A systematic review is only as good as the studies it did not miss. An AI screener tuned for speed is the wrong tool; one tuned for recall, with humans deciding, is a useful one.
All Universities & Research Institutes →
AI for systematic reviews ranks and pre-screens titles and abstracts against your eligibility criteria, then extracts study characteristics and outcomes from included full texts into your extraction form, with every value linked to the page it came from. Reviewers keep making the inclusion decisions, and the system records each one so the PRISMA 2020 flow diagram and the audit trail write themselves.
It works alongside the tools reviewers already use, such as Covidence, Rayyan or EPPI-Reviewer, by importing and exporting in their formats, or as a standalone pipeline for a library or evidence-synthesis unit that runs many reviews.
deduplicated across databases
likely includes ranked first
dual review, conflicts resolved
values linked to source pages
flow diagram and audit trail
always to a human, never auto-excluded
The best one for a given review is the one whose recall you have measured on your own topic. Screening tools differ less than their marketing suggests; what matters is how they are used, with a validated stopping rule, dual human review and a full record of decisions. We build pipelines that make that measurement part of the process.
It can do much of the mechanical work: deduplicating, prioritising screening, extracting data and drafting the PRISMA record. It cannot replace the review team’s judgement on eligibility edge cases, risk of bias or certainty of evidence, and most methodological guidance still expects human reviewers to make those decisions and be named for them.
Put AI where the hours are and the judgement is lightest: deduplication, screening prioritisation and data extraction with source links. Keep humans on inclusion decisions, conflicts and quality appraisal. Measure recall on a labelled sample before relying on any automated ranking, and log every decision so the review stays reproducible.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Bring a completed review. We will measure what a screener would have caught, and what it would have missed.
30-minute technical call · no deck