ContentGrapher
AboutResearchHelp Docs
Analyze →
ContentGrapher
Analyze →
AboutResearchHelp Docs
← All reference pages

Primary Retrieval Role

The five PRR types, how to diagnose a mixed-role page, and what to do when the classification seems wrong.

What primary retrieval role means

Every page has a structural role in the retrieval ecosystem: the job it does for the reader. ContentGrapher classifies this role before running the concept analysis, because the required concept structure depends on what the page is for.

A page trying to do two jobs at once produces a diluted signal. ContentGrapher's model assumes AI retrieval systems prefer a focused guide over a page that mixes explanation, step-by-step instructions, and a product pitch when the query is "how to do X."

The report shows the detected role at the top, under the page title, as one phrase: "Explains", "Guides a task", "Compares options", "Helps assess a choice" or "Supports a next step". If the analysis recorded no role, it reads "Page role not recorded".

The top of a report: the page title "Cache" and, under it, the role phrase "Explains" after a teal dot, then "· Beginning technical writers", the audience of the report.

The five roles

Explain — defines or explains what something is. The reader is building understanding. Required concepts are definitions, relationships, mechanisms, and examples. Example: "What is transformer architecture?"

Guide — procedural how-to execution. The reader is completing a task. Required concepts are steps, prerequisites, decision points, and failure modes. Example: "How to fine-tune a language model."

Compare — X vs. Y, alternatives, trade-offs. The reader is evaluating options. Required concepts are evaluation criteria, trade-offs, use-case fit, and when each option applies. Example: "RAG vs. fine-tuning: when to use each."

Evaluate — is X right for me, best X for Y. The reader is assessing fit for their situation. Required concepts are fit criteria, constraints, decision signals, and alternatives for non-fits. Example: "Is vector search right for my use case?"

Convert — transactional, drives a next step. The reader is taking action. Required concepts are the value proposition, trust signals, objection handling, and a clear action path.

RoleThe report showsThe reader isRequired concepts
ExplainExplainsBuilding understandingDefinitions, relationships, mechanisms, examples
GuideGuides a taskCompleting a taskSteps, prerequisites, decision points, failure modes
CompareCompares optionsEvaluating optionsEvaluation criteria, trade-offs, use-case fit, when each option applies
EvaluateHelps assess a choiceAssessing fit for their situationFit criteria, constraints, decision signals, alternatives for non-fits
ConvertSupports a next stepTaking actionValue proposition, trust signals, objection handling, a clear action path

How the roles connect

The five roles map a reader's progression through a topic: from understanding what something is (Explain), to doing it (Guide), to comparing options (Compare), to assessing fit (Evaluate), to taking action (Convert). This ordering is why scope decisions matter across pages — a concept that belongs to a later stage in this progression often becomes adjacent on an earlier-stage page, because it requires a different kind of explanation than the page's primary role allows.

A well-structured content set routes the reader through these stages via explicit links between focused pages, rather than trying to serve multiple stages on one page.

How to diagnose a mixed-role page

The clearest signal of a mixed-role page is in the boundary classifications: look for adjacent or excluded concepts that belong to a different structural role. If your explain-page has several adjacent concepts that are procedural steps (guide-role content), those are scope problems, not coverage gaps.

A low coverage score alongside an accurate PRR classification usually indicates content gaps within that role, not role mixing. Role mixing and content gaps are different problems. Role mixing shows up in the boundary classifications. Content gaps show up in the next steps.

What to do with a mixed-role page

Separate the roles into dedicated pages and link between them. A user who understands the concept (explain page) should be able to follow a link to the guide. A user who completes the guide should be able to link to the evaluation page.

If separation is not practical, decide which role is primary and demote the secondary role to a brief mention with a link to the dedicated page. Do not try to serve both roles equally.

How sure is the analysis of the role?

The analysis does not measure how sure it is of the page role. The first section of the page overview, "Page role", shows counts that you can check instead: how many concepts are core to this page, for example "7 of 9 concepts are core to this page", and how many are possible separate topics or outside the page's scope, for example "1 possible separate topic" and "1 outside this page’s scope".

The counts come from the classifications on the concept map. They are not a rating of how sure the analysis is. Supportive concepts count in the total although they belong on the page, so a page with many supportive concepts has a lower core count without a role problem.

To judge whether the role fits, select the concepts labelled "Possible separate topic · brief mentions can stay" or "Assessed as outside this page’s scope" and read their "Why" line. The reason "it belongs on a page with a different role" points to role mixing. If several concepts give that reason, check the role before you act on "Decide page scope" tasks, and see "If the classification seems wrong" below.

The "Page role" part of the page overview: "2 of 5 concepts are core to this page", then "1 possible separate topic" and "1 outside this page’s scope", and the note "From the map’s concept labels · certainty not measured".

Do top results do the same job as this page?

The page overview includes a short block, "What did Google show for this topic?". One line compares this page's role with the role that the titles of the top Google results leaned towards, for example "Top result titles leaned towards guiding a task · this page explains". Another line says whether Google showed an AI answer above the results.

Both lines are context. They change neither the coverage score nor the detected role of this page.

See Do top Google results do the same job as my page? and Did Google show an AI answer for my topic? for how each line is made.

If the classification seems wrong

First, check the primary topic (anchor) that ContentGrapher detected — an incorrect topic produces an incorrect role. After the concept map appears and before the full analysis finishes, a "Topic" line shows above the map. Select "Edit topic" (the pencil) beside it to correct the topic; ContentGrapher then runs a new analysis with the corrected topic, which produces a new classification. The pencil is not available while the full analysis runs, and the Topic line no longer shows once the analysis has finished.

If the anchor is correct but the PRR still seems wrong, the classification reflects the structural role ContentGrapher detected from the actual content mix, not the intended purpose. The concept distribution, not the title or intent, drives the classification.

To change the PRR, change the content structure: reduce or remove content that belongs to a different structural role, then re-analyze. See Boundary Classifications to understand which concepts are creating the role conflict.

Related topics

→Boundary Classifications→Do top Google results do the same job as my page?→Did Google show an AI answer for my topic?
← All reference pages