[{"data":1,"prerenderedAt":371},["ShallowReactive",2],{"doc-\u002Fdocs\u002Fresearch-workflows\u002Fliterature-review":3,"docs-nav":250},{"id":4,"title":5,"body":6,"description":16,"extension":243,"meta":244,"navigation":245,"path":246,"seo":247,"stem":248,"__hash__":249},"content\u002Fdocs\u002F3.research-workflows\u002F1.literature-review.md","Literature Review",{"type":7,"value":8,"toc":229},"minimark",[9,13,17,22,45,49,52,58,61,75,78,82,85,96,99,103,111,116,119,123,126,131,134,138,146,150,158,162,199,203],[10,11,5],"h1",{"id":12},"literature-review",[14,15,16],"p",{},"A literature review is a systematic survey of what's been published on a topic. This is the workflow Agent Bayes was built around — start broad, narrow systematically, capture landmark works and debates, and end up with a structured map you can actually write from.",[18,19,21],"h2",{"id":20},"before-you-start","Before you start",[23,24,25,39],"ul",{},[26,27,28,32,33,38],"li",{},[29,30,31],"strong",{},"Curate your KB first."," Retrieval quality dominates everything downstream. If your KB is missing the seminal papers, the review will be missing them too. Use ",[34,35,37],"a",{"href":36},"..\u002Fgetting-started\u002Fzotero-integration","Zotero"," to bring in your existing library, or upload PDFs directly.",[26,40,41,44],{},[29,42,43],{},"Pick a scope."," \"Late Bronze Age collapse\" is a workable topic; \"the ancient world\" is not. The agent does better when the first instruction has a defensible boundary.",[18,46,48],{"id":47},"step-1-establish-the-landscape","Step 1 — Establish the landscape",[14,50,51],{},"Start with one broad instruction. Don't pre-structure the mindmap; let the agent map out the territory.",[53,54,55],"blockquote",{},[14,56,57],{},"Build an overview of the main scholarly perspectives on the Late Bronze Age collapse. Include the leading proponents of each view and the kinds of evidence they rely on.",[14,59,60],{},"The agent runs broad discovery. You should expect, at the end of this first workflow:",[23,62,63,66,69,72],{},[26,64,65],{},"A root branch per major perspective or theme.",[26,67,68],{},"Each branch holding citation-backed claims summarizing that view.",[26,70,71],{},"Contradicting positions as sibling nodes — that's the system working as intended.",[26,73,74],{},"A textual summary describing what it covered and any gaps it noticed.",[14,76,77],{},"If the breadth feels off (too narrow, too wide), correct in the next instruction. Don't try to get it perfect in one shot.",[18,79,81],{"id":80},"step-2-audit-the-breadth","Step 2 — Audit the breadth",[14,83,84],{},"Before going deep, scan the top level of the map:",[23,86,87,90,93],{},[26,88,89],{},"Are all the major schools represented?",[26,91,92],{},"Are the citations weighted reasonably (no one paper dominating)?",[26,94,95],{},"Did the agent flag KB limitations? If so, that often means a foundational text isn't in your library — add it before going further.",[14,97,98],{},"This is the cheapest moment to add sources. Every later step gets better if the corpus is right now.",[18,100,102],{"id":101},"step-3-go-deep-one-branch-at-a-time","Step 3 — Go deep, one branch at a time",[14,104,105,106,110],{},"Select a branch and instruct the agent to expand it. Selection scopes the agent's ",[34,107,109],{"href":108},"..\u002Fworking-with-the-agent\u002Fagent-context","context"," to that subtree.",[53,112,113],{},[14,114,115],{},"Expand the systems-collapse view. Cover the supporting evidence, the main critics, and any recent revisions to the position.",[14,117,118],{},"Repeat for each branch you care about. Going branch-by-branch is significantly better than one mega-instruction — the agent's context stays focused, retrieval is more on-target, and you can review after each pass instead of after everything.",[18,120,122],{"id":121},"step-4-surface-debates-and-contradictions","Step 4 — Surface debates and contradictions",[14,124,125],{},"Once branches are populated, ask the agent to find friction:",[53,127,128],{},[14,129,130],{},"Across the current mindmap, identify the points where these perspectives directly contradict each other. Create sibling-node groupings under shared parent topics where the disagreement is sharp.",[14,132,133],{},"This restructures the map so disagreements are visible at a glance, instead of buried inside two unrelated branches.",[18,135,137],{"id":136},"step-5-find-whats-missing","Step 5 — Find what's missing",[14,139,140,141,145],{},"Use the ",[34,142,144],{"href":143},".\u002Fgap-finding","Gap Finding"," workflow as a follow-up: ask the agent to identify under-explored areas, weakly-supported claims, or open questions visible in the current map. This is where a review stops being a summary and starts being a contribution.",[18,147,149],{"id":148},"step-6-restructure-for-writing","Step 6 — Restructure for writing",[14,151,152,153,157],{},"When the content is settled, ask the agent to reorganize the map into a draft outline (see ",[34,154,156],{"href":155},".\u002Foutlining-a-paper","Outlining a Paper","). The Editor handles this without re-running retrieval — fast and cheap.",[18,159,161],{"id":160},"tips-that-pay-off","Tips that pay off",[23,163,164,170,193],{},[26,165,166,169],{},[29,167,168],{},"Don't dismiss low-confidence claims."," Inspect them. Low confidence often points to genuinely contested ground, which is exactly what a review should cover.",[26,171,172,175,176,180,181,180,184,187,188,192],{},[29,173,174],{},"Use labels"," like ",[177,178,179],"code",{},"primary-source",", ",[177,182,183],{},"review-paper",[177,185,186],{},"weak-methodology"," early. They make Step 4 and Step 5 much easier. See ",[34,189,191],{"href":190},"..\u002Fcore-concepts\u002Flabeled-items","Labeled Items",".",[26,194,195,198],{},[29,196,197],{},"Save your RAG queries"," for the searches you find yourself running by hand. The next person reviewing this topic (often: future you) will thank you.",[18,200,202],{"id":201},"whats-next","What's next",[23,204,205,212,219],{},[26,206,207,211],{},[34,208,210],{"href":209},".\u002Fhypothesis-generation-and-testing","Hypothesis Generation & Testing"," — once you know the landscape, propose your own claims.",[26,213,214,218],{},[34,215,217],{"href":216},".\u002Fthematic-analysis","Thematic Analysis"," — cluster what you found into themes.",[26,220,221,223,224,228],{},[34,222,144],{"href":143}," — what the literature ",[225,226,227],"em",{},"hasn't"," answered.",{"title":230,"searchDepth":231,"depth":231,"links":232},"",4,[233,235,236,237,238,239,240,241,242],{"id":20,"depth":234,"text":21},2,{"id":47,"depth":234,"text":48},{"id":80,"depth":234,"text":81},{"id":101,"depth":234,"text":102},{"id":121,"depth":234,"text":122},{"id":136,"depth":234,"text":137},{"id":148,"depth":234,"text":149},{"id":160,"depth":234,"text":161},{"id":201,"depth":234,"text":202},"md",{},true,"\u002Fdocs\u002Fresearch-workflows\u002Fliterature-review",{"title":5,"description":16},"docs\u002F3.research-workflows\u002F1.literature-review","Z_7PcrLlhyI8BK3-zodnrmbbBNXfNoBCP3_ogulCn4Y",[251,275,310,335,359],{"slug":252,"title":253,"items":254},"getting-started","Getting Started",[255,259,263,267,271],{"path":256,"title":257,"stem":258},"\u002Fdocs\u002Fgetting-started\u002Fintroduction","Introduction","docs\u002F1.getting-started\u002F1.introduction",{"path":260,"title":261,"stem":262},"\u002Fdocs\u002Fgetting-started\u002Fquickstart","Quickstart","docs\u002F1.getting-started\u002F2.quickstart",{"path":264,"title":265,"stem":266},"\u002Fdocs\u002Fgetting-started\u002Fthe-interface","The Interface","docs\u002F1.getting-started\u002F3.the-interface",{"path":268,"title":269,"stem":270},"\u002Fdocs\u002Fgetting-started\u002Fzotero-integration","Zotero Integration","docs\u002F1.getting-started\u002F4.zotero-integration",{"path":272,"title":273,"stem":274},"\u002Fdocs\u002Fgetting-started\u002Fcredits-and-billing","Credits & Billing","docs\u002F1.getting-started\u002F5.credits-and-billing",{"slug":276,"title":277,"items":278},"core-concepts","Core Concepts",[279,283,287,291,294,298,302,306],{"path":280,"title":281,"stem":282},"\u002Fdocs\u002Fcore-concepts\u002Fprojects","Projects","docs\u002F2.core-concepts\u002F1.projects",{"path":284,"title":285,"stem":286},"\u002Fdocs\u002Fcore-concepts\u002Fknowledge-bases","Knowledge Bases","docs\u002F2.core-concepts\u002F2.knowledge-bases",{"path":288,"title":289,"stem":290},"\u002Fdocs\u002Fcore-concepts\u002Frag-and-retrieval","RAG and Retrieval","docs\u002F2.core-concepts\u002F3.rag-and-retrieval",{"path":292,"title":191,"stem":293},"\u002Fdocs\u002Fcore-concepts\u002Flabeled-items","docs\u002F2.core-concepts\u002F4.labeled-items",{"path":295,"title":296,"stem":297},"\u002Fdocs\u002Fcore-concepts\u002Fmindmaps-nodes-and-claims","Mindmaps, Nodes & Claims","docs\u002F2.core-concepts\u002F5.mindmaps-nodes-and-claims",{"path":299,"title":300,"stem":301},"\u002Fdocs\u002Fcore-concepts\u002Fthe-multi-agent-system","The Multi-Agent System","docs\u002F2.core-concepts\u002F6.the-multi-agent-system",{"path":303,"title":304,"stem":305},"\u002Fdocs\u002Fcore-concepts\u002Fterminology-graph-explorer","Terminology Graph Explorer","docs\u002F2.core-concepts\u002F7.terminology-graph-explorer",{"path":307,"title":308,"stem":309},"\u002Fdocs\u002Fcore-concepts\u002Fai-verification","AI Verification","docs\u002F2.core-concepts\u002F8.ai-verification",{"slug":311,"title":312,"items":313},"research-workflows","Research Workflows",[314,315,318,321,325,329,332],{"path":246,"title":5,"stem":248},{"path":316,"title":210,"stem":317},"\u002Fdocs\u002Fresearch-workflows\u002Fhypothesis-generation-and-testing","docs\u002F3.research-workflows\u002F2.hypothesis-generation-and-testing",{"path":319,"title":217,"stem":320},"\u002Fdocs\u002Fresearch-workflows\u002Fthematic-analysis","docs\u002F3.research-workflows\u002F3.thematic-analysis",{"path":322,"title":323,"stem":324},"\u002Fdocs\u002Fresearch-workflows\u002Fcomparative-analysis","Comparative Analysis","docs\u002F3.research-workflows\u002F4.comparative-analysis",{"path":326,"title":327,"stem":328},"\u002Fdocs\u002Fresearch-workflows\u002Fnode-transformation","Node Transformation","docs\u002F3.research-workflows\u002F5.node-transformation",{"path":330,"title":156,"stem":331},"\u002Fdocs\u002Fresearch-workflows\u002Foutlining-a-paper","docs\u002F3.research-workflows\u002F6.outlining-a-paper",{"path":333,"title":144,"stem":334},"\u002Fdocs\u002Fresearch-workflows\u002Fgap-finding","docs\u002F3.research-workflows\u002F7.gap-finding",{"slug":336,"title":337,"items":338},"working-with-the-agent","Working With The Agent",[339,343,347,351,355],{"path":340,"title":341,"stem":342},"\u002Fdocs\u002Fworking-with-the-agent\u002Fwriting-instructions","Writing Instructions","docs\u002F4.working-with-the-agent\u002F1.writing-instructions",{"path":344,"title":345,"stem":346},"\u002Fdocs\u002Fworking-with-the-agent\u002Fagent-context","Agent Context","docs\u002F4.working-with-the-agent\u002F2.agent-context",{"path":348,"title":349,"stem":350},"\u002Fdocs\u002Fworking-with-the-agent\u002Fconversational-refinement","Conversational Refinement","docs\u002F4.working-with-the-agent\u002F3.conversational-refinement",{"path":352,"title":353,"stem":354},"\u002Fdocs\u002Fworking-with-the-agent\u002Fconfidence-gaps-and-iteration-limits","Confidence, Gaps & Iteration Limits","docs\u002F4.working-with-the-agent\u002F4.confidence-gaps-and-iteration-limits",{"path":356,"title":357,"stem":358},"\u002Fdocs\u002Fworking-with-the-agent\u002Fversion-history-and-provenance","Version History & Provenance","docs\u002F4.working-with-the-agent\u002F5.version-history-and-provenance",{"slug":360,"title":361,"items":362},"reference","Reference",[363,367],{"path":364,"title":365,"stem":366},"\u002Fdocs\u002Freference\u002Fsettings-and-api-keys","Settings & API Keys","docs\u002F5.reference\u002F1.settings-and-api-keys",{"path":368,"title":369,"stem":370},"\u002Fdocs\u002Freference\u002Ftroubleshooting-and-faq","Troubleshooting & FAQ","docs\u002F5.reference\u002F2.troubleshooting-and-faq",1780503376376]