi lets you trade on real-world AI and technology events, with markets that move as models launch, benchmarks drop, and announcements happen.
The people who follow this space most closely often see the story developing before everyone else. Put that knowledge to work and trade what you think happens next.
Bonus credit varies from $15 to $500. Terms apply.
Hey!
Last week I shared 8 hidden Claude features you didn't know about.
Now here's Part 2: the remaining 9.
Some are product features. Some are workflows. Some are for developers. All of them will LEVEL YOU UP.
Let’s dive in, but check this week's news first👇
📰 Important News
X updated its algorithm to prioritize posts from mutual followers, helping users see more content from people they regularly interact with.
⚔️ OpenAI's relationships with major partners like Microsoft and Apple have become increasingly strained, highlighting the growing competitive tensions in the AI industry.
🎯 Google expanded ad frequency controls, giving advertisers more flexibility to manage how often people see their campaigns.
⚠️ Australia's eSafety regulator says major tech companies, including Apple, Meta, Google, Snap, and Microsoft, are still leaving significant gaps in protecting children from online sexual extortion.
📸 Meta removed Instagram's AI Remix feature just two days after launch following user feedback and early concerns.
9 More Claude Features You Should Know
1/ Devil's Advocate - Claude That Tears Your Ideas Apart
You've decided something. You're convinced it's right.
That's when you need Claude to tear it apart. Not politely. The full case against it. The three realistic ways it fails. What you're not seeing because you want it to work.
Do this before you commit.
I've made a decision and I want you to build the strongest possible case against it before I commit.
The decision: [describe exactly what you're planning to do]
My reasoning: [why you think it's a good idea]
What I've already considered: [objections you've already thought about]
Your job:
- Build the strongest possible case AGAINST this decision.
- Don't balance it with positives. I already believe in it - I need the counterargument.
- Find the assumptions I'm making that could be wrong.
- Describe the 3 most realistic ways this fails or backfires.
- Tell me what I'm probably underestimating.
- Tell me what I would need to believe for this to be a genuinely bad idea.
Be ruthless. If this is a mistake, I need to know now.2/ Claude in Chrome - Claude That Sees What You See
You're using Claude wrong if you're copy-pasting between tabs.
Claude in Chrome is a browser extension. Claude sees your active tab. Reads it. Clicks links. Fills forms. Navigates. You describe the task and step away.
Install from Chrome Web Store. Sign in. Click the extension. Claude now sees everything you see.
Example task:
I'm on this job listings page.
Go through every listing visible and extract: job title, company name, salary range if shown, and the top 3 requirements.
Build me a comparison table sorted by salary, highest first.
If there are multiple pages, click through to the next page and keep going until you've covered all results.3/ Claude Cowork - Claude That Lives on Your Desktop (and Cloud)
Claude on the web can't see your files on your computer. You have to paste everything manually.
Cowork is a desktop app. Claude has full access to your file system. Reads files, edits documents, creates new ones, organizes folders. No copying.
You hand Claude work and it processes your actual files.
4/ Scheduled Tasks - Claude That Works While You Sleep
Most people open Claude, type, wait, close it.
Scheduled Tasks change that. Set a task once. Claude runs it automatically at the time you choose. Every morning. Every Monday. Every hour. No trigger needed.
Claude finishes and saves output to your folder. This works only in Cowork btw!
Example:
Every weekday morning at 7:30am, do the following:
1. Search for the top AI and crypto news from the last 24 hours
2. Pick the 5 most important stories - focus on things that are surprising, counterintuitive, or have real implications for builders and investors
3. For each story write: headline, 2-sentence summary, why it matters
4. Save the result as "brief-[date].md" in my /briefs folder
Keep the tone direct and analytical. No fluff. Readable in 3 minutes.5/ Skills in Cowork - Install New Capabilities Like Plugins
Skills are instruction sets that give Claude specific capabilities inside Cowork. Like apps on your phone.
Install once. Claude knows how to handle that type of task forever. Building PowerPoints. Working with PDFs. Running specific workflows.
Find and install in Cowork → Customize → Skills. Browse new ones. Claude uses them automatically when the task calls for it.
Your competitor's growth lead already saw the spend spike.
While your team is still in standup, the other growth lead already got the alert. Viktor is an AI employee that lives in Slack. It watches your Meta and TikTok spend overnight, flags the underperformer by 7am, and drafts the new brief before your first meeting.
6/ CLAUDE.md - Rules Claude Reads Automatically Every Session
Create a CLAUDE.md file in your project folder. Claude reads it at the start of every session automatically.
Your coding conventions. Writing style rules. Brand voice. Terminology specific to your work. Write once. Claude follows it forever across every session.
# Project: AI Newsletter
## About this project
Weekly newsletter about AI and crypto for builders and investors. 35,000 subscribers. Tone is direct, analytical, occasionally irreverent.
## Writing rules
- Short paragraphs. Max 3 sentences.
- No bullet points in editorial content. Prose only.
- No em dashes. Use hyphens or restructure the sentence.
- Numbers beat adjectives. Write "saves 3 hours" not "saves significant time".
- Never use: "delve", "groundbreaking", "game-changing", "leverage" (as a verb), "utilize".
- Contractions are fine and encouraged.
## Content rules
- Assume the reader knows what an LLM is. Don't explain basics.
- Lead with the most surprising or counterintuitive thing.
- Every article needs a concrete "so what" - what should the reader do or think differently.
## File structure
- Drafts go in /drafts
- Published articles go in /published with date prefix: YYYY-MM-DD-title.md
- Research notes go in /research7/ Claude Code - AI That Writes, Tests, and Fixes Code
You can write production-level code with Claude. Full features. Complex refactors. Not snippets.
Claude Code takes it further. Works inside your development environment. Reads your actual codebase. Writes code. Runs tests. Reads errors. Fixes bugs in a loop until it's done.
Integrates with VS Code and JetBrains. Drop it in GitHub Actions and it reviews or writes pull requests automatically.
8/ Claude Design - AI for Visual Work (No Design Skills Needed)
Most people don't know this exists. Claude Design is a separate tool for visual work.
Product one-pagers. Pitch decks. Prototypes. Landing page layouts. You describe. Claude builds. Exports to PPTX, Canva, PDF, or HTML.
Replaces a 3-hour Figma session with 10 minutes of talking.
9/ Prompt Caching - 90% Cost Reduction on API Calls
If you're building on the Claude API and sending large repeated context blocks (system prompts, reference docs, codebases), you're wasting money.
Prompt Caching stores content server-side. Subsequent calls reuse it instead of reprocessing. Up to 90% cost reduction on cached tokens. Faster responses too.
Add this to any content block you want cached:
"cache_control": {"type": "ephemeral"}Cache persists 5 minutes and resets on each use. Works for system prompts, documents, tool definitions.
{
"model": "claude-opus-4-8",
"system": [
{
"type": "text",
"text": "[your large system prompt or reference document]",
"cache_control": {"type": "ephemeral"}
}
],
"messages": [
{
"role": "user",
"content": "[user message - this changes each call]"
}
]
}
// System prompt gets cached after the first call.
// Every subsequent call within 5 minutes reuses the cache.
// Cache hit = 90% cheaper + faster response.After the first call, your system prompt gets cached. Every subsequent call within 5 minutes reuses it. 90% cheaper. Faster.
You’re Ahead Now
You officially know more about Claude than 99.9% of people using it.
17 features. Real workflows. Real power.
Stop picking and choosing. Learn them all. Use them all.
That's how you actually master Claude 🙌
All the best,
René
