🇧🇪 | 🇧🇷 Building Product @ Cold IQ Stack ($6M ARR)
Get Leads on Autopilot
Joined February 2021
- Tweets4.3K
- Following1.3K
- Followers4.2K
- Likes11.2K
Pinned Tweet
Anthropic released their complete prompt engineering guide.
99% won't read it. I spent 3 days testing every single technique.
While you're saying "please" and "thank you" to AI, smart operators are using advanced techniques to 10x their output.
Here's how you can do the same:
I see a lot of people surprised that the Brazilian stock market crashed 15 to 20% after Lula's re-election (as if he was suddenly going to destroy the economy) - hint : was already in power, and it's going to be the 4th time he rules the country in the last 20 years.
The truth is that a lot of Brazilian stocks had a rally over the past 3 weeks (following the expectation that Flavia Bolsonaro would come into power)
So today, a lot of stock just basically came back to the level they were about 2 weeks ago
This is more of an indication of where the market was truly hoping for Bolsonaro rather than Lula, suddenly going to destroy the Brazilian economy
BREAKING: 🇧🇷 Brazil's largest oil company Petrobras $PBR crashes -14% after Lula da Silva defeats Flávio Bolsonaro in the presidential election.
Loic retweeted
Seeing Lula supporters say it’s time to buy the Brazilian stock market. To them, I point to the 2014 proxy (after Dilma’s reelection). Those who bought the Ibovespa lost 40% until the impeachment process started in 2016.
Important detail for anyone thinking of buying: Brazil’s current situation is worse than Dilma’s in 2014.
Good luck to the adventurers
This cost 0$ if you have cold iq btw (unlimited people and company search)
Introducing Jev @typesafeai powered people-search
Just $0.0089/lead, No more $600 subscriptions,
Try it at treg.to/people-search
- 85% cheaper than Clay
- #1 on people search bench accuracy
- Plugin to any agent to find anyone
Fully open source, 0% markup
Git Repo below 👇
the AI industry is weirdly similar to the Oil & Gas industry
Very high upfront cost : Training a model <> Exploration / Drilling
Then after that very high profit margin : Inference <> Production phase (getting oil out of the ground)
That's why I'm still bullish on Saas
sure you can vibe code your own version
but is it really worth it to spend tens of hours + maintenance to replace a $29/m Saas with your own shittier version of that?
Yes, you can now build an inbox in an afternoon.
Congratulations, you are now responsible for:
- Deliverability.
- Bounce management.
- SPF, DKIM, DMARC.
- A domain that slowly drifts into spam.
- Finding out it why the hell it's drifting into spam?!
- Parsing emails from a mail server last updated in 2007
- HTML, plain text, and emails somehow containing neither.
- Outlook’s interpretation of HTML.
- Outlook’s other interpretation of HTML.
- Threading that breaks when someone changes the subject.
- Someone starting a new conversation by replying to an email from 2022.
- Forwards inside forwards inside forwards.
- CC, BCC, reply-all, and someone who really shouldn’t have clicked reply-all.
- Attachments.
- Attachments with malware..
- Inline images that become attachments.
- Attachments that were supposed to be inline images.
- A company logo attached to every reply, forever.
- Quoted replies.
- Distinguishing a quoted reply from the actual reply.
- Someone answering your five questions inside the quoted reply.
- Signatures longer than the conversation.
- The out-of-office that answers your out-of-office.
- Two autoresponders having a productive weekend together.
- Notifications that fire twice.
- Notifications that never fire.
- A reply sent from the notification itself.
- A reply to a notification about an internal note.
- Making absolutely sure that notes stays internal.
- Permissions.
- Two teammates writing the same reply.
- Drafts that sync across devices.
- Drafts that overwrite other drafts across devices.
- A confidently displayed “Saved” that was optimistic.
- Snoozed conversations.
- Time zones (!)
- Daylight saving time (!!)
- A conversation snoozed until a time that technically doesn’t exist.
- One customer showing up as three people across email, chat, and Slack.
- Three different people sharing one email address.
- Merging them.
- Undoing the merge.
- Search.
- Search that finds the thing you can literally see on screen.
- Webhooks arriving twice.
- Webhooks arriving out of order.
- Webhooks not arriving.
- Retrying a failed send without sending the customer six apologies.
- Rate limits you discover during your first traffic spike.
- Training your AI on your product.
- Scraping your website.
- Scraping the pages that need JavaScript.
- Not scraping your entire website footer into every answer.
- PDFs.
- PDFs that are actually pictures of PDFs.
- Keeping the content fresh.
- Knowing when content changed.
- Knowing when content disappeared.
- Making the AI forget the pricing page from last year.
- Conflicting answers across your docs, website, and past replies.
- Deciding which one wins.
- Chunking.
- Embeddings.
- Reindexing everything when you change embedding models.
- Retrieval that finds the answer, not just something with similar words.
- Web search tooling.
- Knowing when to search.
- Prompt injection hiding in a page you just scraped.
- An agent confidently promising a feature you don’t have.
- An agent confidently issuing a refund it shouldn’t.
- Tool permissions.
- Tool timeouts.
- Tool retries that issue the refund twice.
- Knowing when to hand off to a human.
- Actually handing off to a human.
- Not continuing to argue after handing off to a human.
- Evaluating whether any of this works.
- Evaluating it again after a model update.
- Token budgets.
- Context windows.
- A customer pasting an entire novel into the chat.
- WebSockets.
- WebSocket authentication.
- Reconnecting WebSockets.
- Reconnecting 10,000 WebSockets at once after a restart.
- A connection that looks alive but isn’t.
- A phone switching from Wi-Fi to mobile data mid-message.
- Messages that arrive once.
- Messages that arrive in order.
- Messages that arrive.
- Syncing read states.
- Unread badges.
- Typing indicators that stop typing eventually.
- A customer opening your widget in six tabs.
- Anonymous users becoming logged-in users.
- Logged-in users logging out on a shared computer.
- The iPhone keyboard covering the message composer.
- Safari.
- Keyboard navigation.
- A widget that must not slow down the actual product.
- Explaining that “sent” and “delivered” are different things.
- A help center.
- An editor.
- An editor that survives pasting from Google Docs.
- Images.
- Image resizing.
- Broken images.
- Article drafts.
- Autosave.
- Version history.
- Restoring the version before someone deleted half the article.
- Reordering nested categories without losing an afternoon.
- Slugs.
- 301 Redirects when slugs change.
- Internal links that now point nowhere.
- Working out which translations need updating after an edit.
- Search that understands what customers mean.
- Custom domains.
- DNS verification.
- SSL certificates.
- Renewing SSL certificates.
- Someone putting Cloudflare in front of your Cloudflare.
- Mobile layouts.
- Dark mode.
- Code blocks.
- Tables on small screens.
- Sitemaps.
- Canonical URLs.
- Accidentally indexing draft content.
- Accidentally deindexing published content.
- Cache invalidation.
- “I published it. Why does it still show the old version?”
- Making sure your AI sees the new version too.
- Spam.
- Phishing.
- Someone uploading malware as “a screenshot of the issue.”
- Someone pasting their CC details into chat.
- Someone asking you to delete every trace of that CC.
- Logs that also contain the CC.
- Backups that also contain the CC.
- Backups.
- Restoring backups.
- Discovering those are two separate features.
- An expired token.
- A background job that quietly stopped on Thursday.
- “Disk is full.” Sunday. 3 a.m.
- Monitoring all of this.
- Monitoring the monitoring.
Now you have two jobs 🤷♂️
2 things Open AI model are still better at :
- Browser / Computer use - undefeated
- DEEEP research of a bug, it's just relentless
Loic retweeted
Finding your ICP is one of the most difficult parts of marketing. It used to take a lot of data and research... you can now find it in one prompt.
We launched our beta a few weeks ago and already shipped:
- an MCP
- access to 40+ data providers
- access through Slack
- working as a team
- an intelligence layer
... and a few more that are still not visible (yet).
Now I want to show you exactly what this looks like. This first demo will be on finding your ICP from your domain name.
In the next few days, I'll cover every feature and every use case you need to know about ColdIQ's chat interface.
If my French accent is too much, I'll do a quick recap here:
- Paste your domain name
- Ask to find your ICP
- Wait for the tools to do the research
- Clarify if needed
Voilà
ps: we’re still far from the vision we have at @thecoldiq Give it a try for free and let us know what you think (link in the first comment).
Soon enough restaurants will be overwhelmed by agent calling them
At that point they’ll have an agent autoresponder that will take the reservation of the guest agent calling them
