Gregator is for people who want to actually learn things, not just get AI summaries. Enter a topic, and in a few minutes you get a multi-chapter course built from real sources — with credibility scores, inline citations, and an AI companion to discuss it all with.
Here is an actual chapter from a Gregator course. Each claim links to a source. Each source has a credibility score. You read it like an article, not a conversation.
Naked mRNA is inherently unstable in biological environments. Ribonucleases in the bloodstream degrade unprotected mRNA within minutes, making direct injection ineffective for most therapeutic applications.[1] The solution is encapsulation in lipid nanoparticles (LNPs) — roughly 80–100nm spheres composed of ionizable lipids, helper lipids, cholesterol, and PEG-lipid conjugates.[2]
LNPs are taken up by cells through receptor-mediated endocytosis. Once inside the endosome, the ionizable lipid component becomes positively charged in the acidic environment (pH ~5–6), destabilizing the endosomal membrane and releasing the mRNA cargo into the cytoplasm.[1][3] This is where ribosomes can translate the mRNA into the target protein — in the case of COVID-19 vaccines, the SARS-CoV-2 spike protein.
Despite their effectiveness, LNPs introduce practical constraints. The lipid formulation is sensitive to temperature — the BNT162b2 (Pfizer-BioNTech) vaccine originally required storage at -70°C, though reformulation improved this to standard refrigeration for shorter periods.[4]
You type a topic. Gregator runs a research pipeline and shows you progress in real time. When it finishes, you have a course you can read and discuss.
A question, a concept, a field. Gregator breaks it into chapters — typically 3 to 8 depending on complexity — and decides what angles each one needs.
For each chapter, Gregator queries academic databases, web search, and news in parallel. Sources are deduplicated, then each one is scored for credibility: evidence type, publication tier, and whether it contains marketing language.
Claims from the strongest sources are extracted and assembled into structured narratives. Every claim has an inline citation. Where evidence conflicts, Gregator flags it rather than hiding the disagreement.
You get a multi-chapter course you can read at your own pace. Open any source to see its full assessment. Chat with Greg to go deeper. Your progress is tracked from first encounter to mastery.
The course is the core. These features help you build on it — connecting topics, revisiting what you've learned, and staying current.
Greg is an AI chat partner loaded with your course context — the chapters, the sources, the specific claims. Ask follow-up questions and Greg answers from your research, not from general knowledge. When Greg cites something, you can click through to the original source and its credibility score.
As you research more topics, Gregator maps how they relate — prerequisites, contradictions, shared sources. Visual and list views.
Weekly recommendations based on your research history. Topics adjacent to what you've studied that you might not have found on your own.
Every source in your course has a panel like this. Source type (peer-reviewed, institutional, journalism, community), evidence quality, positive and negative signals, and any flags the scoring pipeline found — marketing language, missing citations, or single-source claims.
Academic databases, web search, and news are queried in parallel for each chapter. Results are deduplicated and ranked before synthesis begins.
Greg is loaded with your course context — the chapters, sources, and claims from your research. When you ask a question, Greg answers from that material and cites the specific sources. You can click any citation to see the full source assessment.
"I used to spend hours opening tabs, evaluating sources, and trying to piece together what the consensus actually was. Gregator does that in minutes and shows me exactly which claims are well-supported and which aren't. It changed how I prepare for deep-dive presentations."
AI makes it easy to get answers. It doesn't make it easy to understand. Gregator is built to close that gap.
No engagement loops, no algorithmic feeds, no time-on-site metrics. Gregator succeeds when you learn something and leave.
Gregator builds interpretations grounded in sources — and when evidence conflicts or a source has weak backing, it tells you. You see where confidence is high and where it isn't.
Click any citation to see the source, its credibility tier, and what the scoring found. Nothing is hidden behind a "trust me."
Gregator uses AI to synthesize sources, so the usual caveats apply — it can misinterpret or oversimplify. The difference is that every claim has a visible citation you can click to read the original source and see how it was scored. If something looks off, you can check immediately. That's the point.
Sources are gathered live when you submit a topic. The pipeline queries current web and academic databases. Courses are not pre-built — they are generated on demand. You can also re-run research on any topic to get updated sources.
Gregator flags it. You'll see "Mixed evidence" insight cards in the chapter text explaining what the disagreement is, which sources support each side, and what the evidence quality looks like for each. It doesn't paper over conflicts.
Each source is categorized by type (peer-reviewed, institutional, journalism, community), then scored across several signals: whether claims are quantitatively backed, whether multiple independent sources corroborate key findings, and whether promotional or marketing language is present. The full breakdown is visible on every source.
Typically 2–4 minutes depending on topic complexity and how many sources need to be analyzed. You can watch the pipeline run in real time. Each stage has a progress indicator, and chapters appear as they are completed.
Standard Greg uses a capable but smaller language model — good for follow-up questions and basic discussion. Advanced Greg (Pro and above) uses a larger model that gives more nuanced answers, handles longer conversations, and is better at synthesizing information across multiple chapters.
All plans include the full research pipeline with source scoring. Higher tiers give you longer courses, better AI models, and tools for ongoing learning.
Your first 5 courses are free. No credit card needed.