AI should help researchers think deeper, not think less

The wrong question is whether AI can replace researchers. The useful question is whether it can help a researcher stay with a hard problem long enough to understand it.

That distinction sounds philosophical until you start designing the tool. Then it becomes a product requirement, which is the least romantic form a philosophy can take.

If the goal is replacement, the interface tends toward a button that produces an answer. If the goal is augmentation, the interface has to preserve the parts of research that make knowledge defensible: sources, uncertainty, disagreement, history, revision, and the human decision about what matters.

This fork is being argued well beyond research software. Harvard Business Review recently made the case that companies choosing augmentation over automation may win in the long run. I think research is where the argument is easiest to settle.

We built Agent Bayes around the second idea, not as a line in a manifesto after the fact but at the requirements and design level. The product is not trying to make research feel like ordering a report from a model. It is trying to help a person build a structure they can inspect, challenge, and keep improving.

The scarce resource is not text, it is sustained attention

LLMs made text cheap. That is useful, but it also distorts the conversation around research tools.

Most serious research problems are not blocked because no one can produce another paragraph. They are blocked because the researcher has to hold too many partially connected things in mind (usually across forty Zotero tabs!) at once: which papers agree, which ones only appear to agree, which claims are strongly supported, which ones depend on definitions, where the evidence ends, and which open question is actually worth another week.

When you as a researcher have a deep understanding of a subject, you can see where everything fits. You can see the contradictions, the gaps, the historical context, and the methodological shortcomings. Only then you can come up with a novel interpretation, challenge a consensus, or propose a new experiment. That is the work that makes research worth doing.

It is not glamorous. It often happens between sessions with a tool, while walking, rereading a passage, sketching a structure, throwing away a neat idea because a source does not support it, or realizing that two literatures use the same word to mean different things.

AI can speed up the entry into that state. It can surface relevant passages, provide background when you enter a field, translate across terminology, identify likely gaps, and suggest angles you might have missed.

But it cannot do the human part for you. It cannot sit with a problem for days, months, or years. It cannot feel when a theory is too neat, recognize the social and historical texture behind an argument, or decide which distinction matters morally, methodologically, or interpretively. In fields like history, archaeology, anthropology, sociology, psychology, and political thought, that human layer is not decoration. It is part of the subject.

Mohamed Mannaa, recently described the strange loop that forms when reviewers use AI to draft their reports and authors use AI to draft the responses. The work still looks human-led, but the thinking has been quietly outsourced on both sides. His warning is the same as ours from the other direction: the danger is not that AI produces text, it is that the person stops doing the part that made the text worth producing.

On the other hand, the body of research literature is growing faster than any one person can read. Researchers find themselves in a situation where they must use AI to keep up, but they expose themselves to the risk of blindly trusting a model that does not understand the stakes.

The best research tools should therefore make the human researchers more capable, accelerating their ability to keep the evidence visible, the disagreements legible, and the gaps clear. They should make it easier to think deeper, not think less.

Quality beats quantity

A bad research assistant gives you more. More summaries, more bullets, more plausible claims, more citations to verify yourself later. Spitting out more text than the U.S. Treasury prints dollars.

A good one generates claims that are scoped by the evidence, and scored by confidence. It provides accurate provenance for every citation it uses, that you can inspect in context.

Recent work on citation hallucination and verification is moving in this direction. Papers such as HalluCiteChecker, SemanticCite, and audits of LLM citation behavior such as How LLMs Cite and Why It Matters all circle the same practical problem: generated academic text can sound finished before it is epistemically earned.

That is why "quality over quantity" cannot be a vague preference. In a research workspace, it has to become a set of constraints:

• A claim should point to the passage that supports it.
• A citation should be inspectable, not decorative.
• A source disagreement should remain visible.
• A corpus limitation should be reported, not papered over.

These constraints slow the system down in small ways. They are worth it. Fast wrong answers are not a productivity improvement for work you will later have to defend in a seminar, peer review, policy memo, dissertation committee, or your own conscience. Reviewer 2 has never once been persuaded by the argument that the model sounded confident.

Research is not only retrieval

The most tempting product fantasy is that research becomes a better search problem. Put the right papers in, ask the right question, retrieve the right chunks, and let the model synthesize.

Retrieval matters enormously. If the relevant evidence never reaches the model, the rest of the system is theater.

But retrieval is not enough, because research is not merely locating information. It is building an interpretation under constraint.

One paper states a conclusion. Another reports that conclusion as a view held by others, then spends the next ten pages attacking it. A third uses the same term in a narrower population. A fourth has a null result that matters precisely because the literature expected otherwise. A fifth is old, methodologically limited, and still historically important because everyone else is responding to it.

These distinctions are easy to destroy in a fluent synthesis. A model can turn a contested field into a paragraph that sounds balanced and is wrong about the shape of the debate.

That is why the intermediate representation matters. If everything becomes prose too early, the researcher loses the ability to see what happened to the evidence. If the system first represents claims, citations, conflicts, and gaps as separate objects, the researcher can intervene before prose smooths the edges away.

The tool should preserve the researcher, not hide them

There is a subtle failure mode in AI research products: they make the user feel productive while moving the actual reasoning somewhere opaque.

You ask and it answers. You ask again and it answers again. The transcript grows, but your model of the field does not necessarily become more inspectable. You may feel momentum, but the work is still trapped in a conversation that is hard to reorganize, audit, or build from. The insight you need is in there somewhere, roughly a few screens up, just past the model's third "You are right" apology.

The experience we want is different.

You start with a question and a library of sources. The tool helps map what the sources say into a visible structure. You expand a branch because it looks thin. You collapse another because it is a tangent. You open the exact page behind a claim and decide the wording is too strong. You split one node into two because the citation supports the method but not the conclusion. You keep two contradictory explanations next to each other because the disagreement is not a problem to fix yet. It is the thing you are trying to understand.

The point is not that the agent is always right. The point is that its work is legible enough for you to dwell on it, challenge it, and improve it. The point is that the researcher remains the owner of the knowledge being built.

This is also why editing matters. A research system that only generates is asking the user to accept or reject whole artifacts. Perla Khattar calls this failure symbolic approval: when a person is asked to sign off on work they had no hand in shaping, oversight becomes a ritual and accountability quietly drains away. A research system that lets the user revise claims, move nodes, attach citations manually, verify wording against passages, and restore previous versions treats the researcher as the owner of the knowledge being built.

We encoded this philosophy as requirements

Agent Bayes is built around a mindmap because a durable structure gives the researcher something to think with. The map is not a visualization slapped on top of chat. It is the primary artifact.

At the requirements level, that decision shaped the system:

• Every substantive claim in the mindmap needs citation provenance back to the user's library.
• Citations are tied to passages and pages, so the researcher can inspect the evidence in context.
• Inspecting is easy: the user can click a claim and see the relevant passage, or opens the original source document to read the surrounding text using a built-in PDF viewer.
• Contradicting viewpoints are represented as sibling nodes rather than averaged into one consensus paragraph.
• The system distinguishes retrievable gaps from knowledge-base limitations.
• Agent workflows are bounded to a maximum of three refinement loops, so the tool cannot disappear into uncontrolled self-improvement while consuming time and credits.
• The mindmap has version history, undo and redo, and provenance for agent and human edits, because research is iterative and should be easily auditable and inspectable with a built-in diff viewer.
• The user can search the corpus directly and attach citations manually, because not every act of research should require an autonomous agent run.

Those are product choices, but they are also philosophical choices. They say the researcher remains responsible for interpretation, and the system should make that responsibility easier to carry.

Using the tool should feel like building, not receiving

From the user's side, the important moment is not "the AI gave me an answer." It is "I can now see the structure of what I know."

A mindmap that is easily editable, allows you to reorganize nodes, create abstraction layers, and shape the information in a way that forms understanding.

Imagine you are entering a new field. You have a Zotero library, a rough question, and the uncomfortable sense that everyone else already knows the debate you are trying to reconstruct. You ask Agent Bayes to map the major positions in your sources.

The first result is not the final literature review. It is a scaffold. You see branches for methods, concepts, competing explanations, and open questions.

Now the work begins.

You tell the agent to deepen one branch, but not the whole map. You use semantic search manually for a phrase from a paper you remember. You attach a passage as evidence. You label a set of citations because they might become a section later. You reorganize the map into the shape of an argument. The tool has accelerated you, but it has not replaced your thinking.

The honest limitation: AI does not understand why you care

There are domains where the most important thing is not only what the sources say, but why the question matters to people.

Historical actors had incentives, fears, social positions, blind spots, and vocabularies that do not map cleanly onto contemporary categories. Psychological and sociological claims are often entangled with measurement choices, cultural assumptions, and ethical stakes. Archaeological interpretation can turn on material context that is easy to flatten into a clean explanation. Political writing may be strategic, ironic, defensive, or constrained by the institutions around it.

An AI system can help retrieve, compare, translate, summarize, and challenge. It can surface patterns faster than a person working alone. But it does not have a lived relationship to the question. It does not know why a distinction feels morally loaded, why a silence in an archive matters, or why a claim that looks minor changes the interpretation of a whole field.

It is a reason to design tools that keep the human close to the evidence.

The future of research tools is not autopilot

The next generation of research tooling should not be measured by how much text it can produce while the user looks on his phone.

It should be measured by whether it helps a serious person think with more context, more precision, and more courage. Can it help you notice that your library does not support a claim you wanted to make? Can it keep a disagreement visible instead of resolving it cosmetically? Can it make your own revisions part of the artifact rather than a private layer outside the system? Can it help you return to a problem after a week and continue from a structure that still makes sense?

That is the bet behind Agent Bayes.

AI should make it easier to enter a field, find evidence, see gaps, and generate possibilities. It should also make it harder to hide from the sources, harder to confuse fluency with understanding, and harder to forget that knowledge is something humans build over time.