# PromptQL PromptQL é um espaço de trabalho de IA colaborativo para equipes que precisam de contexto compartilhado, respostas com citações e atualizações de wiki geradas a partir do trabalho em andamento. Ele transforma informações dispersas de Slack, documentos, tickets, CRM e tabelas de data warehouse em conhecimento reutilizável. - Findings24: - Site: - Preços: Freemium - Categorias: Base de Conhecimento IA, Assistente pessoal de IA, Automação de fluxos de trabalho com IA ## O que é PromptQL? PromptQL is a multiplayer AI workspace for teams that want shared context instead of isolated chat histories. The product is presented as a team brain that helps people work in shared AI threads, show their work with sources and assumptions, and turn useful context into wiki updates that others can reuse. The site positions PromptQL for situations where context is spread across multiple systems and people keep having to re-explain the same things. It starts from existing information in tools such as Slack, docs, tickets, CRM, and warehouse tables, then turns corrections made during work into cited knowledge, reusable skills, and semantic-model changes. ## O que PromptQL pode fazer? ### Shared threads and shared context Teams work in shared AI threads instead of isolated chats. PromptQL keeps the context available to everyone in the workspace so the next person does not start from scratch. ### Context that compounds PromptQL learns from corrections made in the flow of work. The homepage says corrections stick for everyone and become reusable skills, team knowledge, or semantic-model changes. ### Cited answers and reviewable edits On each task, PromptQL shows the sources it used and the assumptions it made. The homepage also describes cited, scoped knowledge with revision history and editorial controls. ### Cross-source context gathering PromptQL starts from context scattered across Slack, docs, tickets, CRM, and warehouse tables. It can surface ambiguity, prompt teammates for missing context, and turn the result into wiki updates. ### Usage-based billing in OLUs Pricing is usage-based through Operational Language Units. The pricing page says OLUs normalize token types and models, include infrastructure and sandbox hosting, and expose per-step usage breakdowns. ### Model choice and enterprise controls The platform supports model choice per thread and mentions open-weight and proprietary models. Enterprise features listed on the pricing page include SSO, private networking, dedicated VPC/BYOC, audit trails, and fine-grained permissions. ## Casos de uso ### Account and churn analysis Customer success or account teams can ask whether an account is at risk, pull together usage and ticket signals, and preserve the reason behind recurring patterns so the team does not keep relearning the same issue. ### Metric definition and source-of-truth maintenance Revenue, operations, or finance teams can reconcile where a metric should come from, capture the correct source of truth, and mark stale assumptions so later threads use the updated semantic model. ### Shared troubleshooting and handoffs Support, product, and engineering teams can resolve a missing-context question by pulling in the teammate who knows, then converting the answer into a cited wiki update for future sessions. ### Recurring request handling Marketing and other knowledge-heavy teams can use PromptQL as a starting point for recurring requests, so work begins in a thread instead of in a separate queue of tickets and follow-ups. ## Perguntas frequentes ### What is PromptQL? PromptQL is a multiplayer AI workspace that lets teams work in shared threads and then turn the context they create into suggested wiki edits. The site describes it as a shared brain for team AI work. ### How does PromptQL pricing work? The pricing page says PromptQL measures usage in Operational Language Units (OLUs), a normalized unit that rolls up different token types and models into one billable measure. ### Can I choose different AI models for different tasks? Yes. The pricing page says you can switch models per thread, and even mid-thread. It also notes that PromptQL gives access to every model available in its lineup, which expands over time. ### What kinds of data or context does PromptQL connect to? The homepage says PromptQL starts from context already scattered across Slack, docs, tickets, CRM, and warehouse tables, and the demo page highlights challenges like semantic layers and tool schemas. ### Is PromptQL meant for individuals or teams? PromptQL is presented as a team product for shared AI threads, wiki updates, and scoped access control. The source does not spell out limits on team size or deployment setup on the public pages provided. ## Informações rápidas - **Category**: Multiplayer AI workspace - **Primary use**: Shared team threads and context management - **Pricing model**: Usage-based, measured in Operational Language Units (OLUs) - **Source domain**: promptql.io - **Public workflow**: Work in shared AI threads, review suggested wiki edits, then accept or edit them - **Enterprise options**: SSO, private networking, dedicated VPC/BYOC, audit trails