the AI Code Reviewer you won't turn off

Joined March 2025
33 Photos and videos
Pinned Tweet
Ask Macroscope Anything (AMA) is now Macroscope Agent, and it got a big upgrade today: → 6 new integrations (Sentry, Amplitude, GCP Logging, GitHub API, image gen, and MCP) → Event-driven automations triggered by commits and PRs → Webhook delivery an API
2
8
21
4,381
Macroscope retweeted

5
9
35
29,225
Macroscope retweeted
Anthropic’s new Fable 5 model is now available as a choice on Macroscope’s Check Run Agents. In our early testing, Fable’s bug detection is exceptional (the highest of any model we’ve tested), though it runs quite hot on latency and cost relative to our current production code review pipeline. We haven’t switched it on as the default model for our pipeline, but for those who prefer to maximize recall (bug detection) it’s a trivial switch with Check Run Agents :)
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.
5
6
24
4,010
Macroscope retweeted
made a video demoing a bunch of @Macroscope's features: - get an automated, real-time view of your product development — how is the product changing, where is engineering focus allocated. an executive summary of product changes based purely on codebase activity and context from @linear /@Jira. - understand your engineering team's output in aggregate and broken down by individual IC. we estimate coding time per commit so you can see the multiplicative effect of AI tools. beyond token spend, see how much code is actually getting landed across your devs and your autonomous agents (@cursor_ai, @DevinAI, etc). - our Agent acts as an always-on teammate in Slack — ask questions about your codebase, product, or team activity. it can also take actions: fix bugs, create PRs, generate architecture diagrams, pull analytics from PostHog, query BigQuery, and more. native integrations with Linear, Sentry, LaunchDarkly, PostHog, GCP, and the MCP ecosystem. - set up Macros to automate SDLC chores and workflows: one of ours scans Google Cloud production logs daily, clusters similar issues, identifies root causes, creates PRs with fixes, and tags the relevant engineer. all on autopilot. - subscribe Slack channels to get automatic commit and PR summaries. one slash command and you've got a real-time feed of what's shipping — with plain-English summaries legible to anyone, not just engineers.
4
9
46
6,307
Check Run Agents are now live for all customers. Learn more about how they work below and reply letting us know how your team is using them!
Check Run Agents, now available in @Macroscope. we made a video to show you how it works! these are super flexible agents you control that let you enforce your team's coding conventions, workflows, and compliance checks during code review. just define in markdown and include trigger rules, model choice/reasoning levels, and tool access (including any 3rd party integrations and MCP servers you've already connected to macroscope)-- then the agent spawns as a Check in GitHub. we've been delighted by the creativity and complexity of what our customers have been doing with check run agents: enforcing style conventions, coordinating multistep db migration workflows, ensuring public-facing docs are updated in sync with code changes, and more.
2
2
12
1,469
Macroscope retweeted
May 1
Announcing the companies Sponsoring the Situation. @meetgranola @kong @macroscope @blitzyai @merge_api @adquick
8
14
208
24,141
Macroscope Agent reacts to events across your workflow and takes action autonomously. In this demo, Agent: → Pulls PostHog data to answer product questions in seconds → Auto-updates docs and enforces feature flag rules when PRs open → Catches a Sentry error, traces the root cause, and opens a fix PR with tests
1
2
14
201,821
Macroscope retweeted
@kayvz at @macroscope on avoiding the false positives that kill code review products, by grounding agents in up-to-date web context.
1
4
30
4,156
Macroscope retweeted
I filed a minor bug with @Macroscope at 9 am London time. By 3 pm London time (7 am SF time!) @kayvz personally responded and was fixing it. Founder mode.
11
17
273
18,211
Macroscope retweeted
Apr 15
My conversation with @kayvz, co-founder of Macroscope and Periscope. We talk about selling for $120M pre-launch to @dickc at Twitter, turning down @elonmusk, getting trolled by Kobe Bryant and much more. His family immigrated to the Bay Area from Iran and he grew up an aspiring filmmaker. With a push from his mom, however, he toured and eventually got admitted to Stanford. This led to a series of software startups with his best friends and eventual acquisitions from Blackboard and Twitter. He led product there and eventually (graciously) turned down Elon to co-found Macroscope. Kayvon is an incredible storyteller, family man, & product mind. And while his accomplishments are many, he's an even better person. I hope you enjoy this as much as I did! Timestamps: 00:00 Intro 1:54 Fleeing the Iranian Revolution to California 4:32 How Gaming Sparked a Career in Tech 8:28 Growing Up With 12 Kids 12:32 Pissing Off an Apple Exec with a Jailbroken iPhone 4:29 From a Cardboard Sign to Winning Emmys 19:20 Building Software While Skipping Class 20:53 Selling $100k Apps to Best Buy & HP 22:32 Getting Acquired Over a Spam Call 27:03 The Importance of Passion 34:21 The Origins of Periscope 39:20 Scott Belsky Invented "Teleportation" 43:20 Six Months of Failed Designs 47:33 Selling to Twitter Before Launching 54:07 Trolled by Kobe Bryant 57:41 Turning Down Elon Musk 01:01:54 Founding Macroscope 01:10:21 His Two Most Consequential Life Decisions
16
11
97
76,280
Macroscope retweeted
Here's my conversation with Joel Beasley on the @moderncto_io podcast. We discuss: - What @Macroscope is & why we built it - Why AI code review is already better than humans at finding bugs - The Periscope story: 0 to 1M users in a week & getting acquired by Twitter Plus, agent obsession mode, replacing Retool in 2 hours with Claude Code, why big companies need to be jolted, and leadership advice from Bret Taylor 0:00 Intro 0:18 What is Macroscope 3:53 From Periscope to Macroscope — the founding story 9:29 AI code review & building trust 13:48 When does human code review end? 18:43 Building apps with AI in hours 20:31 Agent obsession mode & OpenClaw 22:28 Replacing a year of Retool with a 2-hour Claude Code session 25:14 AI's impact on engineering teams & layoffs 29:10 Why big companies need to be jolted 33:03 The Periscope story — live streaming, hearts & Twitter 37:03 Integrating Periscope into Twitter & building Spaces 41:28 Best leadership advice
4
10
26
3,602
Macroscope retweeted
when we launched @Macroscope, our "Ask Macroscope Anything" feature was a chatbot that answered questions about your codebase. 6 months later: it now generates code, creates PRs, queries your production logs, and can automatically react to events across your entire stack. It’s not just a chatbot anymore. so we're renaming it Agent, and it's getting a big upgrade today:
5
7
40
8,410
Ask Macroscope Anything (AMA) is now Macroscope Agent, and it got a big upgrade today: → 6 new integrations (Sentry, Amplitude, GCP Logging, GitHub API, image gen, and MCP) → Event-driven automations triggered by commits and PRs → Webhook delivery an API
2
8
21
4,381
Agent now has an API. Send a POST with a query and where you want the answer. Agent runs async and delivers to Slack channel, a thread, or a custom webhook. Connecting any workflow: CI pipelines, incident tooling, internal apps. If it can make an HTTP request, it can use Agent.
1
5
236
Some use cases we love internally: → Customer files an issue in Pylon. Agent root-causes using the codebase, drafts fix PRs if possible or tracks the issue in Linear. → Morning Macro automation queries GCP logs, clusters the top errors, opens PRs. → Sentry alert hits Slack. Agent reads the Sentry details, researches the codebase to understand the bug, pushes a fix. Read more on our blog: macroscope.com/blog/introduc…
4
205
Macroscope retweeted

1
8
36
4,405
Today, we’re announcing that Macroscope is shifting to usage-based pricing. Coding agents are transforming coding output drastically, and seats are no longer representative of how much code we process and review. Across our customers in the last 3 months, each dev “seat” on avg produced: → 1.8x more commits → 1.9x more code reviews → 1.7x larger avg reviews
1
5
18
1,382
This new pricing model is effective for all new customers today, and comes with $100 of free credits so you can try @Macroscope. For our current customers: you’ll stay on the seat-based plan until April 27, then auto-transition to usage-based pricing. We hope this gives you time to observe usage patterns and configure spending controls. Please reach out if you have any questions.
1
4
203