Screening
- Dual review screening that supports multiple reviewers or Elicit as a reviewer
- Title, abstract, and full-text screening
- Exclusion reasons and quotes for all screening decisions
Extraction
- Results extracted from both text and figures
- Up to 40,000 papers extracted per review When we launched the upgraded Elicit systematic review last month, we talked a lot about speed. Under the hood, here are the key features doing the actual work:
Search
- Boolean and MeSH keyword queries alongside high-recall semantic search
- Autotranslate between keyword and semantic search 
checked in at @atproto.nyc - June 2026 [pevhrcgc] #atprotonyc abundance (2025) klein, thompson
Are you ready?! 
Oh...and we launched a new website (what up .com!), clarified our license with the new Open Innovation Grant, and completely revamped our documentation today too.
Read more: directus.com/resources/v... An improved content editing experience. Native draft and publishing workflows built into the core.
AI-assisted translations. Scale across languages with schema scaffolding handled for you.
Granular access control for AI. Agents act on behalf of real users with the right permissions applied. Most backends are built for developers.
But the rest of the team is building, too.
Directus v12 is out today. A major upgrade built around one idea: the whole team should be able to work on the same backend without getting in each other's way.
Here's what shipped: 
Day 1/30. ☀️
A Sunday school teacher asked. Our CTO Dana Lawson delivered.
VerseBars picks a random Bible verse, writes it into a rap, and performs it over a beat synthesized live in your browser. Built and shipped today on Netlify.
Try it 👉 biblebeats.netlify.app #HotAppSummer 
We're working to improve the Mermaid diagram experience in Zed. This week's stable will feature faster and more accurate rendering. More improvements are coming.
Links to both advisories:
◇ github.com/vitejs/launc...
◇ github.com/vitejs/vite/... We've published two Windows-related security advisories: ◇ If Vite runs with `--host`, denied files may have been reachable over the network. ◇ launch-editor with NTLM enabled may leak NTLMv2 hashes via a malicious page. Update to Vite 8.0.16/7.3.5/6.4.3, Vite+ 0.1.24, and launch-editor 2.14.1.
Zed Office Hours is back! 🛠️
@conradirwin will be reviewing PRs live on Thursday, June 4 at 12pm ET / 9am PT. Watch how the team thinks about reviews and what gets merged.
luma.com/4tulj8sd every day, we stray further, etc
Put differently: specs as code
This could look something like "literate TypeScript". A mixture of TypeScript, Markdown and React. Think Jupyter Notebooks but modern and embracing web technologies. Still early days but I'm already working towards this spec-driven vision.
I'm slowly but surely forming a better idea how to do "better specs". The key idea is to make them structured and allowing a spec to contain structured source of truth definitions and rich artifacts such as code-defined diagrams, API/CLI/schema definitions, etc.
Tomorrow Command Code will drop one of the best deals ever.
Noon 12pm pacific. Guess and it's yours for free. 
Tomorrow Command Code drops one of the best deals ever.
Noon 12pm pacific. Can't wait to share. 
This is getting ridiculous!
MiMo V2.5 is up to 99% off on Command Code.
Let's get it! 
we're growing too, hiring in sf and remote worldwide.
check open roles on my profile bio on X. if you like engineering deep dives on how we're doing all this, i've linked some relevant posts below. try it now.
npm i -g command-code we're going open source next month. today we're a cli at the core, and we're also launching a full-fledged gui app, sandboxed background agents, and cooking up something fun i can't wait to share.