Macroscope

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!

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

Curious how Macroscope's new Agent works? Ivan Gomez walks through some of his favorite workflows below ⬇️

Ask Macroscope Anything is now Macroscope Agent. What started as a codebase chatbot now connects to your production stack, reacts to events in your workflow, and can be triggered via API. What we shipped today: 🔌 New integrations and capabilities - Sentry, Amplitude, GCP Cloud Logging, GitHub API, image generation, and MCP connections - Agent can now query error tracking, product analytics, production logs, and any MCP-compatible tool alongside your codebase, Slack, Linear, Jira, and the rest ⚡ Event-driven automations - Macros are now able to: - Trigger on new commits and pull requests with full context about what changed - Filter by repository and branch - Deliver results to Slack channels, Slack threads, or webhook URLs 🔗 Agent API - Trigger Agent programmatically from any system - Send a POST with a query and a destination > Agent runs asynchronously and delivers the response to Slack or a webhook - CI pipelines, incident tooling, and internal apps can all use it How teams are using it: 🎫 Customer support triage: Bug filed in Pylon. Agent root-causes it, drafts a fix PR, and writes a response. 🔍 Production health sweeps: Morning macro queries logs, clusters errors, opens PRs for the top issues. 🛠 Sentry autofix: Error alert hits Slack. Agent reads the stack trace, finds the bug, pushes a fix. Available now for all Macroscope customers. Details in the comments.

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 In order to better align our model - we’re shifting to usage-based pricing across our core features:   → Code Review: $0.05 per KB of diff reviewed (10KB min/review)    → Status: $0.05 per commit processed   → Agent: Included with Status at no additional cost Based on recent historical data across our customers, with this pricing model:   → Average cost per review across all customers: $0.95   → Over half of all reviews cost just $0.50 We believe this approach is fair (you pay for what you control), aligned (your costs scale along with the quantity of work we do) and future-proof (works for agent code and human code alike). Usage based pricing 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. Read more about how it works in the link below ⬇️

On Martian's independent Code Review benchmark, Macroscope ranks #5 overall on f1 score (a metric that balances precision and recall) and higher than formidable competitors we respect like Cursor BugBot, Devin, Greptile, CodeRabbit, and Claude Code Reviewer. Also, fun fact: we 🫶 Claude Code but PSA...why pay $25 per review with Claude Code Reviewer (according to their own estimates) when you can pay an order of magnitude less for better performance (according to an independent benchmark) with Macroscope 😄

I realize bragging about a product you work on is a bit taboo, but I absolutely have to brag on Macroscope for a second. I’m out getting some car service done. My CEO noticed a bug in an upcoming feature branch. While out via slack, I had Macroscope start a PR that needed to target that specific feature branch. I failed to mention the branch name in my prompt. Without that context, one would assume the change would need to compare against our main branch. But Macroscope contextually just got it right, correctly found the issue, fixed the bug, and targeted the correct branch. I think that’s actually pretty amazing. I can’t emphasize how awesome that is to have all that done without the necessary context all while I’m sitting in a lobby at the car shop. #Macroscope

Today we released Macroscope Code Review v3. We believe two things matter for great code review: catching bugs that would cause major harm in production, and not wasting developer time with noise. v3 delivers this. Read more below.