Our Approach / The world’s first collective dialogue system.
What is the Remesh “Collective Dialogue System?”
It's a modern research environment that gathers data from digital conversations. The researcher asks questions, participants respond, then evaluate each other's responses. This collective response process is rapidly deployed and can transform the level of depth and scale you can achieve to make research-backed decisions.
Technology that makes more possible. And makes it easier.
Our AI-driven research tools help you do more with less.
The Collective Response Interface
Put simply, this is where the conversation happens. Researchers and participants engage in a conversational environment that feels organic but has been carefully crafted to optimize outcomes, whether live or asynchronously. After submitting their response, participants complete voting exercises to indicate how much or little they agree or disagree with each others’ responses, giving you the most complete picture possible.
"Agreement" Prediction Engine
A constantly evolving and improving algorithm that delivers representative insights with a high level of confidence. Our model learns from the participants’ voting exercises, as well as the linguistic meaning of each response. Why? Because it would be impossible to vote on each and every response. But using our advanced algorithm and LLM technology, we can predict how they would vote on each if they did. Every interaction enriches the depth, nuance, and confidence of results.
Segmentation Overlay
By layering your demographic segments on the “agreement” prediction data, you can unlock never-before-possible insights: pinpoint the most representative responses, determine the level of agreement in key groups, and identify consensus. This is a valuable repository of insights with a new element of confidence to guide your decisions and impress stakeholders.
Research-Specific NLP and LLM Technology
Our rapidly-evolving technology transforms the tedious to effortless. What once were daunting (if not impossible) tasks for large-scale studies are distilled to a few simple clicks. Tagging. Coding. Thematic analysis. Translations. Summaries. Immense amounts of data can be processed in an instant, all while maintaining your expert human oversight.
Let’s walk through how a collective response works.
How it Works
Step 1
Step 2
Step 3
Step 4
Step 5
/ 5
1
First, there’s an open-ended question or prompt.
Pre-programmed or sent on the fly.
.webp)
2
Participants respond in their own words.
Using free-form text, they can share their honest thoughts without constraints, giving you access to a rich source of data that supports your hypothesis — or takes you down an unexpected path you hadn’t considered.
.webp)
3
Participants evaluate responses shared by others.
This helps understand how well responses reflect the views of specific segments and discover areas of resonance.
.webp)
4
Responses are immediately analyzed.
The Remesh algorithm analyzes each response to understand its meaning and how similar or different it is from other responses. And predicts how participants would vote on every response they didn't see (since voting on thousands of responses would be next to impossible).
.webp)
5
Results are generated instantly.
Organize and analyze response data by themes, codes, sentiment, or create summaries.
The results allow us to better understand what best represents each segment, the group overall, and where there is consensus.
A transformative impact on research and decision-making.
Diversity /
Efficiency / Scalability / Confidence
01
Ensures a wide range of perspectives are considered, enhancing the diversity of insights.
02
Significantly accelerate the insight generation process, from data collection to analysis
03
Provides in-depth insights from a large audience.
04
Advanced AI analysis tools enable confident, actionable conclusions.
Diverse applications.
Market Research
Foundation Research
Market Research
Ideate & Develop Product Ideas
Market Research
Develop Ads and Creative
Market Research
Develop Marketing Messaging
Market Research
Concept Development
Market Research
Package Testing
Market Research
Concept Testing
Market Research
Claims & RTB Development
Employee Research
.webp)
Employee Health, Benefits, and Total Rewards
Employee Research
Change Management
Employee Research
Culture
Employee Research
Diversity & Inclusion
Employee Research
Organizational Effectiveness
Employee Research
Employee Listening
Employee Research
Employee Experience Design
Employee Research
Future of Work
Questions about our technology? We value transparency. Let’s clear some things up.
Yes. Customers may optionally enable Generative AI features, as well as disable them at any time.
Ultimately, we believe that AI technology is best used to help humans — not replace them. Our use of Generative AI helps our customers gain game-changing efficiencies that empower them to do their job faster and better.
When participants vote on each other’s responses, they’re only voting on a few responses (because voting on every single response would be near-impossible). But we can use their voting behavior and responses to predict their level of agreement with every other response. Learn more in this published paper.
Percent Agree is an estimate of the percentage of participants that would agree with a particular response.
We compute Percent Agree scores using a machine learning model called collaborative filtering, which uses the voting activities the participants complete after submitting their own responses. You can learn more about how this is calculated here.
Remesh is designed for anyone who conducts research — professionals in insights, marketing, human resources, and government all use Remesh to better understand their audience.
Remesh is easy to use, making it suitable for junior-level team members, while also having advanced capabilities tailored to the expert researcher. Team roles can be assigned to give everyone the access they need to make meaningful contributions.
At Remesh, ensuring the safety of your data is our top priority. With the advancement of AI technology, concerns about data privacy, security, and ownership have grown. Rest assured, we take these concerns seriously. While we've been utilizing AI for over a decade, we've only recently incorporated Large Language Models (LLMs) following the removal of the requirement to retain and utilize customers' input data.
Please view our Privacy Policy and Terms of Service. Data is not used to train or tune any models. Please also review OpenAI’s Terms & Policies and specific API Data Usage Policies.
In addition, Remesh undergoes an annual third-party audit. This rigorous process includes a comprehensive Penetration Testing report and a SOC 2 Type II certification, affirming our adherence to the highest standards for security and privacy. These measures are part of our ongoing effort to safeguard your data and trust in our AI-powered solutions.
©All Rights Reserved 2024. Read our Privacy policy