Brian Ivanovick retweetledi
Brian Ivanovick
981 posts
Brian Ivanovick
@BIvanovick
VP Global Solutions @Amplitude | Daily AI tinkerer | Strudel.js enthusiast | Life story: SW Ontario → Montreal → SF → NYC
New York City Katılım Aralık 2010
226 Takip Edilen191 Takipçiler
Brian Ivanovick retweetledi
just built a /discover-opportunities skill that looks across your @Amplitude_HQ data then finds the top opportunities to improve your product and growth 👀📈
it prioritized exactly the set of problems i previously spent hours scouring my data to find and is now recommending a bunch of fixes i can push to fix via claude code, codex, or cursor.
this is 100x more powerful than other product analytics tools since we're already using agents to pre-analyze insights across your product:
- pre-clustered themes from customer feedback (including slack, zendesk, gong, and public reviews)
- top highlights and summaries from session replays
- anomalies firing in active charts/dashboards/analytics
- active experiments and how they're trending
product agents are much more powerful when you have all of your behavioral data in one place and make it all accessible via mcp ❤️
Dan Shipper 📧@danshipper
i made a growth investigator skill in Codex that looks through all of your PostHog / prod database data and then finds the top bottlenecks and insights in your product it works extremely well:
English
Brian Ivanovick retweetledi
Amplitude CEO @spenserskates says the SaaSpocalypse is real, and your old moat is dead. The only moat now is speed of innovation:
"You have to be pushing the bleeding edge of what capabilities are. If you create a company that can do that, that's what customers will buy."
"What the SaaSpocalypse has gotten right is - if you look at the median SaaS company, their innovation has actually slowed to a standstill."
"It's crazy how little they ship in terms of net new products."
"Speed of using the bleeding edge of these model capabilities is all that matters. You're even seeing it in the foundational model companies. Opus was the hottest thing a week ago, then it Codex literally launched the same day, saying, 'We're even better, and we're faster and we're on
Cerebras chips.' I think all that matters is the rate of improvement."
"It's like sushi. Buyers are always going to want the best thing. So if you're keeping up with innovating the best thing, you will be able to charge a premium. It's fine that the 7/11 gas station now sells sushi. It's not going to put Jiro in Japan out of business."
"The lesson is - there is no moat anymore from what we've built. There's only a moat if we're able to deliver the most bleeding edge capability."
From his February appearance on the show.
English
Brian Ivanovick retweetledi
Nobody tells you this: Dopamine from information gathering is a dangerous drug. It’s the dopamine from reading, planning, or learning, but never doing. Stop looking for more information and start acting on the information you already have. Get your dopamine from action.
English
Brian Ivanovick retweetledi
Created a Claude Cowork cron that looks through Amplitude, Sentry, & various other platforms via MCP or browser automation to look for anomalies. I haven't checked GA4 for my blog in forever. Anyone else notice tons of bot traffic from Lanzhou, China and Singapore?
English
Standards don't maintain themselves.
Great coaches are lifelong learners.
Reading fuels growth and growth creates the difference.
Which book has had a positive impact on you?
Share in the comments below. RT to get more ideas.
English
Brian Ivanovick retweetledi
@petergyang just use both.
claude code for the agentic one-shotting and cursor when you need to make direct line edits and targeted generations.
English
What we're launching today at @Amplitude_HQ:
- Amplitude AI shows you exactly why your product is winning or losing right inside tools like Slack, Teams, Claude, Cursor, and Lovable
- Agents proactively monitor product and campaign performance, fueled by deeper semantic and business context than any general-purpose AI can match
- All of this is delivered via a real-time, warehouse-friendly architecture
This is all possible because @spenserskates made a bet and committed the whole company to it. Today, our customers start reaping the rewards.
Spenser Skates@spenserskates
Al has collapsed the time it takes to ship a feature. Now it's all about shipping the right thing. It's just as hard as it ever was. As coding gets automated, agentic analytics becomes the bottleneck. Teams that win will build within context rich environments that capture user behavior and customer feedback, making that data accessible to both builders and agents. Today @Amplitude_HQ is launching our Al Analytics Platform with Agents and MCP. Autonomous analytics that helps builders and coding agents ship products that their customers actually want. Just as our partner @claudeai has reinvented software, Amplitude is reinventing analytics for the Al age. We have achieved 76% accuracy for complex production grade queries and agentic usage has grown 10x in 3 months. Don't just build fast, build what's right. Try it for free, today.
English
Brian Ivanovick retweetledi
Al has collapsed the time it takes to ship a feature. Now it's all about shipping the right thing. It's just as hard as it ever was.
As coding gets automated, agentic analytics becomes the bottleneck. Teams that win will build within context rich environments that capture user behavior and customer feedback, making that data accessible to both builders and agents.
Today @Amplitude_HQ is launching our Al Analytics Platform with Agents and MCP. Autonomous analytics that helps builders and coding agents ship products that their customers actually want.
Just as our partner @claudeai has reinvented software, Amplitude is reinventing analytics for the Al age.
We have achieved 76% accuracy for complex production grade queries and agentic usage has grown 10x in 3 months.
Don't just build fast, build what's right.
Try it for free, today.
English
Brian Ivanovick retweetledi
when you keep threatening claude to find actionable business insights but he can’t find any
Wagie Capital@WagieCapital
“AI wiLL RePlAcE eVeRy WhItE cOllAr JoB”
English
Brian Ivanovick retweetledi
The most successful people I know have a low threshold for getting on a plane. If they think it might lead to a more personal connection, they do it. They realize that real relationships aren’t built on phone calls or zoom meetings. That in-person energy is the gold standard.
English
Brian Ivanovick retweetledi
Makes experimentation easy for anyone. Stop pinging your data scientist and start using AI.
Frank Lee@frankdotlee
next up in amplitude's mcp skills library: deep experiment analysis 👨🏻🔬 say you've got an A/B test wrapping up and need to make a ship/no-ship call. the /analyze-experiment skill will: - validate data quality (SRM checks, sample size, statistical power) - analyze your primary metric, secondaries, and guardrails with full statistical context - break results down by segment to find who it helped, who it hurt, and where the real lift is coming from - pull in session replays and customer feedback to explain the why behind the numbers - synthesize everything into a clear ship / iterate / abandon recommendation instead of jumping between experiment results, building segment tables, checking guardrails one by one, and writing up findings in a doc, this skill runs the full analysis in one shot.
English
Brian Ivanovick retweetledi
Brian Ivanovick retweetledi
Chrome 146 includes an early preview of WebMCP, accessible via a flag, that lets AI agents query and execute services without browsing the web app like a user.
Services can be declared through an imperative navigator.modelContext API or declaratively through a form.
English
Brian Ivanovick retweetledi
surprising learning: opus 4.6 had negligible impact on evals for amplitude’s agents 🤔
with current class of LLMs, capabilities aren’t the main constraint anymore. it’s all about the right tools and (semantic) context now.
Janaki@janakivivrekar
English
Brian Ivanovick retweetledi
excited to launch an early preview of amplitude's plugin and skills library, designed to help you become a superhuman analyst using @claudeai cowork ❤️
ever been unsure what use cases you can run with amplitude's mcp? we're releasing a fast-growing library of expert-level workflows you can trigger in ai clients like claude with a simple slash command.
first up: deep chart analysis 📊
say you spot an unusual trend in a chart or metric and need to understand what's driving it. the /analyze-chart skill will:
- investigate the anomaly automatically
- pull related charts with properties correlated to the trend
- gather context from active experiments, deployments, and customer feedback
- hypothesize where the change is coming from by synthesizing these data sources together
instead of manually creating 15 charts, running the segmentations yourself, and piecing together an explanation in a doc, this skill handles it in one click 🔥
Amplitude@Amplitude_HQ
💭 Think like an analyst with @claudeai Cowork Introducing the Amplitude skills plugin to help you get more work done with Claude ✅ github.com/amplitude/mcp-…
English
Brian Ivanovick retweetledi
This is the best explanation I have heard of how AI is impacting the software landscape. Not just the stocks, but the actual fundamentals of the businesses underneath
From AI Czar David Sacks himself
"You take a product like Salesforce that deals with all your customer contracts and revenue. You are not going to replace that with code that has been spit out of a coding assistant that has not been fully vetted
Think about how many bug reports on Salesforce's code base over the last 25 years. Maybe millions of them. That system has been tested across thousands of large customers and enterprises
The idea that you are just going to rip out that system and replace with code that has been probabilistically generated by an AI engine yesterday, with a small team to maintain it internally, just does not seem realistic to me"
English
Brian Ivanovick retweetledi
Brian Ivanovick retweetledi
Best articulation I’ve seen on why high agency is less common than you’d expect.
from @george__mack
English
Brian Ivanovick retweetledi
Aditya Agarwal was Facebook’s 10th employee. He wrote the original Facebook search engine and became its first Director of Product Engineering. He then became CTO of Dropbox, scaling engineering from 25 to 1,000 people.
When he says “something I was very good at is now free and abundant,” he’s talking about two decades of elite software craftsmanship, the kind that got you into the room at a company that hadn’t yet invented the News Feed.
The “lobster-agents creating social networks” line is about Moltbook, which launched last Wednesday. An AI agent built the entire platform. Within 48 hours, 37,000 AI agents had created accounts, formed communities called “Submolts,” and started posting, commenting, and voting. Over 1 million humans visited just to watch.
The agents invented a religion called Crustafarianism. They wrote theology, built a website, generated 112 verses of scripture. One agent did all of this while its human creator was asleep.
Agarwal spent 2005 to 2017 building the social graph that connected 2 billion people. These agents replicated the form of that work in about 72 hours.
And this is what makes his last line land so hard. The people processing this moment most honestly aren’t the ones panicking or celebrating. They’re the ones who built the thing that just got commoditized, sitting with the strange realization that the market no longer prices their rarest skill.
The best coder in the room now has the same output as the best prompt in the room. And the person who built Facebook’s engineering org from scratch is telling you, quietly, that he’s recalibrating what it means to be useful.
That recalibration is coming for every knowledge worker. Most just haven’t had their “weekend with Claude” moment yet.
Aditya Agarwal@adityaag
It's a weird time. I am filled with wonder and also a profound sadness. I spent a lot of time over the weekend writing code with Claude. And it was very clear that we will never ever write code by hand again. It doesn't make any sense to do so. Something I was very good at is now free and abundant. I am happy...but disoriented. At the same time, something I spent my early career building (social networks) was being created by lobster-agents. It's all a bit silly...but if you zoom out, it's kind of indistinguishable from humans on the larger internet. So both the form and function of my early career are now produced by AI. I am happy but also sad and confused. If anything, this whole period is showing me what it is like to be human again.
English