# Dori — complete website text Website: https://trydori.io/?site=1 Generated: 2026-10-09T10:45:25.006Z This file contains the public marketing website, its interactive examples, and the full testing guides. Each page has a source URL. Example personas and findings are illustrative. --- # Dori > Dori helps builders test products and web flows with synthetic customers, uncover UI/UX friction and turn findings into improvements before shipping. Dori provides pre-human validation and product taste for builders and their agents. It uses synthetic participants to explore products, UI/UX flows and customer-facing AI agents through browser-accessible interfaces. Synthetic findings are hypotheses to investigate. They do not replace human customer research, prove factual correctness or predict measured conversion rates. Examples in these guides are illustrative, not live customer test results. Test execution depends on current availability and account access. Refer to the public website and your account for current availability and pricing. ## Testing guides - [Synthetic customer testing](https://trydori.io/synthetic-customer-testing.md): Synthetic customer testing uses AI participants to explore a product from different customer perspectives. Dori helps builders find confusion, friction and trust issues before sharing a product with real users. - [Onboarding testing](https://trydori.io/onboarding-testing.md): Onboarding testing examines whether a new user can move from arrival to a first useful result. Dori uses synthetic participants to explore signup and setup flows, showing where instructions, decisions or interface states may create friction. - [AI agent testing](https://trydori.io/ai-agent-testing.md): Dori helps builders examine customer-facing AI agents through a browser-accessible interface. Synthetic participants can explore whether a chat or agent experience understands their goal, explains its actions and helps them recover when an interaction goes wrong. ## Product information - [Dori homepage](https://trydori.io/): Product overview and current plans. - [Founders](https://trydori.io/founders): Meet the team and get in touch. - [Blogs and socials](https://trydori.io/blogs-socials): Product updates, builder stories, and community perspectives. - [For agents](https://trydori.io/for-agents): Read or download the website as plain text. - [Complete website text](https://trydori.io/llms-full.txt): Every homepage section, interactive example, prices in GBP and USD, founders, social updates, all guides, contact details, website privacy policy, and website terms in one UTF-8 text file. ## Optional - [Website privacy policy](https://trydori.io/privacy.html): The marketing website and earlier demo or early-access requests. - [Website terms](https://trydori.io/terms.html): Terms for the marketing website and public guides. - [Privacy policy](https://trydori.io/privacy): How account, workspace and test data are handled. - [Terms of service](https://trydori.io/terms): Terms for using Dori. - [Sitemap](https://trydori.io/sitemap.xml): Canonical public website pages. --- # Homepage Source: https://trydori.io/?site=1 [MEET DORI Human behaviour simulation](https://trydori.io/signup) # Find the friction. Before you ship, design, or build. Dori simulates how people think, decide, and interact with your product. Build the audience you need, then explore what drives trust, adoption, and conversion. [Start free](https://trydori.io/signup) [Watch demo](https://trydori.io/?site=1#how-it-works) Your audience. Your scenario. Evidence for your next decision. The curious explorer The goal-focused user Making a decision “What happens next?” Looking for clarity A different perspective “Let me try it first.” Simulated people. Individual perspectives. Pause rotating portraits Create your account now. Account access currently requires approval. Test execution is not yet available. Dori IN ACTION Your audience, in action Run the example. Illustrative AI personas simulating human behaviour. your-product.com ### Your product. Different perspectives. See five example personas interpret, hesitate, and decide. Run example An example panel. Your audience is yours to define. Maya The quick skimmer ••• your-product.com your product ☰ Make room for your next idea. Get started Free Start exploring Pro More possibilities Skims. Clicks. Backtracks. Alex The careful comparer ••• your-product.com your product ☰ Make room for your next idea. Get started Free Start exploring Pro More possibilities Compares every option. Leah The first-time visitor ••• your-product.com your product ☰ Make room for your next idea. Get started Free Start exploring Pro More possibilities Pauses at the next step. Ben The goal-focused user ••• your-product.com your product ☰ Make room for your next idea. Get started Free Start exploring Pro More possibilities Takes the shortest route. Sam The detail checker ••• your-product.com your product ☰ Make room for your next idea. Get started Free Start exploring Pro More possibilities Reads the fine print. Maya: “Wait, what am I signing up for?” EXAMPLE AUDIENCE SIMULATION ### Where progress stalls. 5 example personas · One product scenario Run complete #### Drop-off risk 2 / 5 hesitated or stopped at sign-up Maya Alex Leah Ben Sam #### Value clarity gaps 3 / 5 needed more clarity before committing #### Conversion blocker 1 shared obstacle: an account before value Try product Account gate The path to conversion Friction, first value, and commitment Collapse THE PATH TO CONVERSION #### Interest is there. The first win is missing. Illustrative journey · not a measured funnel 01 ##### Understand the offer 3 clarity gaps The next step, plan value, and flexibility. 02 ##### Take the next step 2 hesitation signals Sign-up creates uncertainty or stops progress. 03 ##### Reach first value Not observed A useful outcome is still behind setup. 04 ##### Choose to convert Not measured Validate sign-up and paid conversion with real users. Value realization point to test: a useful preview before setup, so visitors can experience the benefit before being asked to commit. Explore the persona findings 5 perspectives, with evidence and recommendations Collapse FOLLOW THE SIGNAL #### The behaviour behind the risk. 5 example findings All signals Drop-off & friction Value & conversion Maya Unclear next step Alex Value is hard to compare Leah Hesitation before sign-up Ben Setup blocks the first win Sam Commitment feels permanent Value & conversion Test next ##### Unclear next step > “Wait, what am I signing up for?” Maya · The quick skimmer · Synthetic persona - Reads the offer - Clicks Get started - Returns to homepage ###### Observed in this demo Clicked Get started, then returned to the homepage. ###### Potential impact Interest may fade before the product’s value becomes clear. ###### Change to test Show what happens after the click, with a concrete preview. What success would look like Visitors can explain the next step and reach the preview without backtracking. Measure with real-user tests and product analytics; this example does not predict conversion lift. Value & conversion Test next ##### Value is hard to compare > “What does the free plan include?” Alex · The careful comparer · Synthetic persona - Explores Free - Checks Pro - Returns to Free ###### Observed in this demo Moved between Free and Pro to find what each plan includes. ###### Potential impact Unclear limits can delay a plan choice, even when there is interest. ###### Change to test Compare the key limits and outcomes beside each plan. What success would look like Visitors choose a suitable plan and can explain the trade-off. Measure with real-user tests and product analytics; this example does not predict conversion lift. Drop-off & friction Test first ##### Hesitation before sign-up > “Do I need an account first?” Leah · The first-time visitor · Synthetic persona - Finds Get started - Looks for requirements - Hesitates ###### Observed in this demo Paused at Get started and looked for the sign-up requirements. ###### Potential impact Uncertainty about commitment may prevent a first attempt. ###### Change to test Preview the steps and explain what information is needed. What success would look like First-time visitors start confidently without searching for reassurance. Measure with real-user tests and product analytics; this example does not predict conversion lift. Drop-off & friction Test first ##### Setup blocks the first win > “I just want to try it now.” Ben · The goal-focused user · Synthetic persona - Wants to try - Meets account gate - Stops before value ###### Observed in this demo Went straight to the primary action, then stopped at the account requirement. ###### Potential impact The user may leave before experiencing a useful outcome. ###### Change to test Let people try a short preview before creating an account. What success would look like More visitors reach a useful result, then choose to create an account. Measure with real-user tests and product analytics; this example does not predict conversion lift. Value & conversion Test next ##### Commitment feels permanent > “Can I change this later?” Sam · The detail checker · Synthetic persona - Reviews pricing - Searches terms - Checks flexibility ###### Observed in this demo Left the plans to look for cancellation and change-of-plan terms. ###### Potential impact Unanswered questions about flexibility can hold up conversion. ###### Change to test Put change and cancellation terms next to the plan choice. What success would look like Visitors understand their options before committing to a plan. Measure with real-user tests and product analytics; this example does not predict conversion lift. What to test next 3 experiments and the outcomes to watch Collapse TURN FINDINGS INTO EXPERIMENTS #### What to test next. 01 ##### Let value come before the account. Offer a useful preview before sign-up. WATCH Preview → account creation 02 ##### Make the plan choice easier. Show limits, outcomes, and flexibility together. WATCH Plan selection → checkout 03 ##### Make the next decision feel clear. Explain the first step and what it requires. WATCH Primary CTA → first useful action Expand a section to explore the example findings. Scroll for details. Select the heading again to return to the overview. Run example Example audience Findings Five example personas · Build your own audience in Dori Replay demo Pause demo FROM PERSPECTIVES TO PROOF ## Watch them find their own way. One example audience. Different goals, habits, and decisions. Define the audience and scenario that matter to your product. Find friction See where people hesitate. Explore confusing flows, unclear copy and moments that weaken trust. Follow the evidence Understand what happened. Connect UI/UX findings to the simulated customer’s journey. Improve with purpose Choose what to change next. Use the findings to refine your product before testing with real people. THE COST OF UNANSWERED QUESTIONS ## Your roadmap won’t wait. But customer insight takes time. Budgets get approved. Teams start building. Customer conversations take time. When decisions move faster than research, expensive assumptions can make it into the product. Product investment Are we solving a problem customers care about? Potential cost: Engineering effort in the wrong place. Market expansion Will this work for our next audience? Potential cost: A launch built on assumptions from another market. Pricing & packaging Is the value clear enough to justify the commitment? Potential cost: An offer customers struggle to understand. Adoption Does this fit how customers actually work? Potential cost: A launch that struggles to become a habit. ILLUSTRATIVE PRODUCT DECISIONS Simulate your audience’s response before the decision is made. [See how Dori works](https://trydori.io/?site=1#workflow) More relevant simulations start with what you know about people. amplitude mixpanel intercom slack your interview notes 01 Define your audience. Choose the people, context, and question to explore. 02 Simulate interactions. Explore how people respond, weigh choices, and act. 03 Act on the evidence. Trace decisions to behaviour and choose what to test next. FROM BRIEF TO BEHAVIOUR ## Your next product decision. Backed by behaviour. Give your audience a scenario. Explore their motivations, reactions, and decisions as they interact with your product. Can someone get to their first project? Jess, an illustrative simulated persona in a blue shirt Jess · Curious explorer · Simulated persona Dori Your research workspace 01 / 03 A GOOD PLACE TO START ### What are you wondering? Your product your-product.com Your question Can a first-time user get to their first project without getting stuck? Describe your audience New users · Small teams New users · Small teams Operations leads · Growing companies First-time buyers · A new market Experienced users · Complex workflows Run example simulation This example uses Jess. Your brief stays on this page. Dori An example product session 02 / 03 THROUGH JESS’S EYES ### A little help getting started. Your first project is ready. Bring your team along. Your project My first workspace Invite a teammate name@company.com Invite your team Explore on my own first Illustrative simulation · Wants value before involving her team Dori Your research workspace 03 / 03 A CLEARER NEXT MOVE ### Let people explore first. Jess pauses at the invite step. She wants to see value before involving her team. Move the invitation until after the first project. [See the evidence](https://trydori.io/?site=1#verdict) Try another question Illustrative simulation · One moment, a useful next step The curious explorer Tries first. Reads later. Explore persona The careful planner Details make the difference. Explore persona The busy team lead Every minute counts. Explore persona Close persona profile Arjun Patel 31 yrs Independent founder Openness: 5 out of 5 Conscientiousness: 3 out of 5 Extraversion: 4 out of 5 Agreeableness: 4 out of 5 Neuroticism: 2 out of 5 What matters Get to a useful result quickly. How they explore Explores by clicking, then circles back for context. Illustrative persona · Example personality traits Example profiles. Build the audience your product needs. YOUR AUDIENCE, YOUR QUESTION ## The audience you need. For the question you have. Build any audience your product needs. Simulate their choices, motivations, and interactions. - First-time buyers - Experienced pros - Existing customers - New markets Tailored by role, needs, and experience. Grounded in your customer insights. [A few things worth knowing](https://trydori.io/?site=1#faq) ## A fresh perspective. On your next move. Simulate the decisions behind conversion, adoption, and demand—with audiences defined for each question. An example Pro plan at $49 a month. Nora asks: What do I get before I commit? VALUE & PRICING ### Make the value clear. Simulate how your target buyers weigh value, compare alternatives, and decide whether to commit. Explore the example Nora Simulated persona > “What do I get before I commit?” Nora compares the offer, then returns to the feature list. A concrete example helps her understand what she is paying for. A DIRECTION TO TEST Show an example outcome beside the plan. An example team invitation screen with an Explore first path highlighted beside the email field. FIRST-TIME EXPERIENCE ### Find the first win. Explore the expectations and motivations that help your audience get started and experience value. Explore the example Arjun Simulated persona > “Can I try it on my own first?” Arjun pauses at the invitation step and looks for a way to explore. He wants to try one project before involving his team. A DIRECTION TO TEST Move team invitations until after the first project. A smart summary concept surrounded by three simulated persona reactions, including: Will this save me a step? PRODUCT IDEAS ### Give your idea a reality check. Bring a concept to the audience it is meant for. Explore relevance, objections, and reasons to adopt. Explore the example Imani Simulated persona > “Will this save my team a step?” Imani skips the feature introduction and searches for the action that helps her team finish their work. A DIRECTION TO TEST Lead with the task it helps people complete. Illustrative simulations. Validate with real people. BUILT FOR PRODUCT DECISIONS ## For everyone who makes the call. ### Researchers Explore audience behaviours and reactions before a study. Bring sharper hypotheses into conversations with real people. ### Product teams Simulate how your audience discovers value, adopts a workflow, and decides whether to commit. ### Agencies Build the audience each client needs. Explore how different customers respond to products, concepts, and messaging. ### AI builders Simulate how people ask questions, interpret responses, and build or lose trust in your AI product. PRICING ## Start with a question. Make room for evidence. Test with synthetic customers. Choose the allowance that fits your product and team. Prices in £ GBP $ USD Fixed prices in each currency. Prices in GBP: Free £0, Pro £49, Ultra £199. ### Free £0 Free account A first look at how synthetic customers experience your product. - 3 persona tests total - Across all workspaces on your account - Lifetime allowance. No monthly reset. [Start free](https://trydori.io/signup) Create your account now. Test execution is not yet available. ### Pro £49 per paid seat / month A regular testing rhythm for each builder on your team. - 8 persona tests per paid seat - A fresh allowance each billing month - Unused tests do not roll over [Create account](https://trydori.io/signup) Pro checkout is not yet available. You can create an account now. ### Ultra £199 per workspace / month A shared test allowance for builders working together. - 40 pooled persona tests per billing month - 3 builder seats included - Unused tests do not roll over [Create account](https://trydori.io/signup) Ultra checkout is not yet available. You can create an account now. ### One persona tested = one test. A study with three personas uses three tests. Free includes three tests total over your account’s lifetime, across all workspaces. Free tests do not reset monthly. Paid allowances renew each billing month and do not roll over. Compare test allowances Allowance | Free | Pro | Ultra Price in GBP | £0 Free account | £49 per paid seat / month | £199 per workspace / month Persona tests | 3 total | 8 per paid seat | 40 pooled per workspace Allowance period | Account lifetime | Each billing month | Each billing month Builder seats included | Free account | Charged per paid seat | 3 builder seats Unused tests roll over? | No monthly reset | No | No FREQUENTLY ASKED QUESTIONS ## What you need to know. See the workflow before you start. [Watch demo](https://trydori.io/?site=1#how-it-works) What counts as a persona test? One persona tested = one test. A study with three personas uses three tests. The five-persona demo is illustrative; it does not change your plan’s allowance. How does the Free allowance work? Free includes three persona tests total over your account’s lifetime, across all workspaces. Creating another workspace does not give you more Free tests. Free tests do not reset monthly. What do Pro and Ultra include? Pro includes eight persona tests per paid seat each billing month. Ultra includes forty pooled persona tests per workspace each billing month, with three builder seats included. See the pricing cards for fixed GBP and USD prices. Do unused paid tests roll over? No. Pro and Ultra allowances renew each billing month, and unused tests do not roll over. Free is a lifetime account allowance, not a monthly allowance. Can I purchase a paid plan now? The plan cards show current paid checkout availability. Create an account first; when checkout is available, choose your plan in the app’s account-plan flow. Authentication, onboarding and purchases all happen in the app. What can I test with Dori? Dori helps builders validate products with synthetic customers. Give them a product and a scenario to explore. See where the UI, copy or workflow causes friction, confusion or trust issues, then use evidence-backed findings to decide what to improve. Are synthetic customers real users? No. They are simulated customers with different goals, motivations and habits. Use their findings to spot potential issues and sharpen the questions you take to real people. Validate important assumptions with real users. How do I get started? Choose Start free to create your account in the Dori app. New accounts currently require admin approval before entry. Test execution is not yet available. The app handles access and onboarding. Bring a product, an audience and a question you want to validate. For a preview of the workflow, watch the demo on this page. Dori BUILD WITH YOUR CUSTOMERS IN MIND ## Find the friction. Build a better next version. Test with synthetic customers. Turn UI/UX findings into evidence-backed improvements. [Start free](https://trydori.io/signup) [Watch demo](https://trydori.io/?site=1#how-it-works) --- # Pricing in USD Source: https://trydori.io/?site=1#pricing PRICING ## Start with a question. Make room for evidence. Test with synthetic customers. Choose the allowance that fits your product and team. Prices in £ GBP $ USD Fixed prices in each currency. Prices in USD: Free $0, Pro $49, Ultra $199. ### Free $0 Free account A first look at how synthetic customers experience your product. - 3 persona tests total - Across all workspaces on your account - Lifetime allowance. No monthly reset. [Start free](https://trydori.io/signup) Create your account now. Test execution is not yet available. ### Pro $49 per paid seat / month A regular testing rhythm for each builder on your team. - 8 persona tests per paid seat - A fresh allowance each billing month - Unused tests do not roll over [Create account](https://trydori.io/signup) Pro checkout is not yet available. You can create an account now. ### Ultra $199 per workspace / month A shared test allowance for builders working together. - 40 pooled persona tests per billing month - 3 builder seats included - Unused tests do not roll over [Create account](https://trydori.io/signup) Ultra checkout is not yet available. You can create an account now. ### One persona tested = one test. A study with three personas uses three tests. Free includes three tests total over your account’s lifetime, across all workspaces. Free tests do not reset monthly. Paid allowances renew each billing month and do not roll over. Compare test allowances Allowance | Free | Pro | Ultra Price in USD | $0 Free account | $49 per paid seat / month | $199 per workspace / month Persona tests | 3 total | 8 per paid seat | 40 pooled per workspace Allowance period | Account lifetime | Each billing month | Each billing month Builder seats included | Free account | Charged per paid seat | 3 builder seats Unused tests roll over? | No monthly reset | No | No --- # Illustrative persona profiles Source: https://trydori.io/?site=1#why-dori Fictional example profiles. Personality scores are illustrative, not assessments of the portraits. ## Arjun Patel 31 years · Independent founder The curious explorer Tries first. Reads later. What matters: Get to a useful result quickly. How they explore: Explores by clicking, then circles back for context. Openness: 5 out of 5 Conscientiousness: 3 out of 5 Extraversion: 4 out of 5 Agreeableness: 4 out of 5 Neuroticism: 2 out of 5 ## Nora Ellis 58 years · Operations consultant The careful planner Details make the difference. What matters: Understand the details before committing. How they explore: Compares options and reads the terms before choosing. Openness: 3 out of 5 Conscientiousness: 5 out of 5 Extraversion: 2 out of 5 Agreeableness: 4 out of 5 Neuroticism: 2 out of 5 ## Imani Brooks 34 years · Product team lead The busy team lead Every minute counts. What matters: Find a clear path for the whole team. How they explore: Scans for the next step and skips anything that slows it down. Openness: 4 out of 5 Conscientiousness: 4 out of 5 Extraversion: 5 out of 5 Agreeableness: 3 out of 5 Neuroticism: 3 out of 5 --- # Meet the founders | Dori Source: https://trydori.io/founders THE FOUNDERS # The people behind Dori. We’re building Dori to help teams find friction earlier and make their next version better. Have a question, an idea, or feedback? We’d love to hear what you’re building. SF ### Samuel Faroun-Amin Co-founder [LinkedIn](https://www.linkedin.com/in/samuel-faroun/) HS ### Harmandeep Singh Co-founder [LinkedIn](https://www.linkedin.com/in/harmandeepsingh7/) GET IN TOUCH ### A question for the team? For product questions, support, or privacy requests, email us directly. [samy@trydori.io](mailto:samy@trydori.io) --- # For agents | Dori Source: https://trydori.io/for-agents FOR AGENTS # The whole site. In plain text. Read everything about Dori in one file. Product information, pricing, founders, community updates, guides, and website policies—all without running JavaScript. Updated with each website release. COMPLETE WEBSITE TEXT ## One file. Every section. https://trydori.io/llms-full.txt [Read full text](https://trydori.io/llms-full.txt) [Download .txt](https://trydori.io/llms-full.txt) UTF-8 plain text · Headings and source links included ## What’s included ### Product and workflow Every homepage section, audience, use case, and interactive example. ### Pricing and availability Free, Pro, and Ultra in GBP and USD, with allowances and current access notices. ### Founders and contact The people behind Dori, their profiles, and how to reach the team. ### Blogs and socials Builder stories and community updates, with author credits and original links. ### Testing guides Synthetic customer testing, onboarding testing, and AI agent testing. ### Company and policies Company details, the website privacy policy, and website terms. [Compact index](https://trydori.io/llms.txt) [Synthetic customer guide](https://trydori.io/synthetic-customer-testing.md) [Onboarding guide](https://trydori.io/onboarding-testing.md) [AI agent guide](https://trydori.io/ai-agent-testing.md) --- # Blogs & socials | Dori Source: https://trydori.io/blogs-socials BLOGS & SOCIALS # Ideas, updates, and people. Follow what we’re learning, making, and sharing with the Dori community. From the founder LinkedIn ### Dori in the hands of builders Samuel reflects on sponsoring an onboarding hackathon, where builders used Dori’s custom personas to explore their ideas and improve their flows. Samuel Faroun-Amin Read post Source link: https://lnkd.in/p/etMQtcnB Builder story LinkedIn ### A fresh perspective on student onboarding Elissa shares how her team used Dori to test a student research concept, identify improvements before presenting, and earn second place at the hackathon. Elissa Chung Read post Source link: https://lnkd.in/p/eAJ4xSN5 Community perspective LinkedIn ### Bringing builders together Sima looks back at a day of collaborative building at Ramen Space and Dori’s role in helping teams test what they shipped. Sima Rahman-Huang Read post Source link: https://lnkd.in/p/e-54KseS Explore our product guides [Synthetic customer testing](https://trydori.io/synthetic-customer-testing) [Onboarding testing](https://trydori.io/onboarding-testing) [AI agent testing](https://trydori.io/ai-agent-testing) --- # Synthetic customer testing for builders Source: https://trydori.io/synthetic-customer-testing Synthetic customer testing uses AI participants to explore a product from different customer perspectives. Dori helps builders find confusion, friction and trust issues before sharing a product with real users. ## What is synthetic customer testing? It is a way to rehearse a product experience with simulated people. You give AI participants a customer context and a task, then inspect what they do, where they struggle and what the evidence suggests changing. The findings help you form hypotheses for your next iteration. ## When to use it Use it when you have a landing page, prototype or working web product and want an early view of how different people might experience it. It can help solo builders, product teams and builder agents examine clarity, navigation and trust before a human research session. ## How to approach the test ### 1. Set a decision and a task Choose a specific question, such as whether a new visitor understands the product before signing up. Give participants a realistic goal rather than asking them to find every possible problem. ### 2. Choose relevant perspectives Create participants with the needs, context and familiarity you want to explore. A time-constrained first-time visitor can reveal different friction from an experienced evaluator. ### 3. Review behaviour and evidence Inspect the journey, findings and available screenshots or recordings. Check that a finding is supported by a visible action or response rather than an assumption about a whole customer segment. ### 4. Change one thing and test again Turn a finding into a concrete product change. Revisit the task, then use real customer research and product data to validate the decision. ## Illustrative example — not a live test result ### Task Understand the product and decide whether to create an account. ### Participant A first-time builder evaluating a new testing tool. ### Observation The participant opens the pricing section, returns to the hero and looks for an example report before choosing Sign up. ### Evidence Illustrative sequence: pricing → hero → search for a report example. A real finding should link to the relevant steps and captured evidence. ### Interpretation The visitor may need to see what a test produces before committing to setup. ### Change Show a clearly labelled sample report beside the primary call to action. ## What to look for - Value proposition and next-step clarity - Terminology and navigation - Trust signals and expectations - Differences between participant perspectives ## What this test can and cannot tell you AI participants do not represent a statistically sampled customer population. Their actions depend on the task, persona context and model. A repeated finding is a reason to investigate, not a measured prevalence rate, conversion forecast or proof of what real customers will do. ## Common questions ### Does Dori replace real customer research? No. Synthetic tests can surface questions earlier. Interviews, usability sessions with people and behavioural data are still needed to confirm customer needs and product outcomes. ### What should I test first? Start with one decision and one short task: understand the product, find a price, sign up or reach a first useful result. Narrow tasks make findings easier to act on. ### How should I judge a finding? Look for a clear observation, the step where it happened and supporting evidence. Separate what the participant did from the interpretation and the change you want to try. ## Getting started Test execution depends on current availability and account access. Check your account before planning a study. Product information: https://trydori.io/ --- # Test onboarding flows before you ship Source: https://trydori.io/onboarding-testing Onboarding testing examines whether a new user can move from arrival to a first useful result. Dori uses synthetic participants to explore signup and setup flows, showing where instructions, decisions or interface states may create friction. ## How can synthetic customers test onboarding? Give a participant a realistic first-use goal and let it work through the browser flow. Review the choices, pauses, errors and expectations along the way. The useful output is a supported explanation of what made the journey harder and a specific change to test next. ## When to use it Use this approach when you are building or changing registration, account setup, workspace creation or a first-run experience. It is especially useful before you invite new users to a product or ask people to evaluate a prototype. ## How to approach the test ### 1. Define the first useful result State what the participant should accomplish: create a workspace, understand a setup requirement or reach an initial result. Do not treat account creation alone as proof of a successful onboarding experience. ### 2. Describe the starting context Specify what the visitor knows, why they arrived and how familiar they are with similar tools. Keep the task neutral so it does not reveal the path you expect them to follow. ### 3. Inspect each transition Review labels, required fields, error messages, progress cues and the moment after setup. Look for uncertainty about what to enter, why it is needed and what happens next. ### 4. Prioritise and retest Choose a supported source of friction, revise the copy or flow and repeat the same goal. Follow up with human testing and analytics to assess the effect on activation. ## Illustrative example — not a live test result ### Task Create a workspace and reach a first useful result. ### Participant A new user who has not used the product before. ### Observation At the company URL field, the participant tries a social profile because the form does not explain which URLs are supported. ### Evidence Illustrative sequence: read field label → enter social URL → see validation error. A real report should capture the entered value, error state and subsequent action. ### Interpretation The input requirement is unclear at the point where the user needs to decide. ### Change Explain the supported URL type beside the field and provide an actionable error message. ## What to look for - Signup and setup instructions - Required fields and validation errors - Progress, loading and recovery states - Clarity of the first useful result ## What this test can and cannot tell you Synthetic onboarding tests can identify candidate friction, but they do not measure human activation or conversion rates. A participant may also be blocked by CAPTCHA, multi-factor authentication or inaccessible interfaces. Treat an automation limitation separately from a usability problem and use human testing for those steps. ## Common questions ### Can Dori predict onboarding conversion? A synthetic test does not produce a measured human conversion rate. Use it to identify hypotheses, then evaluate changes with real users and analytics. ### Should participants receive step-by-step instructions? Give the outcome and enough context to attempt it. Detailed navigation instructions can hide the confusion you are trying to discover. ### How do I compare two onboarding versions? Keep the task and participant context consistent, compare supported observations and investigate material differences. Confirm the outcome with human research or a properly designed experiment. ## Getting started Test execution depends on current availability and account access. Check your account before planning a study. Product information: https://trydori.io/ --- # Test AI agent experiences with synthetic customers Source: https://trydori.io/ai-agent-testing Dori helps builders examine customer-facing AI agents through a browser-accessible interface. Synthetic participants can explore whether a chat or agent experience understands their goal, explains its actions and helps them recover when an interaction goes wrong. ## What does customer-facing AI agent testing evaluate? It evaluates the experience a person has while using an agent: task clarity, questions, responses, visible actions, trust and recovery. Start with a realistic customer goal, observe the interaction and review the evidence behind each finding before deciding what to change. ## When to use it Use it for a web chat assistant, an agent embedded in your product or a browser-accessible agent workflow. Product teams and builder agents can use the observations to refine instructions, interaction design and how the interface communicates progress or uncertainty. ## How to approach the test ### 1. Choose a customer goal Use a concrete task such as finding an option that meets a budget, preparing a draft or understanding a recommendation. Define what a useful outcome would look like from the customer perspective. ### 2. Vary context and expectations Explore participants with different familiarity, constraints and communication styles. Test ambiguity that a person could reasonably introduce without hiding the core task. ### 3. Review the full interaction Inspect the prompts, replies and visible state changes. Check whether the agent asks useful questions, distinguishes proposed actions from completed actions and provides a clear path when it cannot proceed. ### 4. Turn evidence into a revision Separate interface problems from response-quality problems. Adjust the flow, instructions or copy, then retest and use a broader evaluation programme for model reliability. ## Illustrative example — not a live test result ### Task Ask an assistant to prepare a shortlist within a stated budget. ### Participant A customer who expects to review options before taking an action. ### Observation The assistant gives recommendations but does not explain which options satisfy the budget or what information is missing. ### Evidence Illustrative transcript: budget constraint in the request → recommendations without a budget comparison → follow-up asking which options qualify. A real report should reference the actual exchange. ### Interpretation The customer cannot confidently judge whether the response meets the constraint. ### Change Make the budget comparison explicit and ask for missing information before claiming the goal is complete. ## What to look for - Goal understanding and clarification - Response clarity and visible constraints - Communication about actions and uncertainty - Error recovery and next steps ## What this test can and cannot tell you This page describes testing an agent through its web interface. It is not a direct API benchmark, a comprehensive security assessment or proof of factual correctness. Synthetic participants can miss failures or share model biases; use human review, domain-specific evaluations and security testing where the decision requires them. ## Common questions ### Can I test an agent without a web interface? This Dori workflow uses a browser-accessible product surface. Direct API evaluations need a separate test harness and suitable evaluation criteria. ### What makes an agent finding actionable? A finding should show the customer goal, the relevant exchange or visible behaviour, why it created difficulty and a specific revision to investigate. ### Does a successful synthetic task prove reliability? No. Agent behaviour can vary with wording, context and model updates. Test multiple scenarios and combine observations with task-specific evaluations and human review. ## Getting started Test execution depends on current availability and account access. Check your account before planning a study. Product information: https://trydori.io/ --- # Website privacy policy Source: https://trydori.io/privacy.html [← Back to Dori](https://trydori.io/?site=1) Legal # Privacy Policy Last updated: October 9, 2026 ## Who we are Dori is a trading name of MESONA AI LTD, registered in England and Wales, company number 16277578. Registered office: Charter Court, 16a Unit 1 Harcourt Street, London, England, W1H 4HE. This policy covers the Dori marketing website and demo or early-access requests previously collected here. For account, workspace, and test data, see the [application privacy policy](https://trydori.io/privacy). ## What we collect This landing page links to the Dori application for account creation and sign-in. It no longer collects demo or early-access requests. Account registration and use of the application are covered by the [application privacy policy](https://trydori.io/privacy). We do not run advertising trackers or sell data to anyone. If you email us, we receive your email address and the information you choose to include in your message so we can respond to your enquiry. ## How we use it - To answer questions, support enquiries, or privacy requests you send us. - To reply to your demo or early-access request. - To follow up about Dori if you have asked us to. We will not add you to a marketing list you didn't ask for. ## Where it lives Demo and early-access requests collected on October 5, 2026 were stored in Supabase, which processes the data on our behalf. Earlier requests remain in Google Firebase (Firestore). These request records include your email address, the form you submitted, and the submission time. They are separate from application account registrations. ## How long we keep it We keep demo-request emails until we have followed up and you tell us you're no longer interested, or you ask us to delete them — whichever comes first. ## Your choices You can ask us at any time to see, correct, or delete the information we hold about you. Email [samy@trydori.io](mailto:samy@trydori.io) or write to our registered office above with your request. You can also reply to any email we've sent you. ## Contact For questions about this policy or a privacy request, contact [samy@trydori.io](mailto:samy@trydori.io). ## Changes If this policy changes in a way that matters, we'll update this page and the date above. [Founders](https://trydori.io/founders) · [Blogs & socials](https://trydori.io/blogs-socials) · [For agents](https://trydori.io/for-agents) · [Contact](https://trydori.io/founders#contact) · [Website terms](https://trydori.io/terms.html) Dori is a trading name of MESONA AI LTD, registered in England and Wales, company number 16277578. Registered office: Charter Court, 16a Unit 1 Harcourt Street, London, England, W1H 4HE. --- # Website terms Source: https://trydori.io/terms.html LEGAL # Website terms Last updated: October 9, 2026 ## Who operates this website Dori is a trading name of MESONA AI LTD, registered in England and Wales, company number 16277578. Registered office: Charter Court, 16a Unit 1 Harcourt Street, London, England, W1H 4HE. These terms cover the Dori marketing website and its public guides. Account access and use of the Dori application are covered by the [application terms of service](https://trydori.io/terms) and any commercial agreement you have with us. ## Using this website You may browse the website and use its guides to learn about Dori. Please do not interfere with the website, attempt unauthorised access, or use it for unlawful purposes. The Dori name, branding, and original website content belong to MESONA AI LTD or their respective owners. You may share links and quote short extracts with attribution. Contact us if you would like to reuse our branding or substantial parts of the content. ## Product information and examples Public demos and sample findings are illustrative. Synthetic customers are simulated participants; their findings help identify questions to investigate and do not replace research with real people or guarantee business outcomes. Features and availability may change as Dori develops. Check the current availability notices, pricing, and account information before planning a study. Purchases and plan changes take place in the application under the terms presented there. ## Links to other websites This website links to the Dori application and external sites, including founder profiles. Those services have their own terms and privacy notices. ## Privacy See our [website privacy policy](https://trydori.io/privacy.html) for information about this marketing website and earlier demo or early-access requests. The [application privacy policy](https://trydori.io/privacy) describes account, workspace, and test data. ## Your rights Nothing in these website terms limits any rights you have under applicable law or excludes liability that cannot lawfully be excluded. ## Contact and changes For questions about this website or these terms, email [samy@trydori.io](mailto:samy@trydori.io) or write to our registered office above. We will update this page and its date when the website terms change. --- # Company footer Dori is a trading name of MESONA AI LTD, registered in England and Wales, company number 16277578. Registered office: Charter Court, 16a Unit 1 Harcourt Street, London, England, W1H 4HE. Contact: samy@trydori.io © 2026 Dori