(1/5) After months of research and iteration, I couldn’t be more excited to announce, our SOTA memory system - Rune, built for our use case of long multi-turn, personal conversations that evolve into relationships.
There’s been a lot of chatter around memory systems but for us, the problem wasn’t just reducing context bloat, it was about our agents delivering a truly human-like experience.
Humans are special and the human memory system was our benchmark; We remember important things no matter if they are recent or not. We don't always have recency bias. If someone tells you they had a bad breakup, and months later they hesitate about dating again you understand why, without being told. We somehow know what’s important and what’s not. We know how to connect the dots.
Rune is our attempt to get there. A memory system built not just to store conversations — but to preserve context, continuity, and meaning across time. Built for Vaya, by Anuvaya.
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.
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.
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
You can now create PRs directly from Slack with Macroscope.
Customer reported a bug via screenshot? Just @ tag Macroscope → 👀 it reads the Slack thread → 📄 parses any attachments → ✅ creates a PR fixing the bug
Great consumer products start with a deep understanding of humans.
Ive always been obsessed with the ‘why’ behind human choices. This piece captures it beautifully.
Maahin’s insights and first principle thinking is always intriguing.
How we did it: an agentic approach combined with "auto-tune” – a system we built that uses LLMs to automatically find the best-performing prompt, model, and language combination.
Learn more in our technical deep dive: https://t.co/6wXONb1q1V
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 ...
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.
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.
Don't drop out of college to start or work for a startup. There will be other (and probably better) startup opportunities, but you can't get your college years back.
Introducing July — your AI talent coordinator.
July automates back office workflows for talent managers, including analytics, CRM, and payments tasks.
No more spreadsheets or screenshots. Just smarter, faster talent management.