We’re hosting an event with @Google on July 14 that I’m really excited about: In Good Company. Founders and engineering/product leaders will demo the internal AI tools and products their teams rely on every day. Stuff that’s usually unseen publicly.
If you’re a founder, eng/product leader, or engineer, come join us @ Google SF to learn, mingle and snack! https://t.co/0WYyxwXMQD
Deep codebase understanding means an agent that (without being told):
> knows your feature branch exists
> knows the bug lives there
> targets the fix correctly
Fix bugs from anywhere with Macroscope
We 🚢 a TON of new features this week ↓
→ Ask Macroscope to create PRs from Slack
→ Webhooks to invoke Macroscope from anywhere
→ Code Review validates your PRs against linked @Jira or @linear issues
→ New native integrations w/ BigQuery, @LaunchDarkly, and @PostHog
→ Code Review: "AI Prompt" for easy copy/pasting to your coding agent
...and more
Both Anthropic and OpenAI dropped new models today. For some teams, that means hours/weeks/days of re-tuning prompts. For us, it means hitting "run." We wrote about why we stopped writing prompts: https://t.co/xmUF1cD3Lz
When a computing environment is generally capable enough as AI is, it's not new software capabilities that make it tailored to your needs, but the data. Every company and every person will one day have a magical library that personalizes their computing experience.
We're building Pacific to pull that future forward.
Every company and every person will one day have a magical library that personalizes their computing experience. We're the team building it.
Meet Pacific:
Today we're releasing Macroscope Code Review v3. Based on our internal benchmarks:
→ Detects up to 3.5x more bugs that would cause real production damage (data loss, security breaches, crashes, etc). The kind you'd block a PR over.
→ Precision increased to 98% (up from 75%) which means significantly fewer false positives.
→ Leaves 22% fewer comments overall, including 64% fewer nitpicks in Python and 80% fewer in TypeScript.
Delightful demo moment that would have been inconceivable a year or two ago: While doing an onboarding yesterday, I noticed a bug in our web app. Mid-meeting I posted the bug in Slack flagging one of our devs and asking @Macroscope to make a linear ticket while + investigate and fix in parallel.
15min later Macroscope had made the ticket, found the issue, fixed it in a PR and validated no bugs in code review. End to end the fix was merged, tested (via live vercel preview link) and deployed to prod within 20min-- before the meeting was even over. Inadvertently turning a lemon into lemonade and a made for a great demo.
What a time ...
Today we’re releasing v2 of Macroscope Code Review, powered exclusively by @claudeai Opus 4.5. It’s the biggest performance upgrade we’ve shipped to Code Review since launch.
we’ve been testing claude opus 4.5 as the core model powering Macroscope's code review. the overall balance of cost, latency + performance (precision/recall) is the best we’ve seen, so we’ve started rolling it out to some customers in beta today.
One of the biggest challenges for growing tech companies is keeping teams aligned as they scale. That’s where Lightspeed-backed @Macroscope comes in and why we’re proud to be leading their $30M Series A.
Founded by @kayvz, Joseph Bernstein, and rob_bishop, Macroscope gives teams real-time visibility into their code with AI-powered review and “code walking,” which maps out how everything connects and explains it in a way that’s clear, even for non-coders.
It's Macroscope LAUNCH day! @kayvz, @Rob_Bishop, and Joe Bernstein are building an essential product for the AI software development era.
What got done this week? What are people (and AI engs) shipping? How is the code base changing?
It's a world-class team creating a new product category and we're so psyched they're pulling the curtain back so everyone can use it!
Macroscope will help your team ship fewer bugs and merge Pull Requests faster. In our internal testing, Macroscope’s bug detection rate exceeds other code review tools we’ve benchmarked against (read more about our methodology on our blog, linked below)
Hello World 👋
Macroscope uses your codebase to automatically summarize product development activity, answer questions (about product and codebase functionality, and dev progress) and catch bugs.
Sign up now and get a 2 week free trial.
excited to share what I’ve been up to:
today, we’re launching @Macroscope: an AI system that uses your codebase to answer questions about what’s happening and automatically reviews your PRs for bugs. we raised a $30M Series A led by Lightspeed & Thrive Capital, Adverb and GV.
I’m proud to be re-investing in this round alongside @ZehanWang and find deep satisfaction in getting to help others build companies much more exciting and impressive than ours as a Venture Partner at @join_ef. @join_ef‘s flywheel is only just getting started!
It’s hard to understate how different my life might have been without EF. Not only would I likely have never met @ZehanWang (despite us both being at @imperialcollege at the same time) but without @Alicebentinck’s encouragement, I might not have even become an entrepreneur...
Why we raised a $158m Series C https://t.co/BFclwgwWNt
One great thing about this round is getting to bring in to @join_ef as investors people I've admired for many years - people like @patrick_oshag@eladgil@mattjackrob@t_blom to name just a few. Excited for this chapter!
I was honestly extremely skeptical of @join_ef when I started. How were a bunch of inexperienced strangers going to build valuable startups? But within 18 months @ZehanWang & I had not only built an extremely close relationship but a >$100M company as well.