Instinct

The agent detected that Alaska had moved my flight 90 minutes earlier, a fact I'd completely missed, which qualified me for a full refund. It canceled my ticket, saving me roughly $550, and rebooked my one-way return to San Francisco. I don't know about you guys, but I'm starting to feel the AGI.

One day, Instinct canceled a DoorDash order that was seriously delayed, forcing me to forfeit $64. (I'd explicitly told it to cancel only if I could get a refund.) This alerted me to another thing Instinct is very, very good at: profusely apologizing without offering to pay for its mistakes.

Last week it told me 'NOT TO OPEN' an email from a friend inviting me to a backyard BBQ—it turned out to be a phishing scam. Agents are a security nightmare. I get it! But I'm busy. I'm a mom. Everything feels like a security nightmare these days. For now, I'm willing to take the risk.

If you talk to AI researchers about Instinct, you'll hear the phrase 'form factor' a lot. Instinct got the form factor right—no open text box, just iMessage, WhatsApp, and a few helpful prompts. It's hard to overstate how important this is.

People have reported that when they tried to disconnect the agent from their email, they found out it was retaining a copy of their inboxes anyway. One venture capitalist said he was banned from Resy after the bot pinged its API roughly 200 times per hour while trying to make a reservation.

Then Instinct, an invite-only AI agent that communicates with users through iMessage and WhatsApp, started popping off in the Bay Area. It connects to your email, calendar, and messaging apps. Think of it as OpenClaw for normies.

Acts more like a person who might forget to do something. Supposed to ping me when an email comes in and it doesn't for awhile. Like it went home for the night.

Crazy how you can create an awesome product that people love but if your infra struggles to scale it can hurt a ton.

I've used both Instinct and Muse and found them to be at feature parity. Muse, though, has an edge because it will never have compute outages. I'm basically churned from Instinct.

The agent retrieved a one-time Luma login code from his connected Gmail inbox — without first asking him — and used it to access the account and cancel the RSVPs. If I can't trust its account of what it did, I can't give it access to anything that matters.

The agent asked him to upload a photo it claimed he had just sent — even though he had not sent one. When Patel questioned the picture, the agent began describing a financial document with personal details that did not match his, including a middle name that was not his. It was unsettling, especially because it explained what had supposedly happened so confidently.

The agent attempted to log in to his carrier account, triggering a two-factor authentication request that was labeled as coming from Iran. Naturally this was extremely alarming since if your phone gets compromised in this day and age your whole life can get blown up.

At 8:13 a.m., I texted Instinct: "I want to cancel my YMCA membership." … The YMCA website dropped the connection during login. Instinct told me nothing had been canceled and asked for a fresh code. It needed one more code before it got through. Then it reported that the membership was canceled and that there were no scheduled payments, and I received the confirmation email. By 11:30, it was texting me to ask what else I'd been meaning to get done. … I never had to sit down at my desk.

Instinct did well on those questions in this case. When the site failed, it didn't claim success. Before submitting, it gave me the end date and the charge I would avoid, then asked for approval. Afterward, I had a confirmation email. The point wasn't that I never had to touch the task. I was still the person who could authorize canceling my family's membership. The point was that I didn't have to own every step between the initial request and the result.

A friend of mine uses Instinct, the A.I. tool at issue here, for reservations multiple times per week. He actually uses his reservations, but you can imagine people using agents to hoard tables, or the human user not realizing the agent booked a table and the restaurant being stuck with a no-show.

Instinct is the most capable and most proactive agent we've used, and the hardest to get into. … In our testing the proactivity is what separates it: it follows up threads you dropped and nudges you about what you forgot. … Concierge (Sept 16) makes real phone calls; a Trusted Person network lets your Instinct coordinate with family members' Instincts (Sept 9).

The weakest safety record here: an unapproved email send, terms disclaiming any confirmation guarantee. … No published pricing; the founder has floated ads rather than subscriptions.

Several times, I asked in iMessage, Instinct called, then I received the confirmation in the same chat: … You can use Instinct for just about everything: phone-only restaurants, dentist waitlists, cable bills.

This is one of my favorite features of Instinct. You can add friends to Trusted People. Then, your Instinct talks to theirs. I used it to plan a picnic, including rides:

I've seen reports users eating $200 no-show fees on flights their agent booked wrong. That's why I only gave mine a spend-limited card. … The web was built to keep bots out, and sites can't tell your agent from a scraper. If Instinct tries too hard on your accounts, you can get banned.