> For the complete documentation index, see [llms.txt](https://help.metaforms.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.metaforms.ai/getting-started/quickstart.md). # What is Metaforms? ### Metaforms is the Agentic OS for Market Research. In plain language, we make research delivery faster and easier, with AI agents that work alongside your team at every step — from designing the research to the final report. These agents help draft questionnaires, program surveys, test live links, handle revisions and trackers, validate data, clean and code open ends, create tables, and prepare reporting output. They run inside a shared unified workflow, so the context your team adds in an earlier stage is preserved across the lifecycle of the project. Your team gets value from Metaforms without changing the platforms, templates, workflows, and review habits it already works with. **We support all major survey programming platforms such as Decipher, Confirmit, Qualtrics, and Dimensions.** ### A unified agentic platform, organized by one module for each stage The modules you see in your account depend on what your team has bought and rolled out. Usually, teams start with Survey Programming. From there, they may add other modules as more of their delivery work moves into Metaforms. Here's the full suite of modules inside Metaforms: #### Research Manager Helps your team review and shape questionnaires before programming begins. #### Survey Programming Turns a questionnaire into a survey your programmer can review in batches before launch. We've designed it to work with the survey platforms your team already uses, including **Decipher, Dimensions, Confirmit, and Qualtrics.** #### Change Management Compares revised questionnaires and helps your team review downstream dependencies, including tracker wave updates. #### QA and Link Testing Tests a live survey link against the questionnaire so issues can be fixed before fieldwork. #### Data Validation Checks collected responses against questionnaire logic and project rules. #### Open-End Coding Cleans and codes open-text responses with your team reviewing the code frame and assignments. #### Tabulations Creates tables from validated data and the analysis plan. #### Reporting Helps turn validated data and tables into report-ready output. You may only use one of these modules today. That is fine. *Metaforms is designed so each module can be useful on its own, while still fitting into the same project workflow when your team adds more.* ### A reliable way for any research team to integrate AI in their delivery operations Working with agents isn't quite like using regular software. It's still software, sure, but now it can actually think. Which means, now, *you're also teaching the system how your team likes things done!* Metaforms lets seasoned research teams hand work to agents without handing over judgment, because every output still passes through someone who knows what good looks like. An agent programs a small batch of questions, your team checks it and gives feedback, and the next batch uses that feedback. If the output needs a frequent correction, that correction can become an AI rule. If a setup is going to repeat, it can become a template. This is what makes agents useful in real research operations. *Your standards become part of the next piece of work the agents generate.* And this is also how agents become dependable enough for real production work. They do the heavy lifting, your team checks and corrects what comes out, and the whole system sharpens as your team feeds it better rules. ### When you need a hand Good support is how new tools actually take hold. So we built help and learning into Metaforms because AI only works when someone's there the moment you get stuck, *and that's a job we genuinely love showing up for.* Also, working with agents is still pretty new, so yeah, there's a learning curve! That's why we like to be hands-on with our rollouts. Our customer success team and subject matter experts work with your team to set up your workflows, build templates that standardize your team’s conventions, and help you give the system good feedback. **Support is available 24/7.** **A real person monitors requests and responds under 30 minutes and will help through your account channel or the support links in this Help Center.** --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://help.metaforms.ai/getting-started/quickstart.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.