Ryan Sherlock
@ryan_sherlock
Pedal, pedal, pedal, code, code, code. Director of Engineering @intercom
At @intercom, R&D is about solving real customer problems, fast and at scale. AI tools are already boosting our velocity, helping us raise the bar, not just write code faster. @darraghcurran shares our plan to double the system’s output. Wild, exciting times in software (with a…
Continuing on the momentum @eoghan shared earlier this week - our whole R&D org are taking on a goal to 2x our productivity through mastery of the wonderful new tools and capabilities AI gives us builders. Buckle up! fin.ai/ideas/2x/
Watching internal demos of this @intercom (and now live!) has been so cool. Opening up phone support to a whole class of customers that couldn't previously consider it.
.@intercom is using the Realtime API to power Fin Voice, their AI Agent for phone support. The new model follows call scripts better, executes function calls more consistently, and hallucinates less, helping provide human-quality AI support, 24/7.
21 years ago today, after months of work, @dhh released Rails v0.5.0 to the world with the note: “this piece will grow in public.” He wasn’t wrong. Since then, Rails has powered countless companies, grew with the support of thousands of contributors, and has kept true to its core…
What a crazy few days!
To put it mildly, the past week at Windsurf has been crazy. There have been a lot of different rumors and reports, so I want to share a transparent account of how it actually went down. Before I start, I just want to say that Varun and Douglas were great founders and this…
Another entry to the Fin AI blog - this time a deep dive on getting LLM inference times down in production, to investigate putting reasoning models in latency critical tasks. There's a lot you can do to get inference time down, compared to a naive approach. Link below!
Ben Healy takes 🟡🟡🟡🟡 @ Tour de France 2025 👏👏👏👏👏👏 #TDF2025 irishcyclingnews.com/ben-healy-take… via @irish_cycling
Our heartbeat is truly THE best customer-centric signal we monitor @intercom. Customer’s perspective is the only valid perspective, period.
I wrote a post on stop monitoring systems; start monitoring outcomes. TL;DR: Your latency and error rate dashboards can be all green, yet customers are having a bad time. Why? Because you’re not measuring what actually matters: customer outcomes. @intercom, with millions of…
Two great new posts to share on the @Fin_ai research blog - detailed technical discussions, the first about how we built this really deep LLM powered feature; and the second about how we used causal techniques, combined with LLMs, to measure the impact. Links below!
I'm so excited by this trend! Have seen PRs fly from Design and PM - no long feedback loops, just people spotting issues and fixing them. Previously, a designer might notice a small UI detail, raise it, get told to file it on GitHub, and then it would just sit in the backlog,…
There's some magic happening in the @intercom design org right now 👀 I kid you not I took more notes from tomorrow's episode with @thoughtwax than any Dive Club convo ever... Think you're gonna like this one ✌️
So much FUD and FOMO going around what the AI revolution is driving. 107% of our code is written by LLMs, my Claude bill is $83k a month, think about the water etc, etc. I started having to mute words. You know what’s not BS? Cold hard cash. We believe so much in Fin, our AI…
Today we’re launching the Fin Million Dollar Guarantee. We’ve been making big claims about our industry-best performance, but we know such claims are cheap. So it’s time to put our money where our mouths are. If we don’t deliver on these claims, we’ll pay you $1M. First, some…
We're putting our money ($1M) where our mouths (or more specifically our resolution rates) are with @Fin_ai - read @eoghan's post for the details.
Today we’re launching the Fin Million Dollar Guarantee. We’ve been making big claims about our industry-best performance, but we know such claims are cheap. So it’s time to put our money where our mouths are. If we don’t deliver on these claims, we’ll pay you $1M. First, some…
I gave a talk at @TheLeadDev about Intercom’s wonderful monolith!
From the post “The result is that Fin is now a strong 8 figure ARR business that in Q1 grew at an annualized rate of 393%, and we’ll pass $100M ARR with Fin in 2.5 quarters.” It’s been fun in this 😀
This is a story about how we rebooted a 15 year old decelerating business to be on course to be the fastest growing large software company in the world in four quarters from today… :) The Q1 Intercom board meeting starts in one hour. Q1 FY26 was the largest quarter by net new…
i was at an event this week and 3 different people told me how good their experience of using @Fin_ai was.
OpenAI is experiencing an outage since morning, but @Fin_ai is running smoothly! We use OpenAI for some components but have robust fallbacks in place for exactly this scenario. When you choose @intercom , you get this battle-tested reliability built in.