Previous Founder Sell their live video startup periscope Twitter is back with a new startup – no surprise, this time it’s an AI-centric company.
On Wednesday, former Twitter product owner Kayvon Beykpour Announcement Macro mirroran AI system designed for developers and product owners, summarizes updates to the code base and catches errors, etc.
The startup was founded in July 2023 by Beykpour, now CEO of Macro Mirror, and Kids Friends Joe Bernsteinformerly Periscope and its previous corporate startup, the terrible Clever, sold to Blackboard in 2009. Rob Bishophe sold his computer vision and machine learning company Magic Pony Technology, Go to Twitter 2016.
company Describe its products As an “AI-driven understanding engine” designed to save engineers time and the founder’s product type,”Hope we haveWhen building an early stage company.
Today, engineers use various tools to track work like JIRA, linear and spreadsheets and spend too much time on meetings rather than building, Beykpour said. Macro dimensions are designed to solve this problem.
“I feel like I’m having this pain … Whether it’s every company I work in, or we build our own startups, or huge publicly available companies like Twitter, we’ve all had a difficult way.”
“Trying to understand what everyone is doing, especially when you have organizations like Twitter and organizations with thousands of engineers, that’s actually the bulk of my job and my least favorite part of being a Twitter product owner,” he said.
TechCrunch Events
San Francisco
|
October 27-29, 2025
To resolve this and other issues, Macroscope customers first install their GitHub app, which gives companies access to the code base. They then have the option to install other integrations such as Slack App, Linear App, and Jira apps. The software then does the rest by analyzing the code and pointing out changes that are taking place.
This involves a process called code walk, which uses an abstract syntax tree (AST) (a structural representation of programming code) to gather important background on how the basics of client code work. This knowledge is then used in conjunction with the Big Language Model (LLMS).
Once up and running, engineers can use macro mirrors to spot bugs (pull requests) fixed in their PRs, summarize PRS, summarize how the code base changes, and ask research-based questions. Meanwhile, the product owner can use the software to obtain real-time summary of product updates, productivity insights, answers to natural language questions about products, code or development activities, etc. This can help them determine which teams prioritize engineering allocation.
“Whatever your technical competence is, you can ask natural language questions,” Beykpour notes. “This can be very useful if you try to understand the code base without distracting the team’s senior engineers. Very valuable. If you are CEO and want to literally understand, ‘What did we do this week?’, your choice is to ask the macro mirror or distract some teammates,” he added. “One is much more expensive than the other.”
While there is no product that offers direct competitors to all the direct competitors offered by macro mirrors, it does compete in the code review space – developers check and test code changes before implementation – using tools like Coderabbit, Cursor Bugbot, Graphite Diamond, Gretpile, Gretpile, and more. However, the company says its product has 5% more errors than the next tool when it has its own internal benchmarks of over 100 real-world errors. It also generated 75% of the comments. (it Share its benchmarks publicly in blog posts)
The software costs $30 per month per active developer, starting with five seats and offers enterprise pricing and custom integrations for large businesses. It requires the use of github cloud. Prior to the launch, many startups and large companies have been using the product, including XMTP, Things, United Masters, Bilt, Class.com, Seed.com, Seed.com, Parkhub, A24 Labs, and more.
The San Francisco-based startup has 20 people and received $30 million in Series A funding, which closed in July and was led by Michael Migno at Lightspeed. Other investors include adverbs, Thrive Capital and Google Ventures. To date, Macro mirrors have raised $40 million.
