# Get your context Source: https://docs.semilattice.ai/api-reference/context/get-your-context https://api.semilattice.ai/openapi.json get /v1/context Return the caller's saved context, or {has_context: false}. # Create a project Source: https://docs.semilattice.ai/api-reference/projects/create-a-project https://api.semilattice.ai/openapi.json post /v1/projects Create a project. Create one first when you plan to run several related simulations, then pass its id as project_id when creating simulations. # Get a project Source: https://docs.semilattice.ai/api-reference/projects/get-a-project https://api.semilattice.ai/openapi.json get /v1/projects/{project_id} Fetch a project with its rounds, simulations, and each round's current synthesis. # List projects Source: https://docs.semilattice.ai/api-reference/projects/list-projects https://api.semilattice.ai/openapi.json get /v1/projects List projects visible to the caller, most recently active first. # Discover goals and inputs Source: https://docs.semilattice.ai/api-reference/simulation-schema/discover-goals-and-inputs https://api.semilattice.ai/openapi.json get /v1/simulation-schema Return a mode's goal list when `goal` is omitted, or a single goal's input schema when `goal` is given. `mode` is `research` or `journey`. # Create a simulation Source: https://docs.semilattice.ai/api-reference/simulations/create-a-simulation https://api.semilattice.ai/openapi.json post /v1/simulations Create a simulation from mode + goal + inputs + user_model_ids. Returns immediately in status `planning`; the plan is generated in the background. Poll GET /{id} until status is `planned`. # Edit the plan Source: https://docs.semilattice.ai/api-reference/simulations/edit-the-plan https://api.semilattice.ai/openapi.json patch /v1/simulations/{simulation_id}/plan Edit the generated plan while the simulation is in status `planned`. # Get a simulation Source: https://docs.semilattice.ai/api-reference/simulations/get-a-simulation https://api.semilattice.ai/openapi.json get /v1/simulations/{simulation_id} Fetch a simulation by id. The polling target: returns progress while running, and synthesis + markdown + results once completed. # List simulations Source: https://docs.semilattice.ai/api-reference/simulations/list-simulations https://api.semilattice.ai/openapi.json get /v1/simulations List the caller's simulations, newest first. Optionally filter by status or by project_id (projects group related simulations). # Make a simulation public Source: https://docs.semilattice.ai/api-reference/simulations/make-a-simulation-public https://api.semilattice.ai/openapi.json post /v1/simulations/{simulation_id}/share Make a simulation publicly viewable and return its shareable URL. # Move a simulation into a project Source: https://docs.semilattice.ai/api-reference/simulations/move-a-simulation-into-a-project https://api.semilattice.ai/openapi.json patch /v1/simulations/{simulation_id} Move a simulation into a project. Allowed only when the simulation has no project yet; it joins the project's latest round (a first round is created for an empty project). Anything else returns 409. # Run a simulation Source: https://docs.semilattice.ai/api-reference/simulations/run-a-simulation https://api.semilattice.ai/openapi.json post /v1/simulations/{simulation_id}/run Kick off background execution of a `planned` simulation (→ `running`). # List user models Source: https://docs.semilattice.ai/api-reference/user-models/list-user-models https://api.semilattice.ai/openapi.json get /v1/user-models List user models available to run simulations against, with accuracy and metadata. Use the ids as `user_model_ids`. # Changelog Source: https://docs.semilattice.ai/changelog What moved, what shipped, what we're thinking about. ## Projects: an agent that plans and runs your simulations. Describe a decision or upload a spec and an agent plans a set of simulations against it, runs them, and gives you a synthesis across all of them with what to change. Apply the findings to v2 and start a new round to find a better solution. The simulations run at the same time, so you can search several directions on the same decision at once. Each round keeps its own simulations and synthesis, so you can go back and see what you asked and what came back at every stage. Read the [announcement](https://semilattice.ai/blog/projects). ## Semilattice Custom: a custom model of your users for \$1,799/mo. Semilattice Custom is the product offering for Anacreon. We build a custom **anacreon** model of your users, your customers, or any segment you can define, tested for accuracy on held-out questions and delivered with its own accuracy report. A Custom subscription includes unlimited simulations, unlimited seats, organisation features, and API and MCP access. Custom is a partnership, not a licence: we meet with you regularly to help you point your model at the decisions you're actually making. Read the [announcement](https://semilattice.ai/blog/semilattice-custom) or [book a call](https://app.semilattice.ai/user-models/request). ## Anacreon: state-of-the-art accuracy in simulating individuals. A new kind of user model. Rather than predicting audience-level answer distributions, **anacreon** models the individual: hundreds of simulacra, each one a model of a single person, so results can be segmented and re-cut any way you need. Diverse and minority opinions survive instead of being averaged away. On held-out individual-level questions, **anacreon** achieves a state-of-the-art ordinal alignment of 0.775, ahead of every published academic baseline. Custom user models we build for customers are **anacreon** models. Read the [announcement](https://semilattice.ai/blog/anacreon) or the [technical report](https://semilattice.ai/research/anacreon). ## Logged-in user journey simulations. Notifications. You can now run user journey simulations on logged-in user flows. Add test account credentials and watch simulated users navigate dashboards, account settings, private content feeds, and anything behind a login wall. We've also added in-app and email notifications, so you can trigger simulations, get on with something else, and be notified to return when they're done. ## MCP v2: agentic validation with simulated users. The Semilattice MCP now supports full User Research and User Journey simulations, enabling rapid validation at any point in your product or marketing workflow. Use it for discovery, concept validation, feature prioritisation, message testing, conversion flow optimisation, UX comprehension, and usability testing. See the [MCP introduction](/mcp/introduction) to get started. ## Automatic simulation titles. Simulation titles are now set automatically when the simulation plan is generated, based on the simulation's parameters. Works for both user research and user journey simulations. You can rename a simulation from the simulations list or from its results page. ## Multi-segment simulations. You can now run a single simulation across multiple user models. Toggle **Compare multiple** on the user model selection step, add the user models you want to test, and run. Results come back segmented by user model: paired bars in the predictions pane so cross-segment differences read at a glance. Use it to understand your users' pain points or differences; or compare how messages or ideas resonate with different user segments in one simulation. ## Compare options in user journey simulation. You can now paste two URLs instead of one. Pick a user model, and simulated users navigate both versions. Results come back paired: completion rates, page flow, time on task, and per-user observations for each variant. Because the data comes from the user model rather than real traffic, neither URL needs to be your own. Test a draft against what's in production. Test your page against a competitor's. Test today's site against last year's from the Internet Archive. Any two live URLs work. The rest of the flow is unchanged. Pick a test type, paste the URLs, pick a user model, review the generated task and success criteria, and run. The "Compare two options" toggle sits on the Define step. ## User journey simulation. Open sign-up. Simulated users can now navigate your product. Give Semilattice a URL, pick a user model, and watch them click through your product in minutes. See where they get stuck, what they find and what they miss. Five modes. Findability, conversion flow, comprehension, discovery, or define your own. The system writes the test scenario for you. Describe what you want to learn, pick a user model, and it generates a realistic user task and success criteria. Review, edit if you want, then run. Results show completion rates, page flow, per-user session replays with screenshots, and written observations describing exactly what happened. Key findings and recommendations extracted automatically. Export as PDF or share via URL. Sign-up is open at semilattice.ai. ## Results you can act on. Export and share. Simulation results are now organised for decisions. We extract findings that are well-supported by the evidence, highlight noteworthy things you might otherwise miss, and list specific recommendations for next steps. Charts sit in a side pane so you can read the synthesis and check the data at the same time. The most important predictions come up first. Every report shows the user model's prediction accuracy, so you can calibrate your confidence in the results. New export options make it easier to take Semilattice findings into your process. Download a PDF to share with execs, a CSV for your own analysis, a Markdown file for Claude or Notion, or chart images for embedding anywhere. And you can now share results with colleagues via a URL. Context extraction is richer. The product pulls more from your URL and understands more about your product before you ask your first question. ## User models, redesigned. Product testing in alpha. Complete redesign of the user model experience. Every user model now has a detail page with accuracy scores and accuracy badges so you can gauge reliability at a glance. Drill into individual questions to compare ground truth against predictions with paired bar charts. Search and filter across everything. [Read more on the blog →](https://semilattice.ai/blog/audiences-redesign) User journey simulation (alpha) gives you simulated users that interact with live websites as specific user segments would. They navigate, convert, get confused, miss things. ## 91% accurate against the FCA Financial Lives Survey We tested our UK Consumer Finance user model against the FCA's most comprehensive benchmark: 207 questions it had never seen, covering trust, financial literacy, product usage, and demographics. Overall accuracy: 91%. The interesting part is where it gets things wrong. The model knows the right answer to financial literacy questions, but real people often don't. It predicts what people *should* think, not always what they *do* think. That gap is the research question. [Read the full analysis →](https://semilattice.ai/blog/fca-comparison) ## New landing page, new colour language, in-app login The entire public face of Semilattice has been rebuilt. New landing page with an interactive decision tree hero, animated product walkthroughs, and a colour system built around indigo, pink, and teal. Login and signup now happen inside the app. ## Decision tool: from question to evidence in minutes New guided flow for product decisions. Describe what you're considering, choose a user model, and Semilattice designs the research, runs it against simulated user models, and returns a report with key insights, survey results, and recommendations. Minutes, not weeks. Built for the moment someone asks on a Sunday whether you should move that feature behind the paywall. [Read more →](https://semilattice.ai/blog/less-noise-in-early-decisions) ## 16 segments of financial life 16 UK Consumer Finance user models, from Growing Families to Just About Managing. Each segment built on real research data with distinct demographics, financial behaviours, and attitudes. Every product decision in consumer finance is a "what if," and the people that matter to you aren't one group. Now you can ask each segment separately. [Explore the segments →](https://semilattice.ai/blog/fintech-user-models) ## Semilattice MCP [Semilattice MCP](/mcp/introduction) lets AI assistants and agents predict how specific user models answer questions. Connect your IDE, your agent framework, or any MCP-compatible tool. Four tools: `list_population_models`, `create_prediction`, `get_prediction`, `wait_for_prediction`. Your AI can ask your user model a question and wait for the answer programmatically. [Connect yours →](/mcp/connect) ## Test batches: evaluate accuracy for your use case New evaluation feature. Upload ground truth data for your specific domain and test how well a population model performs on the questions that matter to you, not just the seed data it was built on. Cross-validation tells you the model's general accuracy. Test batches tell you whether it's accurate *for your problem*. [Learn how →](https://semilattice.ai/blog/test-batches) ## Batches, 3× faster predictions, simplified API `API v1.1.0` · `SDK v0.6.0` #### Batches Group predictions with a name and description. Fetch all predictions in a batch with `/predictions/batch/{batch_id}`. #### Speed Predictions now return in \~20 seconds, roughly 3x faster than before. #### New methods * `GET /populations` — list all available population models * `GET /predictions|tests/batch/{batch_id}` — fetch batch details #### Simplified naming We renamed methods and fields to make the API easier to read. Old names still work but are marked deprecated. * `POST /answers` → `POST /predictions` * `POST /answers/benchmark` → `POST /tests` * `simulated_answer_percentages` → `predicted_answer_percentages` * `kullback_leibler_divergence` → `information_loss` ## The Semilattice API: user insights as infrastructure `API v1.1.0` · `SDK v0.5.2` V1 release. Predict user behaviour like you make database queries. * Create population models with custom seed data * Test model accuracy with built-in cross-validation * Test against external ground truth * Predict new questions [Get started →](/introduction) ## Humans + Time Human systems are complex, emergent, unpredictable, and fundamentally resistant to the modelling techniques that work for physical and biological systems. The human element has held back modelling because we lacked both the data and the computational models to work with it. Large Language Models change this. They contain enough encoded human behaviour to simulate how specific groups of people would respond to questions they've never been asked. That's the foundation Semilattice is built on. [Read the full essay →](https://semilattice.ai/blog/humans-time) ## Introducing Semilattice Semilattice gives you an AI user model that answers questions like they do, in seconds. 15 ready-to-use public models covering tech industry segments, from designers and front-end developers to data scientists and engineering managers. The decision-making balance has tipped toward action and away from research. Computational research tips it back without delaying action. Custom models from your own data. Public models to start immediately. [Read the introduction →](https://semilattice.ai/blog/introducing-semilattice) # FAQ Source: https://docs.semilattice.ai/faq Common questions about Semilattice and how it works. ## General Semilattice tests how your users would react to product decisions before you ship them. It uses real human data to predict how specific audiences would answer questions they've never been asked. A user model represents a specific group of people: UK adults interested in consumer finance, software buyers, developers. It's built from real human data and predicts how that group would answer new questions. There are two kinds: our 50+ ready-made **answers-1** models, which predict audience-level answer distributions, and custom **anacreon** models we build for customers, which model every individual in the audience separately. See [User models](/user-models) for the differences. Every user model is tested and shows its accuracy score in the dashboard. **Anacreon** models are tested on held-out questions per individual and achieve a state-of-the-art ordinal alignment of 0.775, ahead of every published academic baseline. See the [technical report](https://semilattice.ai/research/anacreon). **answers-1** models are tested using leave-one-out cross-validation: each question in the seed data is temporarily removed and predicted as if it were new, then compared to the real answer. Our UK Consumer Finance user models score 90% on this measure. Yes. We'd love to work with you to build a custom **anacreon** model of your users: an individual-level model built from unstructured data like interviews, reviews, and open-ended survey responses, tested for accuracy on held-out questions. All your data and the model itself remains yours. [Get in touch →](https://semilattice.ai/research/anacreon) Short version: we use it to build and operate **your** audience model, and nothing else. Your data is never used to train other customers' models, never accessible to other customers, and never used to train foundation models. We do use aggregate performance metrics (accuracy scores, test results) to improve the methodology of how we build models in general — that is not the same as training on your content. See [Security](/security) and [Privacy](/privacy) for the full detail. Currently single-choice questions, including scales. Anything you'd put in a survey: feature preferences, pricing sensitivity, competitive perception, behavioural intent. The model works best with questions that have distinct answer options. Traditional research takes weeks and costs thousands. Semilattice returns predictions in seconds. It doesn't replace deep qualitative research. It fills the gap between gut instinct and a full study, giving you directional signal before you've committed to a direction. Yes. Create an account and run your first simulation now, no credit card required. The free tier includes 49 free public **answers-1** user models, user research and user journey simulations, unlimited simulations, and access to the app, the MCP, and the API. [Create a free account](https://app.semilattice.ai/auth/sign-up) and run your first simulation now. If you want a custom **anacreon** model of your users, [book a call](https://app.semilattice.ai/user-models/request) about Semilattice Custom and we'll scope it together. # Introduction Source: https://docs.semilattice.ai/introduction Simulate how real users react to product changes, concepts, and decisions. Semilattice is a platform for simulated user and market research. Built around AI models of specific groups of users with transparent accuracy metrics, it lets you run simulated discovery, concept exploration, spec validation, feature prioritisation, message testing, conversion flow optimisation, UX comprehension, and usability testing in minutes. ## How it works 1. **Choose a user model**: Select from 50+ ready-made user models, or [work with us](https://semilattice.ai/research/anacreon) to create a custom **anacreon** model, an individual-level model of your users built from your own data. 2. **Describe your decision**: Tell Semilattice about your product change or marketing plan and the planner will build a structured simulation to validate it with simulated users in minutes. 3. **Act on the results**: Rich simulation results provide net new information for decision-making. Fold the findings into the next version and run a new simulation to validate again. ## Get started No credit card. Run your first simulation in minutes. We'll walk you through it and get you set up. ## Example use cases **Concept testing before you build**: You're considering three pricing tiers. Before committing, you ask your user model how they'd react to each. You get a directional signal in minutes instead of commissioning a survey. **Comparing segments**: You want to know whether first-time buyers and returning customers respond differently to a new onboarding flow. You ask the same question to both user models and compare. **User journey simulation on live products**: Simulated users navigate your live website as specific user segments. You see where they get confused, where they drop off, and what they miss. **Quick signal for a meeting**: You have a product review tomorrow and a hypothesis about messaging. You test it against your user model over lunch and bring evidence to the conversation. **Grounding AI workflows**: Connect Semilattice to Claude, Cursor, or any MCP-compatible tool. Your AI can ask your user model a question mid-conversation. # Connect to Semilattice MCP Source: https://docs.semilattice.ai/mcp/connect Learn how to connect your AI assistant, IDE, or agentic tooling to Semilattice MCP ## URL The Semilattice MCP is a remote server accessible over **Streamable HTTP**. The URL is: ``` https://mcp.semilattice.ai ``` ## Client-specific instructions This list is not exhaustive. Semilattice MCP should work with any client which supports connecting to remote MCP servers over Streamable HTTP with OAuth. **Prerequisuites**: paid ChatGPT subscription 1. Navigate to **Settings** from the account menu (bottom left corner) 2. Click **Apps & Connectors** in left-side nav 3. Scroll to the bottom and open **Advanced Settings** 4. Toggle on **Developer Mode** 5. Go back to **Apps & Connectors** tab 6. Click **Create** in top right of the Connectors section 7. Add a descriptive name like `semilattice` in the **name** field and optionally a description 8. Enter `https://mcp.semilattice.ai` as the **MCP Server URL** 9. Select "OAuth" from the authentication dropdown and leave the "OAuth Client ID" and "OAuth Client Secret" fields blank 10. Check to confirm you understand the warning 11. Go through the authentication flow to create or sign into a Semilattice account with your Google email 12. Navigate back to the main chat interface, click the **+** button under the input field, then select **More** and then **Semilattice** to enable ChatGPT to use Semilattice 🎉 Semilattice should now be ready to use with ChatGPT! **Known issue:** ChatGPT cannot execute multiple tool calls in parallel or sequentially. You have to ask every question separately or prompt ChatGPT to continue the process after every question if it has planned to predict multiple questions. 1. Click the ⚙️ icon in the top right to open settings 2. Click **MCP** from the left nav 3. Click **+ Add** in the top right, then **Quick Create** 4. Give the server a descriptive name like “semilattice” 5. From the **Type** dropdown select **Streamable HTTP (streamableHttp)** 6. In the **URL** field enter the Semilattice MCP URL: ``` https://mcp.semilattice.ai ``` 7. Leave the other fields as they are 8. Click **Save** in the top right 9. Click the toggle in the top right to connect 10. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with Cherry Studio! 1. In a CLI where you have Claude Code installed, before running Claude Code itself, run: ```bash theme={null} claude mcp add --transport http semilattice https://mcp.semilattice.ai ``` 2. Start Claude Code with `claude` 3. Run `/mcp` to list MCPs. You should see `semilattice △ disconnected · Enter to login` 4. Select the Semilattice MCP and hit Enter 5. Select the `Authenticate` option on the next screen 6. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with Claude Code! See the [Claude Code docs](https://code.claude.com/docs/en/mcp) for more info. **Prerequisuites**: paid Claude subscription 1. Navigate to **Settings** from the account menu (bottom left corner) 2. Click **Add custom connector** below the list of Connectors 3. Add a descriptive name e.g. `semilattice` 4. Enter the MCP URL: `https://mcp.semilattice.ai` 5. Leave advanced settings blank 6. Click **Connect** 7. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with Claude! **Prerequisuites**: paid Claude subscription 1. Navigate to **Settings** from the account menu (bottom left corner) 2. Click **Add custom connector** below the list of Connectors 3. Add a descriptive name e.g. `semilattice` 4. Enter the MCP URL: `https://mcp.semilattice.ai` 5. Leave "Advanced settings" blank 6. Click **Connect** 7. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with Claude! 1. Open the Cline plugin in your IDE 2. Find and click the **MCP Servers** button to open the MCP Servers menu 3. Select the **Configure** tab and click **Configure MCP Servers** 4. The `cline_mcp_settings.json` file will open in the editor. Update it to add Semilattice MCP: ```json theme={null} { "mcpServers": { "semilattice": { "type": "streamableHttp", "url": "https://mcp.semilattice.ai" } } } ``` 5. Save the file and Semilattice MCP should appear in the Cline plugin interface 6. Click **Authenticate** in the Cline interface 7. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with Cline! **Prerequisuites**: paid ChatGPT subscription 1. Open the Codex config file, usually located at `~/.codex/config.toml`. If you are using the IDE extension, you can find the config file by clicking the gear icon in the top right corner of the extension and then clicking **MCP settings** > **Open config.toml**. 2. Update the config to add Semilattice MCP and enable OAuth authentication: ```toml theme={null} [features] rmcp_client = true # enables OAuth authentication [mcp_servers.semilattice] url = "https://mcp.semilattice.ai" ``` 3. Before running codex itself, run: ```toml theme={null} codex mcp login semilattice ``` 4. Go through the authentication flow to create or sign into a Semilattice account with your Google email 5. Start codex. You should see a brief message saying it’s connecting to Semilattice MCP. Run `/mcp` to verify connection. 🎉 Semilattice should now be ready to use with Codex! See the [Codex docs](https://developers.openai.com/codex/mcp) for more info. 1. Click [this link](cursor://anysphere.cursor-deeplink/mcp/install?name=semilattice\&config=eyJ1cmwiOiJodHRwczovL21jcC5zZW1pbGF0dGljZS5haSJ9) to add Semilattice MCP to Cursor 2. In Cursor, click **Install** to confirm adding Semilattice MCP 3. Click **Connect** to authenticate 4. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with Cursor! The above process will add the Semilattice MCP to your `mcp.json` file. You can also skip the steps above and edit this directly: ```json theme={null} { "mcpServers": { "semilattice": { "url": "https://mcp.semilattice.ai", "headers": {} } } } ``` See the [Cursor docs](https://cursor.com/docs/context/mcp) for more info. 1. Open your `settings.json` file, usually found at `~/.gemini/settings.json` 2. Add Semilattice MCP: ```json theme={null} { ...other config "mcpServers": { "semilattice": { "httpUrl": "https://mcp.semilattice.ai" } } } ``` 3. Start or restart Gemini CLI with `gemini` 4. Authentication should be triggered automatically, if not run `/mcp auth semilattice` 5. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with Gemini CLI! See the [Gemini CLI docs](https://geminicli.com/docs/tools/mcp-server/) for more info. 1. Select **Extensions** from the left-nav 2. Click **Add custom extension** 3. Enter a descriptive name like `semilattice` 4. Select **Streamable HTTP** from the **Type** dropdown 5. Enter the Semilattice MCP URL in the **Endpoint** field: ``` https://mcp.semilattice.ai ``` 6. Leave other fields blank and click **Add Extension** 7. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with goose! 1. Update your `librechat.yaml` file to add Semilattice MCP: ```yaml theme={null} mcpServers: semilattice: type: streamable-http url: https://mcp.semilattice.ai requiresOAuth: true ``` 2. In LibreChat, click the MCP dropdown in the main prompt input field 3. Click the 🔑 key icon next to Semilattice 4. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with LibreChat! See the [LibreChat docs](https://www.librechat.ai/docs/features/mcp) for more info. 1. Open the VSCode command palette: `Shift` + `Command` + `P` (Mac) or `Ctrl` + `Shift` + `P` (Windows/Linux) 2. Type "mcp" and select the **MCP: Add Server...** option 3. Select the **HTTP (HTTP or Server-Sent Events)** option 4. Enter the Semilatatice MCP URL: `https://mcp.semilattice.ai` 5. Enter "semilattice" or another descriptive name when prompted for a Server ID 6. Choose whether to add the MCP globally or just to the current workspace 7. Go through the authentication flow to create or sign into a Semilattice account with your Google email 🎉 Semilattice should now be ready to use with VS Code! The above process will add the Semilattice MCP to your `mcp.json` file. You can also skip the steps above and edit this directly: ```json theme={null} { "servers": { "semilattice": { "url": "https://mcp.semilattice.ai", "type": "http" } }, "inputs": [] } ``` See the [VS Code docs](https://code.visualstudio.com/docs/copilot/customization/mcp-servers) for more info. ## Clients with known problems We're aware that the following clients don't support remote MCP servers with OAuth authentication: * ChatGPT desktop * Continue * Gemini web * Kiro * n8n * OpenCode * Pipelex * Roo Code * Windsurf * Workato * Zed ## Trouble connecting? As MCP is still a young protocol, clients and servers can sometimes have difficulty connecting. If you're experiencing issues with a specific chatbot, agent platform, or IDE, please email us and we'll be happy to investigate: ``` support@semilattice.ai ``` # Introduction Source: https://docs.semilattice.ai/mcp/introduction Use Semilattice from your AI assistant or coding agent. The Semilattice MCP server lets you simulate how real users react to product changes, concepts, and decisions. Use it for discovery, concept validation, feature prioritisation, message testing, conversion flow optimisation, UX comprehension, and usability testing.