Shared AI threads
Users work in shared AI threads, so the context built in one conversation is available to the team rather than trapped in a single chat history.
PromptQL
PromptQL is a multiplayer AI workspace for teams that need shared context, cited answers, and wiki updates based on real work. It helps groups turn conversations into reusable knowledge instead of repeating the same explanations across chats and tools.
What PromptQL is
PromptQL is a multiplayer AI workspace for teams that want shared context instead of isolated chat sessions. It combines AI threads with a wiki-like knowledge layer so work done in conversation can be turned into reusable team context.
The product is built around a simple workflow: start from the context already spread across internal systems, work in a shared thread, review the system’s suggested edits, and accept changes into the wiki when they are correct. The site positions this as a way to reduce repeated explanations, keep context current, and make knowledge available across the team.
The homepage says PromptQL can read from Slack, docs, tickets, CRM, and warehouse tables, and it shows its work by citing the sources it used and the assumptions it made. The pricing page frames access as usage-based, with OLUs as the billing unit and model choice affecting how much work a task consumes.
Core capabilities
Reads from existing work systems
PromptQL starts from context already scattered across Slack, docs, tickets, CRM, and warehouse tables, then pulls the sources needed for each task.
Shows sources and assumptions
On every task, the product shows its work by listing the sources it pulled and the assumptions it made, which makes the output easier to verify.
Turns corrections into reusable context
When context is corrected once, that correction can become shared knowledge, a reusable skill, or a semantic-model change for later use.
Suggests wiki updates
Suggested edits can be reviewed and added to the wiki, so new knowledge is captured in a controlled workflow instead of staying only in chat.
Supports governed wiki workflows
The wiki model includes citations, revision history, audit trails, editorial controls, and scoped access for different connected neighborhoods.
Common ways teams use PromptQL
Support and account context
Customer success and support teams can work from recurring account context, such as renewal risk questions, export lag issues, or recurring ticket patterns, and capture the explanation once so future threads can reuse it.
Board reporting and data source validation
Revenue and finance teams can pull numbers from the current source of truth, flag stale data, and record the correct table or assumption in the wiki for later use.
Day-to-day cross-functional questions
Marketing and operations teams can start from a new thread when they need current status, campaign information, or a quick answer that would otherwise require chasing down multiple tools and people.
Semantic layer and modeling updates
Product, analytics, and data teams can use the shared thread flow to turn repeated corrections into semantic-layer or modeling changes, reducing repeated re-explanations.
Scoped collaboration
Teams that work with external collaborators or scoped internal data can use the wiki and access controls to keep customer, personal, and confidential information in separate connected neighborhoods.
Pros and Cons
Pros
- Shared threads help teams keep context in one place instead of rebuilding it across separate chats.
- The product shows sources and assumptions, which makes outputs easier to review before accepting them.
- Corrections can become reusable team knowledge, helping context compound over time.
- The wiki workflow includes citations, revision history, and editorial controls for managed updates.
- Pricing is usage-based, with a free starting allocation and no separate platform fee described on the pricing page.
Cons
- The collected pages do not provide a full integration catalog or setup documentation, so some implementation details remain unclear from the public site alone.
- Pricing depends on model choice and OLU consumption, so cost per task can vary with the model selected and the complexity of the work.
FAQ
What is PromptQL used for?
PromptQL is a multiplayer AI system for teams. The source describes shared AI threads, suggested wiki edits, and a workflow where corrections become reusable context for the team.
How does PromptQL pricing work?
The pricing page says Starter uses Operational Language Units (OLUs). An OLU is a normalized unit that rolls up different token types and models into one billing unit, and the bill shows per-thread and per-step consumption.
Can teams collaborate in PromptQL?
PromptQL is designed for team usage. The source emphasizes shared threads, shared context, revision history, audit trails, editorial controls, and scoped access for customer, internal, personal, and confidential neighborhoods.
What kind of output does PromptQL produce?
The home page and pricing page mention a shared wiki model, suggested edits, citations to real work, and access to sources such as Slack, docs, tickets, CRM, and warehouse tables. The product appears centered on turning work into reusable knowledge rather than acting as a generic chat app.
What integrations or setup does PromptQL support?
The source suggests PromptQL can connect to several work systems, including Slack, docs, tickets, CRM, and warehouse tables, and the pricing page says users can choose models per thread. Detailed setup requirements are not provided in the collected pages.
Quick Facts
- Category
- Multiplayer AI / team knowledge workspace
- Platform
- Web product with downloads for Mac (Apple Silicon), Windows, iOS, and Android
- Primary users
- Teams that need shared AI context, wiki updates, and governed knowledge capture
- Pricing model
- Usage-based OLUs with a free starting allocation; enterprise plan available
- Source domain
- promptql.io
- Notable workflow
- Work in shared threads, review suggested edits, then add accepted context to the wiki
Alternatives à PromptQL
Falconer
Falconer is an AI-powered company brain that keeps internal documentation accurate, searchable, and up to date by syncing with tools like GitHub, Slack, and Linear. It helps engineering and cross-functional teams centralize knowledge and answer questions from a shared source of truth.
Dcyde
Dcyde is a decision log for product teams that captures what was decided, the reasoning behind it, and the source in one shared place. It supports pinning decisions from Slack, Figma, or inside Dcyde and keeps the record searchable over time.
runevr
runevr is a connected workspace for creative teams that combines boards, media review, chat, recordings, drive, calls, and AI agents in one room-based environment. It is designed to reduce tool switching and keep project context together.
Goldfish
Goldfish is an AI memory app for macOS that helps you reply, write, summarize, and continue using the context already on your Mac. It stores memory locally and writes in your tone.
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.
Biji
Biji est une plateforme polyvalente conçue pour améliorer la productivité grâce à des outils et des fonctionnalités innovants.