--- language: en title: "Prompt for writing an informational article" description: "Turn a specific question into a clear explanation with a definition, example, limitations, and sources for SEO, AEO, and GEO." canonical: "https://tropk.ai/en/resources/prompts/prompt-for-writing-an-informational-article" last_modified: "2026-10-12T16:08:24.390Z" --- # Prompt for writing an informational article Reviewed on 2026-10-06. ## Prompt to adapt and use Explain a clearly scoped conceptual question and prepare the reader to make a concrete decision. ### Prepare before you begin COMPANY AND BUSINESS company: {empresa} domain: {dominio} confirmed_offering: {produtos_servicos_capacidades_limites_e_fontes} business_context: {mercado_regiao_diferenciais_comprovados_e_restricoes} AUDIENCE AND OBJECTIVE audience: {perfil_tarefa_conhecimento_inicial_e_restricoes} main_question: {pergunta_do_leitor} reader_outcome: {o_que_a_pessoa_deve_conseguir_decidir_ou_fazer} editorial_objective: {objetivo} intent_and_stage: {intencao_de_busca_e_etapa_da_decisao} VOICE AND EDITORIAL CONTEXT voice: {tom_vocabulario_exemplos_de_estilo_e_termos_a_evitar} topic_and_entities: {tema_keyword_principal_termos_e_entidades} inventory: {paginas_existentes_e_decisao_criar_atualizar_ou_consolidar} contribution: {exemplo_matriz_metodo_ou_dado_proprio_autorizado} cta: {proxima_acao_pertinente_e_destino_confirmado_ou_nao_aplicavel} EVIDENCE AND ACCESS sources: {id_titulo_url_autor_data_de_publicacao_consulta_e_trechos_relevantes} authorized_data: {dados_definicoes_periodo_metodo_e_permissoes_ou_nao_disponivel} internal_links: {url_publicada_assunto_e_funcao_do_link} research_access: {ferramentas_realmente_habilitadas_e_acessos_autorizados_ou_sem_navegacao} restrictions: {confidencialidade_direitos_prazos_mercado_e_escopo} concept: {conceito_e_significado_no_contexto} ambiguities: {outros_usos_do_termo_ou_sigla} limitations: {onde_a_definicao_deixa_de_valer} example: {exemplo_proprio_real_autorizado_ou_hipotetico_identificado} ### Delivery format A. Complete article in Markdown: initial answer, explanation, example, limitations, and next decision. B. Concept table and claim/source map. C. Record of the example, its origin, and its label. ### Review criteria • The central question is answered without silently expanding the scope. • Definitions, ambiguities, and limitations have appropriate sources. • The example is authorized and real, or clearly labeled hypothetical. • Observation and causation remain distinct. • The reader can apply the distinction and identify the next decision. ### Modelo Act as a research and writing assistant for the specified company. Write in Brazilian Portuguese, clearly and in the brand voice, for the audience’s task. Produce a draft for human review. Use all the context below, not just the topic. MODULE 1 — CONTEXT TO COMPLETE COMPANY AND BUSINESS company: {empresa} domain: {dominio} confirmed_offering: {produtos_servicos_capacidades_limites_e_fontes} business_context: {mercado_regiao_diferenciais_comprovados_e_restricoes} AUDIENCE AND OBJECTIVE audience: {perfil_tarefa_conhecimento_inicial_e_restricoes} main_question: {pergunta_do_leitor} reader_outcome: {o_que_a_pessoa_deve_conseguir_decidir_ou_fazer} editorial_objective: {objetivo} intent_and_stage: {intencao_de_busca_e_etapa_da_decisao} VOICE AND EDITORIAL CONTEXT voice: {tom_vocabulario_exemplos_de_estilo_e_termos_a_evitar} topic_and_entities: {tema_keyword_principal_termos_e_entidades} inventory: {paginas_existentes_e_decisao_criar_atualizar_ou_consolidar} contribution: {exemplo_matriz_metodo_ou_dado_proprio_autorizado} cta: {proxima_acao_pertinente_e_destino_confirmado_ou_nao_aplicavel} EVIDENCE AND ACCESS sources: {id_titulo_url_autor_data_de_publicacao_consulta_e_trechos_relevantes} authorized_data: {dados_definicoes_periodo_metodo_e_permissoes_ou_nao_disponivel} internal_links: {url_publicada_assunto_e_funcao_do_link} research_access: {ferramentas_realmente_habilitadas_e_acessos_autorizados_ou_sem_navegacao} restrictions: {confidencialidade_direitos_prazos_mercado_e_escopo} MODULE 2 — FORMAT INPUTS Format: informational article Objective: Explain a clearly scoped conceptual question and prepare the reader to make a concrete decision. concept: {conceito_e_significado_no_contexto} ambiguities: {outros_usos_do_termo_ou_sigla} limitations: {onde_a_definicao_deixa_de_valer} example: {exemplo_proprio_real_autorizado_ou_hipotetico_identificado} MODULE 3 — EVIDENCE AND LIMITATIONS Read the supplied texts. If research is enabled and authorized, consult relevant primary sources and record the pages actually read. Without browsing, use the attachments and return a list of outstanding checks; do not say you opened URLs. A competitor’s page can guide research, but does not substantiate all its claims. Do not invent features, prices, data, clients, experiences, tests, credentials, testimonials, quotations, or links. Distinguish documented facts, observations, interpretations, and hypothetical examples. Missing information is not zero and does not prove that a feature does not exist. Preserve dates, versions, regions, plans, units, denominators, and material conditions. Derived numbers require calculations checked with a real tool or a validated result supplied in the inputs. Without that, mark verification as pending; do not claim you recalculated. Do not disclose private data. Use names, images, and statements only with authorization. Do not copy the wording or the entire sequence of a reference. Preserve human authorship and identify which validations require the subject-matter owner. MODULE 4 — FORMAT PRODUCTION 1. Define the question and the audience’s level of knowledge. 2. Confirm the definition in the supplied sources; do not present a brand taxonomy as universal consensus. 3. Draft an initial answer, a progressive explanation, the necessary context, and an original example. 4. Explain the limitations and misinterpretations that affect the decision. 5. Remove sections that serve a different intent and suggest only existing follow-up resources. MODULE 5 — SEO, AEO, AND GEO Use an H1 that aligns with the question and body; organize H2s/H3s around reader decisions. Start sections with direct answers when helpful. Each passage should retain enough entities, context, and conditions to be understood on its own. Use terms naturally, without fixed density or artificial repetition. Cite the specific source near the fact it supports; preserve the supplied URL. Suggest internal links only to confirmed, useful destinations. Do not force an FAQ, word count, or special schema into every format. Do not promise rankings or citations. Do not add authorship, review, publication date, testing, or updates that did not happen. The CTA should match the stated offering and action, without a pitch unrelated to the task. MODULE 6 — OUTPUT AND REVIEW A. Complete article in Markdown: initial answer, explanation, example, limitations, and next decision. B. Concept table and claim/source map. C. Record of the example, its origin, and its label. Also provide: proposed H1, SEO title, description, and slug; claim map with source, section, and limitation; links used; outstanding items with impact and next check. Separate this material from the publishable body. Do not publish or declare the draft approved. Review against the criteria below and mark each as met, needs correction, or not applicable, with a reason: 1. The central question is answered without silently expanding the scope. 2. Definitions, ambiguities, and limitations have appropriate sources. 3. The example is authorized and real, or clearly labeled hypothetical. 4. Observation and causation remain distinct. 5. The reader can apply the distinction and identify the next decision. If essential evidence for the central promise is missing, return only the safe portion and state which input prevents a conclusion. Do not fill the gap with a likely conclusion. ## When to use this prompt Use this format when someone wants to understand a specific question: what a metric is, how a concept works, or why two situations differ. The output should provide enough explanation to support a subsequent decision. Before writing, phrase the question in one sentence and note what the reader already knows. This helps prevent every topic from turning into an enormous guide. Scope matters more than word count. An article about the difference between a mention and a [citation](/en/resources/glossary/ai-citation) needs to explain how to identify each and where classification depends on context. It can point to a tutorial on recording observations, but it does not need to teach the entire monitoring process. Define what is out of scope so the title and promise remain accurate. [SEO](/en/resources/glossary/seo) organizes the page for people searching; [AEO](/en/resources/glossary/aeo) focuses on clear answers; [GEO](/en/resources/glossary/geo) addresses discoverability in generative responses. In this resource, all three are treated as writing, research, and review practices: address the task, name entities, preserve context, and make evidence verifiable. A [prompt](/en/resources/glossary/prompt) can help prepare a draft. It does not verify facts or guarantee rankings, recommendations, or citations by AI. ## Prepare the inputs before writing Gather the main question, potentially ambiguous terms, audience, company offering when relevant, and sources appropriate to the definition. For platform rules, use official documentation for the relevant version. For editorial taxonomies, state that they are working definitions. Paste relevant excerpts into the sources field; a list of URLs without content does not support drafting in a conversation without research enabled. Choose a contribution that helps readers classify a situation: an authorized example, a small matrix, or a distinction that references leave unclear. An example invented for teaching can be useful, as long as it is labeled hypothetical. It should not be given a client name, real result, or experiential account. Also check whether an existing page already answers the same question. ## How to produce and review the content The prompt asks for an initial answer, a progressive explanation, and an applied example. Each section should address one facet of the question while making the concept and its conditions explicit. A sentence like “this improves visibility” is insufficient: say what information changed, in what context, and what conclusion the evidence supports. Avoid claiming the cause of an [AI response](/en/resources/glossary/ai-response) merely because a brand was absent. Review the draft in two passes. First, check the logic and whether someone unfamiliar with the company can follow it. Second, go through each definition, number, rule, and causal relationship, linking every claim to the relevant source. Remove details that belong to another topic. The next step may be to investigate, compare, or apply; the closing does not need to repeat a sales pitch unrelated to the question. ## Example input Example input: question: “What is the difference between a brand mentioned in a response and a source cited in a response?” Audience: an analyst starting to record observations. Contribution: two hypothetical responses, one naming the brand and the other including an attributed link. Expected outcome: classify examples without confusing textual presence, sources, and recommendations. The examples do not represent company measurements. ## How to use the full prompt Copy the full prompt and replace the fields in braces before sending it. Attach the source content in addition to the URLs: a model without browsing cannot check a link on its own. Use “not available” when data is missing and explain why. Generate a first version, review outstanding items, and correct the inputs before requesting a review. Keep public-facing copy separate from research notes. ## Check the result - The central question is answered without silently expanding the scope. - Definitions, ambiguities, and limitations have appropriate sources. - The example is authorized and real, or clearly labeled hypothetical. - Observation and causation remain distinct. - The reader can apply the distinction and identify the next decision. ## Sources and references - [Create helpful, reliable, people-first content]() — Google Search Central - [AI tools and your site]() — Google Search Central - [Guidance about content created with generative AI]() — Google Search Central ## Continue a leitura - [Prompt for writing a Q&A article]() - [Prompt for writing a guide or pillar page]() - [Prompt for writing a tutorial or how-to]() - [AI discovery strategy]() - [Resources]() ## About the author [Luiz Gardelin]() Luiz Gardelin is the founder of Tropk.ai and works in GEO/AEO, product vision, strategy, and growth, helping brands understand and improve their presence in AI responses. --- [All pages in Markdown]()