Self-learning

Macroscope learns from every PR, incorporating feedback from your reactions, responses and which review comments are being accepted.

Deep Codebase Understanding

Macroscope uses Abstract Syntax Trees (AST) to create a graph-based representation of how your codebase works, allowing it to find hard-to-detect bugs while avoiding false-positives.

Context from your tickets

Macroscope pulls context from your issue management systems to understand the 'why' behind each change. It evaluates your PRs against their linked tickets and reviews them for issues using that context.

People seem to like it...

Scott Belsky

Cofounder of Behance @ Founder A24 Labs

Macroscope has become a core part of our engineering team, bringing some new superpowers in productivity and keeping us all aligned and up to speed on what's getting done every day.

Shane Mac

CEO, XMTP Labs

Rarely do I see a product that helps everyone in the org save time and do more without asking us to do more. The team does less updating while leadership can see what's actually happening - and even ask questions about it - all without distracting anyone.

Logan Fisher

CPO & CTO, Parkhub

Macroscope just gets it. They've cracked the code on turning huge amounts of complex data into clear, actionable insights-and they've made it effortless for us to make smarter decisions, faster.

Parag Agrawal

CEO, Parallel

We are huge fans. It's the best code review tool we've tested and I personally love that we can avoid unnecessary status update meetings.

Kris Stokking

SVP of Product Development, Class.com

It's become a critical time saver for product development, providing useful feedback to developers during code reviews, reducing time-to-root-cause in troubleshooting, helping organize project plans and release artifacts, and illuminating areas that have lacked clear documentation.

Michael York

CEO, Casa

Macroscope's commit summaries – drawing from their deep understanding of our projects and codebase – are the beating heart of our engineering organization. The kind of upgrade you can never imagine working without.

Nick Molnar

CEO, XMTP Labs

We've used just about every AI-driven PR assistant out there: the signal to noise from Macroscope is the best I've seen. The PR descriptions are better than what we would have written by hand, and when it flags an issue it's almost always a real bug.

Hardik Patil

Product Lead at Anon

Macroscope makes it easy for me to stay on top of engineering progress and developer productivity, even as a solo product lead working with 8 engineers. Their support is ridiculously responsive, and they're super fast at shipping new features I requested.

Marcel Molina

CTO & Cofounder, Particle

Macroscope is like having a distinguished engineer tech lead who's read every diff, understands every project, and can answer any question about your codebase instantly. We can finally focus on shipping instead of process.

Code ReviewMerge PRs faster and fix bugs before they show up in production

Never write a PR description again

Auto-generated summaries to guide reviewers.

Prevent Issues Automatically

High signal bug finding and fixing.

PR Descriptions

Streaming tokens #1738

Open

main

from

chenrui/ai-chat-stream

Streaming chatbot replies

Implements a request/response streaming pipeline for the AI assistant with retry + fallback:

Added ChatStreamHandler in backend/chat/stream.ts to stream tokens via SSE

Created fallback model selection that auto-switches to GPT-4o if GPT-5 fails

Updated Chat.tsx component to render incremental tokens with cursor animation

📍 Where to start:

Begin with backend/chat/stream.tswhich defines the ChatStreamHandler responsible for coordinating retries and fallbacks.

Rob

8:25 PM

@Macroscope What model do we use in our code review pipeline?

Macroscope

8:26 PM

Based on researching the codebase, multiple LLM models are used in concert within the code review pipeline. An initial pass is made using OpenAI's o4-mini-high, and for any detected correctness issues, an additional consensus step uses Anthropic's Opus 4 to reduce likelihood of false-positives.

Rob

8:27 PM

@Macroscope Why did we switch to JWTs?

Macroscope

8:28 PM

To unify and secure how credentials are validated across services.
The new system reduces surface area for token misuse, enables stateless auth flows, and simplifies auditing by embedding scopes and user IDs directly in the token.

AMAAsk Macroscope Anything in Slack

Slack

Set up in seconds

You don't have to do anything differently. Macroscope works with your tools automatically.

Connect GitHub

Once you install the GitHub app, Macroscope starts summarizing your commits & pull requests, automatically identifying projects, providing you productivity statistics, and doing code-review on PRs.

(<10s)

Connect Jira / Linear

Use Linear or JIRA? Macroscope can use context from your ticketing system to enrich its understanding of why work is happening and what's left. Don't use Linear or JIRA? No problem. Macroscope can still figure it out

(Optional)

Connect Slack

Ask anything in Slack, and get answers grounded in the code. Macroscope does deep-research across your entire codebase, the git log, and all the context of your PRs and Issue Tracking system to get you answers.

(Optional)

Security

Keeping your data secure is of paramount importance to us. We have rigorous technical, operational and contractual safeguards in place to protect customer data.