Kyanos · Paper II · Research Note · August 2026 · Revision 2 · 11 August 2026

Legible to Both:
AI Presence Optimization and the Psychology of Persuasion

A short brief for campaigns and advocacy organizations: what answer engines actually measure on your pages, why the same gaps lose you human readers, and what to do about it. The research is in the notes.

Abstract. Making a candidate's website legible to answer engines is usually pitched as a technical chore. It is mostly an editorial one, and the editing it forces is the same editing that helps a voter who gives your page nine seconds. Vague positions, a subject named four different ways, claims with no evidence under them — those are the failures answer engines penalize, and decades of research on how people read and are persuaded says they cost you with human readers too. This brief summarizes that research and what it implies for a campaign or an advocacy organization. It does not claim that fixing them wins votes; that experiment has not been run.
↑ Contents 01 · The Test

If the machine can't tell,
neither can the voter

Ask an answer engine what your candidate thinks about housing. If it hedges, or answers about somebody else, or gives you a sentence that could describe any Democrat in the country, the usual reaction is that the technology failed.

Try the same thing with a person. Hand a stranger your candidate's website and give them nine seconds — roughly what a voter gives it — then ask what your candidate would do about housing. You will often get the same hedge.

That is the argument of this brief. The things that make a page hard for an answer engine to read are, with few exceptions, the things that make it hard for a distracted human to read. Not because the two are alike — they are not — but because both are working under a hard limit on how much they can hold at once, and both are handling prose that never quite says the thing.

"The question is not how do I write for AI. The question is what it means that AI cannot find my candidate's positions on my candidate's own website."

This is worth stating plainly because it changes who owns the work. If AI legibility is a technical problem, it belongs to whoever manages the website. If it is an editorial problem, it belongs to the communications director, and it is the same problem they already have.

↑ Contents 02 · The Four Things Measured

Four dimensions,
in plain terms

Kyanos scores answer-engine responses on four dimensions. They are worth knowing precisely, because each one names a specific way a page fails.

What gets scored
Factual accuracy

Whether what the engine says about you is true. Wrong positions, wrong biography, endorsements you never received. This measures the information environment around you rather than your own copy — which is why some of it is not yours to fix directly.

What gets scored
Subject clarity

Whether the engine can tell who you are. Failure looks like a state senator merged with a U.S. senator of the same name, or accurate facts about an organization that is not yours.

What gets scored
Position explicitness

Whether your positions are stated as commitments rather than implied through affiliation or atmosphere. "Supports environmental protection" fails when there is a documented vote you could have named instead.

What gets scored
Factual density

Whether the claims have evidence underneath them, or are high-sounding language with nothing to check.

Three of those four are entirely within your control. They are written by your staff, on your website, and could be changed this week.

↑ Contents 03 · Why It Costs You People

The same gaps,
the same losses

Each of those failures has a matching literature in psychology and communication research. The detail is in the notes; the short version follows.

Naming the subject four different ways makes the reader do your work. A page that says "she," then "the senator," then "the Congresswoman," costs an attentive human almost nothing. But every small resolution adds up, and the capacity it consumes is capacity not spent on your argument.1 Precise, consistent naming also lets a reader file you under something they already understand — a legislator, an environmental group — which is how information gets remembered rather than merely read.2

An implied position cannot be argued with. Persuasion research distinguishes two routes: careful engagement with an argument, and reaction to cues like credibility or affect. The first produces attitudes that last and resist counter-messaging; the second produces attitudes that reverse easily. Careful engagement requires an argument to be present. "Lifelong commitment to working families" gives a reader nothing to think about — there is no claim to accept or reject.3

Prose that is hard to process is judged as less true. This one is unintuitive and well-replicated: material that takes more effort to read is rated less credible, independent of its content.4 Vagueness does not read as harmless. It reads as evasive.

What is missing from your site is chosen by someone else. Framing research holds that influence comes from what is made salient. Answer engines perform their own selection, from whatever material exists. Decline to make your record salient and the selection still happens, from sources you did not write.5

Voters answer with whatever is nearest to hand. A long-standing model of public opinion holds that people do not retrieve settled views; they assemble an answer from whatever considerations are accessible at that moment.6 An AI answer delivered seconds before someone forms an impression is a strong candidate for what is nearest to hand.

Contradiction is worse than silence. People test a story for internal consistency before they test it against the world. A site that presents a candidate as a fighter on one page and a consensus-builder on the next fails that test for a voter and an engine alike.7

↑ Contents 04 · The Mapping

One failure,
two audiences

Scoring dimensionWhat it means on the pageWhat it costs with people
Subject clarityNamed consistently, role and place statedCredibility cannot attach to a referent the reader has to resolve
Position explicitnessSpecific commitments, named legislationNothing to engage with; the reader reacts to cues instead of arguments
Factual densityClaims with evidence under themReads as assertion; low-effort prose is judged less credible
Narrative coherenceThe same story across every pageContradiction, which readers resolve by disengaging

The column on the right is not a new discipline. It is the job communications directors already have, and have always found hard for ordinary reasons — time, committee approval, the safety of language that cannot be attacked because it does not say anything.

↑ Contents 05 · Limits

What this brief
does not claim

Read this before quoting the argument

This draws on established research. It reports no experiment of its own. We have not measured whether content edited for answer-engine legibility produces better recall, attitude change, or votes than content that was not. The connections here are inferences from well-supported findings, not results. Treat the argument as a working hypothesis.

Legible prose is not maximally persuasive prose. Emotional resonance, narrative, and authentic voice matter to people in ways no scoring rubric captures, and the persuasion literature is explicit that reaction to cues is real and often decisive — particularly for voters who were never going to study a legislative record.8 Some people vote on how a candidate makes them feel.

The claim is narrower than it may sound: prose that fails on subject clarity, position explicitness and factual density tends to fail human readers on those same dimensions. Fixing that does not produce persuasive writing. It produces writing that is capable of being persuasive.

Nor does all of this work double as editing. Structured data markup, Wikidata entries and machine-readable files are genuinely technical and do nothing for a human reader. The overlap argued here covers the editorial dimensions, not the plumbing.

↑ Contents 06 · What To Do

The diagnostic
is the point

The practical value here is not that scoring tells you how to write. It is that scoring makes a familiar failure visible and countable, on a specific page, in a way an internal review rarely does. Nobody circulates a memo saying the issues pages are vague. A score does.

Three things follow, in order of how quickly they can be done.

Read your own issues pages against one question: what exactly does this say, and about whom? Most of what fails is not false. It is diffuse — true sentences that commit to nothing. That review costs a morning and needs no vendor.

Name the subject the same way everywhere, including role and jurisdiction, on every page. This is the cheapest fix available and it addresses the failure most likely to get your candidate confused with someone else.

Replace one implied position per page with a specific one — the bill, the vote, the number. If a claim cannot be made specific, that is worth knowing internally, and it is a different conversation than an editing one.

None of this is new advice. It is the advice every communications shop has already been given and mostly not taken, because the cost of vagueness was invisible. What has changed is that a machine now reads the page first, answers on your behalf, and does it identically every time — which makes the cost measurable for the first time.

Notes
  1. Cognitive load. Sweller distinguishes the inherent difficulty of a subject from load created purely by how it is presented — effort that consumes working memory without adding comprehension. Working memory is limited, so every demand imposed by the structure of a text (inconsistent naming, implicit references, facts that must be assembled from several places) subtracts from what is available for the content. Developed for instructional design; the mechanism is general. Sweller, J. (1988), "Cognitive load during problem solving: Effects on learning," Cognitive Science 12(2), 257–285 (doi:10.1207/s15516709cog1202_4); Sweller, J. (1994), "Cognitive load theory, learning difficulty, and instructional design," Learning and Instruction 4(4), 295–312.
  2. Schema theory. New information is encoded by attaching it to knowledge structures a reader already holds. Information that names entities precisely and places them in known categories is encoded more efficiently and recalled more reliably than information that forces the reader to build a framework first. Voters already hold schemas for legislators, for advocacy groups, for healthcare policy. Bartlett, F.C. (1932), Remembering: A Study in Experimental and Social Psychology, Cambridge University Press; Rumelhart, D.E. (1980), "Schemata: The building blocks of cognition."
  3. Elaboration Likelihood Model. Two routes to persuasion: the central route, involving scrutiny of the argument, and the peripheral route, running on cues such as credibility, social proof and affect. Central-route processing produces attitude change that is more durable and more resistant to counter-persuasion. It requires an argument that is present, clear and elaborable — and the authors showed that even highly motivated readers cannot take the central route when the argument structure is absent. Petty, R.E. & Cacioppo, J.T. (1986), Communication and Persuasion: Central and Peripheral Routes to Attitude Change, Springer-Verlag.
  4. Processing fluency. Material that is easier to process is judged more favourably and more credible, independent of its content — an effect replicated across a wide range of stimuli and framings. Prose that requires resolution work is low-fluency prose. Reber, R., Schwarz, N. & Winkielman, P. (2004), "Processing fluency and aesthetic pleasure," Personality and Social Psychology Review 8(4); Alter, A.L. & Oppenheimer, D.M. (2009), "Uniting the tribes of fluency to form a metacognitive nation," Personality and Social Psychology Review 13(3). Source-credibility dimensions after Hovland, C.I., Janis, I.L. & Kelley, H.H. (1953), Communication and Persuasion, Yale University Press.
  5. Framing and salience. Entman defines framing as selecting some aspects of a perceived reality and making them more salient. Answer engines perform their own salience selection over whatever material exists, which is the sense in which declining to make your record prominent does not prevent a selection — it delegates it. Entman, R.M. (1993), "Framing: Toward clarification of a fractured paradigm," Journal of Communication 43(4). Related: Lakoff, G. & Johnson, M. (1980), Metaphors We Live By; Lakoff, G. (1996, 2004).
  6. Receive-Accept-Sample. Zaller argues that people do not retrieve fixed opinions but assemble an answer from whichever considerations are accessible when they are asked. Accessibility, not conviction, does much of the work. Zaller, J. (1992), The Nature and Origins of Mass Opinion, Cambridge University Press. The model predates AI answers; the mechanism is what makes them worth attention.
  7. Narrative coherence. Fisher argues people judge communication first by whether a story hangs together internally, and second by whether it matches what they know. A subject described one way on one page and another way elsewhere fails the first test. Fisher, W.R. (1984), "Narration as a human communication paradigm," Communication Monographs 51(1); Fisher, W.R. (1987), Human Communication as Narration, University of South Carolina Press.
  8. On emotion, and the objection this raises. Haidt's moral-foundations work and Westen's work on political emotion are sometimes read as showing that fact-based communication is strategically insufficient. Neither contradicts the argument here: both operate on the choice of frame — which moral emotions to activate, which narrative to run — while this brief concerns whether whatever you chose is stated clearly enough to be received. A vague emotional appeal is not more emotionally effective than a specific one. Haidt, J. (2012), The Righteous Mind, Pantheon; Westen, D. (2007), The Political Brain, PublicAffairs.
Note: AI helped me research and draft this document. I have read every word and it has been processed by my (human) brain — I've checked what AI drafted for me, made the edits I wanted, and I stand behind what it says.