--- language: en title: "Prompt for writing about a trend or update" description: "Explain a verifiable change with dates, the previous state, affected audiences and conditional actions, without presenting an announcement as availability." canonical: "https://tropk.ai/en/resources/prompts/prompt-for-writing-about-a-trend-or-update" last_modified: "2026-10-12T16:14:30.324Z" --- # Prompt for writing about a trend or update Reviewed on 2026-10-06. ## Prompt to adapt and use Communicate what changed, what evidence supports the change and what the reader can decide now. ### 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} content_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} internaI_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} change: {evento_ou_direcao_observada_e_fonte_primaria} dates: {publicacao_evento_vigencia_e_fuso_quando_relevante} status: {anunciado_em_teste_parcial_disponivel_ou_vigente_com_evidencia} before_and_now: {estado_anterior_e_atual_com_fontes} affected_audiences: {publico_regiao_versao_plano_e_condicoes} trend_series: {observacoes_janela_metodo_e_limites_ou_nao_aplicavel} impacts: {perfil_mudanca_consequencia_acao_e_condicao} inventory_and_review: {atualizar_pagina_ou_criar_analise_e_gatilho_de_nova_conferencia} ### Delivery format A. Article in Markdown: change, dates, previous context, affected audiences, consequences and conditional actions. B. Timeline and impact table by audience profile. C. Record of sources, uncertainties, URL decision and next review trigger. ### Review criteria • The primary source, publication, event and effective dates are distinguished. • Market, version, audience and availability status are explicit. • A trend has a series and time window; an isolated signal remains identified as a signal. • Facts, interpretations and predictions have appropriate labels and limitations. • Actions by audience profile and the update trigger align with current evidence. ### Modelo Act as a research and writing assistant for the company provided. Write in Brazilian Portuguese, with clarity and the brand’s voice, for the audience’s task. Produce a draft for human review. Use the full 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} content_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} internaI_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: trend or update Objective: Communicate what changed, what evidence supports the change and what the reader can decide now. change: {evento_ou_direcao_observada_e_fonte_primaria} dates: {publicacao_evento_vigencia_e_fuso_quando_relevante} status: {anunciado_em_teste_parcial_disponivel_ou_vigente_com_evidencia} before_and_now: {estado_anterior_e_atual_com_fontes} affected_audiences: {publico_regiao_versao_plano_e_condicoes} trend_series: {observacoes_janela_metodo_e_limites_ou_nao_aplicavel} impacts: {perfil_mudanca_consequencia_acao_e_condicao} inventory_and_review: {atualizar_pagina_ou_criar_analise_e_gatilho_de_nova_conferencia} MODULE 3 — EVIDENCE AND LIMITS Read the supplied texts. If authorized research tools are available, 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, customers, experiences, tests, credentials, testimonials, quotations or links. Distinguish documented facts, observations, interpretations and hypothetical examples. Missing information is neither zero nor proof 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 to have recalculated. Do not expose 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 specify which validations require the subject-matter owner. MODULE 4 — FORMAT PRODUCTION 1. Confirm the primary source, dates, stage and affected audience. Do not confuse an announcement with availability. 2. Compare documented states and decide whether to update a page or create a distinct analysis. 3. For a trend, check the series and time window; without sufficient basis, describe a bounded event or signal. 4. Write the facts, context, interpretation and impact by audience profile, distinguishing between acting, waiting and maintaining current practice. 5. Record uncertainties, conflicting sources and the review trigger. Do not invent urgency, a prediction or an update date. MODULE 5 — SEO, AEO AND GEO Use an H1 that aligns with the question and body; organize H2/H3 headings around reader decisions. Start sections with direct answers when helpful. Each passage must retain enough entity, context and conditions to make sense on its own. Use terms naturally, without fixed keyword 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 an author, reviewer, publication date, test or update that did not happen. The CTA must match the stated offering and action, without a pitch unrelated to the task. MODULE 6 — OUTPUT AND REVIEW A. Article in Markdown: change, dates, previous context, affected audiences, consequences and conditional actions. B. Timeline and impact table by audience profile. C. Record of sources, uncertainties, URL decision and next review trigger. 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. Keep this material separate from the publishable body. Do not publish or declare the draft approved. Review against the criteria below and mark each as met, fix or not applicable, with a reason: 1. The primary source, publication, event and effective dates are distinguished. 2. Market, version, audience and availability status are explicit. 3. A trend has a series and time window; an isolated signal remains identified as a signal. 4. Facts, interpretations and predictions have appropriate labels and limitations. 5. Actions by audience profile and the update trigger align with current evidence. 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 an update when a documented change affects an audience’s task. Explain what changed, who it affects and when it takes effect. An announcement, a test, a partial rollout and a current policy are different states. Before writing, check which state the source confirms. The headline must reflect that state so it does not present a future possibility as an available feature. A trend requires more than one recent example. Define the series, time window or set of observations that supports the stated direction. Without that, present a bounded event or signal. Also consider whether updating an existing page makes sense: a version change may improve the original tutorial, while an event with its own impact may warrant a new analysis. Avoid creating another URL to repeat the same guidance. [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) concerns discovery in generative responses. In this resource, all three appear as writing, research and review practices: address the task, name entities, preserve context and make evidence verifiable. A [prompt](/en/resources/glossary/prompt) helps prepare a draft. It does not verify facts or guarantee rankings, recommendations or citations by an AI. ## Prepare the inputs before writing Gather the [primary source](/en/resources/glossary/primary-source), publication date, event date and effective date, if available. Record the region, version, plan, audience and availability stage. Include the previous state and its evidence so the comparison does not rely on memory. If sources differ, identify the discrepancy and what needs to be verified; do not silently choose the more appealing version. Prepare an impact table by audience profile: confirmed change, supported consequence, possible action and condition to verify. Interpretation can be useful, as long as it is labeled as interpretation. Predictions need assumptions and uncertainty, never manufactured certainty. For a trend, include the series source, period and limitations; for an update, specify the next review trigger, such as a new version or confirmation of availability. ## How to create and review the content The prompt organizes facts, context and consequences in that order. Show what changed compared with the documented state, identify who is affected and explain what the evidence allows people to do now. Distinguish between acting, waiting for confirmation and maintaining current practice. Do not create urgency just because the topic is recent. Guidance without conditions can lead readers to act before the change reaches their circumstances. During review, check the dates and return to the primary source. Does the text distinguish publication, event and effective dates? Does the headline still match actual availability? Is there new information that requires updating the page? Record the review actually performed and preserve the history when relevant. The analysis is useful when it translates the change into a concrete task, with a limitation and a next check, rather than repeating the announcement. ## Example input Hypothetical example: a provider announces a change to a feature, with testing limited to a particular group. The assignment compares the announcement with the previous documentation, distinguishes test participants from other users and proposes checking eligibility before taking action. The headline states that the feature is in testing. This example does not report a real launch or predict that the feature will be available on an unconfirmed date. ## How to use the complete prompt Copy the complete prompt and replace the fields in braces before sending it. Attach the source content as well as the URLs: a model without browsing cannot verify a link on its own. Use “not available” when data is missing and explain why. Generate a first version, check what is outstanding and correct the inputs before requesting a review. Keep public-facing text separate from research notes. ## Check the result - The primary source, publication, event and effective dates are distinguished. - Market, version, audience and availability status are explicit. - A trend has a series and time window; an isolated signal remains identified as a signal. - Facts, interpretations and predictions have appropriate labels and limitations. - Actions by audience profile and the update trigger align with current evidence. ## Sources and references - [Create helpful, reliable, people-first content]() — Google Search Central - [AI features and your website]() — Google Search Central - [Guidance on generative AI-created content]() — Google Search Central ## Continue a leitura - [Prompt for writing an informational article]() - [Prompt for writing a tutorial or how-to]() - [Prompt for writing a research study or benchmark]() - [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]()