[{"data":1,"prerenderedAt":221},["ShallowReactive",2],{"blog-posts":3},[4],{"id":5,"title":6,"author":7,"authorAvatar":8,"authorBio":9,"authorRole":10,"body":11,"cover":205,"coverDark":206,"date":207,"description":208,"draft":209,"extension":210,"meta":211,"navigation":212,"path":213,"seo":214,"stem":215,"tags":216,"video":219,"__hash__":220},"blog\u002Fblog\u002F1.introducing-agent-bayes.md","Introducing Agent Bayes: research you can actually trust","Meir Zana","\u002Fblog\u002Fimg\u002Fmeirz.webp","We are researchers and engineers building tools that help people reason over large bodies of literature without losing the thread back to the source.","Founder",{"type":12,"value":13,"toc":192},"minimark",[14,18,21,24,29,32,39,45,51,55,58,61,64,68,71,74,77,80,83,87,90,93,96,100,103,106,109,113,159,163,166,170,184],[15,16,17],"p",{},"Reading is the easy part. The hard part is holding fifty papers in your head at once: which ones agree, which ones contradict each other, where the evidence is thin, and exactly which sentence in which PDF backs the claim you are about to make. That work does not scale with effort. It scales with the number of sources, and at some point a literature review stops being a reading task and becomes a memory problem.",[15,19,20],{},"The tools meant to help have mostly made this worse. A general chatbot will happily summarize a paper it has never read, invent a citation that looks plausible, and forget the whole conversation the moment you close the tab. You get fluent text with no thread back to the evidence. For casual questions that is fine. For research, an unverifiable claim is worse than no claim at all.",[15,22,23],{},"We built Agent Bayes to close that gap. It is a multi-agent AI research assistant built around a shared, interactive mindmap, where every substantive claim is backed by a citation from your own library that you can open and check.",[25,26,28],"h2",{"id":27},"the-problem-with-chatting-your-way-through-literature","The problem with chatting your way through literature",[15,30,31],{},"Most AI research tools are a chat window bolted onto a language model. That design carries three failures that matter enormously when you are doing serious work.",[15,33,34,38],{},[35,36,37],"strong",{},"They hallucinate sources."," A model optimized to provide answers quickly will produce inaccurate citations that are not easily verifiable. It reads sources, summarizes them, and loses the nuances. You cannot tell the difference from the text alone, so you end up re-verifying everything by hand, which consumes much more time and creates frustration when you find out something is wrong after the fact.",[15,40,41,44],{},[35,42,43],{},"They forget."," A chat thread is a transcript, not a workspace. There is no durable structure that accumulates as you work. There's no way to manage numerous follow-ups or trim what's not needed. You end up pasting context you kept in external tools and hope the model will align with where you left off.",[15,46,47,50],{},[35,48,49],{},"They flatten disagreement."," When summarizing a contested topic, existing tools tend to average the views into a single confident paragraph. But the disagreement is the most important part of the literature. Smoothing it away hides exactly what a researcher needs to see.",[25,52,54],{"id":53},"research-needs-a-structure-you-can-see","Research needs a structure you can see",[15,56,57],{},"Think about how a coding agent works on a real project. It does not operate on one long chat. It works against a codebase: a tree of files and modules, organized so that any part can be found, changed, and reasoned about on its own. That structure is what keeps the work tractable. Take it away, and even a capable agent loses the plot.",[15,59,60],{},"Research is no different. A literature review is not a flat list of summaries. It is a hierarchy: themes split into sub-themes, claims supported by evidence, positions answered by counter-positions. That structure is the actual product of synthesis. A wall of prose hides it, and a chat log destroys it.",[15,62,63],{},"A mindmap makes the hierarchy visible, and seeing it is what lets you act on it. You take in the shape of the argument at a glance: which branches run deep and which are thin, where two lines of evidence converge, which question still has no answer. You spot the gap because you can see the empty branch. You cut the tangent because you can watch it sprawling. You reorganize because the structure is in front of you instead of buried in paragraphs you did not ask for and in notes you maintain and have to re-read and edit constantly in order to navigate and make progress.",[25,65,67],{"id":66},"where-deep-research-gets-you-halfway","Where \"deep research\" gets you halfway",[15,69,70],{},"\"Deep Research\" tools get closer to this than a plain chatbot. They work in two passes: a broad sweep to map out the aspects of a question, then a deeper dive into each one. That first pass is, in effect, a tree, with the aspects as branches. A mind map is simply that tree made explicit and kept around.",[15,72,73],{},"The trouble is what happens next. Say the broad pass surfaces eight aspects and writes a long report covering all of them. Maybe three are genuinely interesting. You have paid for the other five in tokens and reading time, and now you want to go deeper on the three that matter. What are your options?",[15,75,76],{},"You can ask follow-ups in the same conversation, but as the research grows, the thread becomes impossible to track. Each new answer pushes the earlier structure further out of view, and nothing accumulates into a workspace you can navigate.",[15,78,79],{},"Or you can run a fresh deep research pass on each of the three aspects. Now you have three more reports, each with its own structure, none of them connected to the others. You are back to stitching documents together by hand. What you end up with is a pile of notes, citations you never verified pointing at sources you never opened, and claims flattened down to \"this is roughly the spirit of this paper\" rather than what the paper actually says. That is how you get academic slop, and it is a large part of why many researchers are wary of AI in serious work.",[15,81,82],{},"Agent Bayes is built so that the tree is the workspace itself, not a byproduct you throw away once the report is written. It stays around so you can expand or trim any branch, reorganize, rephrase, and edit in place as your understanding changes. And it treats provenance as the point, not an afterthought, which is what the next section is about.",[25,84,86],{"id":85},"a-mindmap-not-a-chat-log","A mindmap, not a chat log",[15,88,89],{},"Agent Bayes replaces the chat transcript with a persistent mind map. The mind map is the single source of truth for your research, and it grows and reorganizes as you work rather than scrolling away.",[15,91,92],{},"You bring a library of papers, uploaded as PDFs or synced from Zotero, and your instructions initiate a multi-agent pipeline that retrieves the relevant passages from your sources, synthesizes citation-backed claims, and writes them into the map as structured nodes. You direct every step, and the work stays yours.",[15,94,95],{},"Because the result is a structure rather than a wall of text, you can expand a branch, dive deeper, restructure an argument, reorganize nodes into chapters, or ask for a prose synthesis when you are ready to write. The mind map is something you build on, not a message you scroll past.",[25,97,99],{"id":98},"every-claim-traces-back-to-a-source","Every claim traces back to a source",[15,101,102],{},"This is the part we care about most. When the agent writes a claim, it does not just name a paper. It pins the claim to the exact passage it drew from, down to the specific page, and gives you a link straight to that spot in the source so you can read it in context. We have put a great deal of effort into reaching this level of provenance, because a citation you cannot check is not really a citation. The system does not fabricate sources, and it will tell you when the evidence is not there rather than filling the gap with confident prose.",[15,104,105],{},"When sources disagree, Agent Bayes preserves the disagreement. Contradicting viewpoints become sibling nodes in the map instead of being averaged into a false consensus. You see the shape of the debate, not a flattened summary of it.",[15,107,108],{},"You can also work without the agent at all. Search your library semantically, in English even when the papers are in other languages, and attach citations to nodes you wrote yourself. When you do, the agent can score how well your wording matches the cited passage and suggest a rewrite where the phrasing overstates the evidence.",[25,110,112],{"id":111},"what-you-get-out-of-it","What you get out of it",[114,115,116,123,129,135,141,147,153],"ul",{},[117,118,119,122],"li",{},[35,120,121],{},"Provenance you can check."," Every claim is pinned to the exact passage and page it came from, with a direct link to the source. No invented citations, no unverifiable summaries.",[117,124,125,128],{},[35,126,127],{},"A structure you can see."," Your research lives as a visible hierarchy you can navigate, expand, prune, and reorganize, instead of a transcript you scroll.",[117,130,131,134],{},[35,132,133],{},"Work that compounds."," The mindmap persists and accumulates across sessions, so your research builds on itself instead of resetting every time you start a new chat.",[117,136,137,140],{},[35,138,139],{},"Disagreement preserved."," Competing views are kept as distinct nodes, so the structure of a debate stays visible instead of being smoothed away.",[117,142,143,146],{},[35,144,145],{},"You stay in control."," You direct the research, approve the structure, and write your own claims. The agent retrieves and drafts, you decide.",[117,148,149,152],{},[35,150,151],{},"A library that answers back."," Semantic search across your whole corpus, across languages, with citations you can attach yourself.",[117,154,155,158],{},[35,156,157],{},"Fast enough to stay in flow."," Typical workflows complete in 90 to 180 seconds, streaming updates into the map as they happen.",[25,160,162],{"id":161},"who-this-is-for","Who this is for",[15,164,165],{},"Agent Bayes is built for people who work with bodies of literature and need to stand behind what they write: master's and PhD students, postdocs, researchers, analysts, and writers.",[25,167,169],{"id":168},"getting-started","Getting started",[15,171,172,173,178,179,183],{},"The fastest way to understand Agent Bayes is to point it at a few papers and watch a mindmap take shape. Start with the ",[174,175,177],"a",{"href":176},"\u002Fdocs\u002Fgetting-started\u002Fquickstart","Quickstart"," to get your first map going in a few minutes, or read the ",[174,180,182],{"href":181},"\u002Fdocs\u002Fgetting-started\u002Fintroduction","Introduction"," for the full tour.",[15,185,186,187,191],{},"We are just getting started, and we would love your feedback. If you want access, ",[174,188,190],{"href":189},"\u002F#waitlist","join the waiting list"," and tell us what you are researching.",{"title":193,"searchDepth":194,"depth":194,"links":195},"",4,[196,198,199,200,201,202,203,204],{"id":27,"depth":197,"text":28},2,{"id":53,"depth":197,"text":54},{"id":66,"depth":197,"text":67},{"id":85,"depth":197,"text":86},{"id":98,"depth":197,"text":99},{"id":111,"depth":197,"text":112},{"id":161,"depth":197,"text":162},{"id":168,"depth":197,"text":169},"\u002Fhero-screenshot-light.webp","\u002Fhero-screenshot-dark.webp","2026-06-11","Why we built a multi-agent research assistant around a shared, citation-backed mindmap, and how it fixes what generic chatbots get wrong about working with literature.",false,"md",{},true,"\u002Fblog\u002Fintroducing-agent-bayes",{"title":6,"description":208},"blog\u002F1.introducing-agent-bayes",[217,218],"Announcements","Product",null,"DUkzN4tGuZlIqR0BwWJVIKZmP_Zx16ZgkwYudhVJMDg",1782903349019]