# Product Docs Product documentation for Beye.ai [Beye.ai](https://beye.ai/) is the Generative BI platform transforming **data into decisions**, streamlining workflows with collaborative analytics for 10x efficiency and growth. Our Conversational Analytics platform empowers business users to create high-fidelity analytic content efficiently and reliably. As a comprehensive end-to-end platform, we support our customers through every step of the business intelligence workflow, from data ingestion to secure, collaborative analytics creation, packaging, and publishing, leveraging AI and intuitive workflows to make analytics self-serve, and oriented on finding the answers from data.
### Contact Support If there is something you need help with that is not available in the Learning Center, please feel free to contact us at . Provide detailed information about the issue, including screenshots or descriptions, and someone from our team will get back to you as soon as possible. [**© 2025 Beye Analytics Inc. DBA Beye Inc. All Rights Reserved | Confidential**](#user-content-fn-1)[^1] [^1]: # Authentication Customers can authenticate via Magic Link, Google, or Microsoft Each customer has a dedicated workspace login provided as part of onboarding process, where the business email domain is authorized and initial members requiring access are provided entry. From here, workspace admins have complete control over user management and permissions within their workspace. #### Magic Link Authentication 1. Enter your email address on the login page. 2. You will receive an email from Beye with a magic link. 3. Click the link in your email to sign in securely. #### Google Authentication 1. Select the option to log in with Google. 2. Authenticate using your Google credentials to access the platform. #### Microsoft Authentication 1. Select the option to log in with Microsoft. 2. Authenticate using your Microsoft credentials to access the platform. ### User Management * **Admin Controls**: Workspace admins can add, remove, and manage user permissions, ensuring that only authorized personnel have access to sensitive data and functionalities. * **Initial Access**: Initial members are granted access based on the authorized business email domain, streamlining the onboarding process for new users. By leveraging these authentication methods, Beye ensures a secure and seamless login experience for all users, while giving admins the tools they need to manage their workspace effectively.
# Analyst AI Agent Skill Library How to leverage our AI engine to answer analytical questions of your data with high accuracy ### Status Quo Business Intelligence Let’s put the business value into the context of a typical day in the life of a supply chain analyst as an example persona. For instance, a supply chain analyst who needs to report on product availability often has to submit a ticket, which is then prioritized by a project manager. Data engineers must write SQL queries to extract data from systems like SAP, and report writers create dashboards in tools like Power BI. The process is often iterative, with gaps between requirements gathering and final delivery. Do you get your question answered? Possibly—but it frequently requires multiple rounds of refinement and iteration. By the time the report is ready, days or weeks may have passed, and the opportunity to make an impactful decision may have already slipped by. This process is complex, time-consuming, and involves multiple teams and tools. It’s inefficient and frustrating for everyone involved. ### Generative Business Intelligence We created a platform that empowers non-technical users—like business analysts, financial planners, supply chain managers, and more—to ask and answer complex data questions on their own, without needing to write code or rely on IT teams for routine tasks. By simplifying these processes, IT teams are freed up to focus on higher-value, organizationally critical initiatives, such as digital transformation and strategic innovation, rather than managing routine data requests. Our goal is to simplify and accelerate your decision-making process. By doing so, we increase overall productivity and enable IT resources to contribute to broader, impactful projects. Ultimately, Beye transforms the way your organization leverages data, leading to better productivity, faster insights, and reliable decisions. ### AI Skills * Data Modeling * SQL * Generative Dashboards * Data Explainability * Anomaly Detection By deeply understanding the workflows of analyst type personas and the skills required to get insights from organizations data, we leverage the above skills to break down questions into smaller chunks and ensure the answers generated by the Beye brain. # AI Data Management AI-first, proprietary ELT layer optimized for analytic workloads The reason why customers are required to send data to Beye.ai is the following: 1. Performance and reliability: Our infrastructure is optimized for analytic workloads, querying large volumes of data and processing it. Also, as part of our ELT model, we have built in capabilities to report on potential data quality issues, data lineage tracking, and anomalies which all can help your data security and management posture. 2. Accelerate the time to onboard and implement: By leveraging the Beye architecture, we can leverage our onboarding automation to implement quickly and reliably 3. Upstream AI-first Capabilities: With data present in Beye, and as historical data grows, we can build on statistical metadata layer that powers our AI engine. With this, users can leverage our no-code capabilities to do data transformations, cleansing and create analytic views all with AI. Setting up ELT Configuration for a Workspace **Transfer files to the storage location**: * Server (S3 Endpoint): storage.googleapis.com * Bucket Path: To be provided by Beye Team * Access Key: To be provided by Beye Team * Secret Key: To be provided by Beye Team 1. For every Customer Workspace, there is a dedicated (ELT) configuration page (see below). The view of this ELT, is limited to the **Workspace Owner** role type.

ELT Option in Workspace Menu

2. Once you click ELT, you can click **Upgrade** (see screenshot below). This will provide you with private information to your dedicated, secure file store location.
Step 1: Install Cyberduck 1. Go to the Cyberduck website: [https://cyberduck.io](https://cyberduck.io/). 2. Download and install Cyberduck for your operating system (Windows or Mac). 3. Open Cyberduck once the installation is complete. Step 2: Configure the Connection 1. In Cyberduck, click Open Connection (at the top of the main window). 2. From the dropdown menu, select Amazon S3 as the connection type. 3. Fill in the required fields: * Server: storage.googleapis.com * Bucket Path: To be provided by Beye Team * Access Key ID: To be provided by Beye Team * Secret Access Key: To be provided by Beye Team. Step 3: Test the Connection 1. Click Connect to establish a connection to the storage bucket. 2. If the connection is successful, you will see the contents of the bucket (it may be empty if no files have been uploaded yet). 3. If you encounter an error, double-check the server, bucket path, and credentials. Step 4: Upload Files 1. Locate the files on your computer that you need to upload. 2. Drag and drop the files directly into the Cyberduck window. * Alternatively, you can click the Upload button, browse for the files, and select them for upload. 3. Cyberduck will start uploading the files. You can see the progress in the Transfers window. # Change Language/Date Settings Update User Settings to Change Date Format Setting ### Description Because our user community is global, we’ve updated the Beye platform so you can set your own date preferences for each workspace. Workspaces inherit the system defaults by default, but you can override them at any time in your personal settings. ### Step 1: Go to User Settings

User Account Settings

### Step 2: Date Formatting

Account Settings - Formatting Section

### Step 3: Go Back to Workspace

Select Workspace from Dropdown

### Language Settings
# Iterative AI Mode Conversational analysis with human-in-the-loop approval ### Summary Iterative mode is the fast, back-and-forth workspace for exploring a question, refining it, and checking the AI’s work before you share it. It keeps short-term memory inside the thread, returns quick previews for tables/charts to keep latency and cost low, and lets you **review & approve** results before they appear in the Message window. Scalars (e.g., “Sales for 1H 2025 was **X**”) run against full data; preview tables/charts are lightweight. Once you’re happy, approve and (optionally) send the work to **Data Studio/GenViz** to build polished analytic content that runs on the full dataset. ### How to get here (UI path) * **Workspace → Channel → Iterative AI** 1. Open your **Workspace** 2. Choose the **Channel** bound to the right Dataverse 3. Click the **Iterative AI** tab/mode 4. Ask your question to start a thread
*** ### Human-in-the-loop workflow (review → approve → share) 1. **Ask** a question and iterate: follow-ups, filters, drilldowns. 2. **Review** the answer in the thread and (where available) check the **Building** panel for logic/SQL transparency. 3. **Approve** to commit the result to the **Message** window (nothing shows to others until you approve). 4. After approval you can: * **Publish** as a Message to the channel * **Pin** important insights * **Share** a view-only link * **Clone** the Message for another audience * **Open in Data Studio / GenViz** to build cards, summary tables, and charts (full-data execution) *** ### Data scope & performance model (preview vs full) * **Scalars = Full data.**\ Examples: totals, averages, single-value KPIs (“Sales for 1H 2025”, “Avg tariff rate last quarter”). These are computed on the full Dataverse so the number you quote is authoritative. * **Tables & charts = Preview by default.**\ To keep **latency low** and the **cost of iteration** minimal, tabular and visual results render from a **sampled/subset preview** while you’re exploring. This is ideal for trying different filters, time ranges, or group-bys rapidly. * **Promote to full data when ready.**\ Once the preview looks right and you **approve**, you can: * run the query on **full data**, or * **hand off to Data Studio/GenViz**, where the visualization/metric is materialized against the full dataset and saved as reusable analytic content. * **Clear indicators.**\ The UI differentiates **Preview** vs **Full** so you always know the data scope behind a result. *** ### What Iterative is best for * Rapid exploration when you don’t know the exact question yet * Multi-turn refinement (e.g., “Explain margin dip → by region → last 6 months → call out anomalies”) * Quick “sanity-check” views before promoting to a full run * Multiple concurrent **threads** within a channel (rename, pin, revisit) *** ### Prompting patterns that work * **Start broad, narrow down:** “Show landed cost by supplier over the last 12 months → add YoY → filter to >$250K purchases → group by category.” * **Ground definitions:** “Use *landed cost* = base + tariff + freight; treat Tier-1 as ‘priority suppliers’.” * **Ask for preview sizes:** “Return a **preview table** (10–20 rows) with Supplier, Orders, Landed Cost, Tariff %.” * **Validate assumptions:** “List the business rules you applied and show the SQL/logic you generated.” * **Promote when ready:** “Looks good—**run on full data** and summarize in 3 bullets.” *** ### Quality checks before you hit **Approve** * **Metric definition** matches your business lexicon (e.g., landed cost formula) * **Filters & time range** are correct (currency/units too) * **Grouping & sort** reflect how you’ll present the result * **Preview vs full**—decide if it’s still exploration (keep preview) or ready to **promote to full** / **open in Data Studio** *** ### When to move to Data Studio / GenViz * You want **production-grade** cards, summary tables, or charts * You need **full data** across heavy joins, longer time windows, or governed measures/dimensions * You plan to **reuse** the metric/visual in messages or other channels *** ### Managing threads * **One topic per thread** to keep the short-term memory clean * **Rename** meaningful threads, **pin** important ones * **Clone** a Message to tailor for a different audience without losing the original context *** ### Troubleshooting * **Answer looks off** → confirm you’re in the right **Channel/Dataverse**; restate key definitions; ask to **show assumptions** * **No rows returned** → relax filters or extend the date range; request a **wider preview** * **Slow response** → reduce scope (recent period, fewer dimensions) or stay in preview until ready for full data # OneShot AI Mode Deep analysis in one go ### Summary **OneShot** is for when you have a specific question and want the **Generative BI AI agent** to do more work up front. It spends \~30 seconds (often less/more depending on scope) on **reasoning and validation** to return a polished package in a single shot: an **executive summary**, **headline metrics**, **supporting tables/charts**, and **suggested follow-up questions**. It’s ideal for updates to leadership, status readouts, or when you already know the outcome you want. ***
### How to get here (UI path) * **Workspace → Channel → OneShot AI** 1. Open your **Workspace** 2. Choose the relevant **Channel** (bound to the right **Dataverse**) 3. Click the **OneShot AI** tab/mode 4. Enter a pointed question and press **Enter** *** ### What OneShot does (under the hood) * **Frames the task:** interprets your question, aligns to your **Dataverse** (business lexicon, measures/dimensions, KPI definitions). * **Validates assumptions:** checks time grain, filters, and metric formulas (e.g., *landed cost* = base + tariff + freight). * **Runs a deeper pass:** aims to compute **scalars on full data** and compile **supporting artifacts** (tables/charts). If a visual would be heavy, it may render a **preview** first and offer “Promote to full data.” * **Packages results:** returns an **executive summary** (what happened + why), **key drivers/outliers**, **supporting views**, and **suggested next questions**—ready to share or promote to **Data Studio/GenViz**. *** ### When to use OneShot (vs. Iterative) * You **know your question** and want a “finished” answer in one go. * You’re preparing a **leadership update** and need a crisp narrative with supporting views. * You’re okay with the agent doing **more reasoning/validation** up front to save back-and-forth steps. * You plan to **publish immediately** or **hand off to Data Studio** for production-grade visuals. *** ### What you can do here (at a glance) * Get an **Executive Summary** that explains the result in plain language. * See **headline metrics** (scalars calculated on full data whenever feasible). * Review **supporting tables/charts** (preview or full, depending on complexity). * Use **Suggested Follow-up Questions** to extend the analysis in one click. * **Approve** the package and then **Publish / Pin / Share / Clone / Open in Data Studio (GenViz)**. *** ### Prompting patterns that work * **Be specific:**\ “Give me an executive summary of **1H 2025 revenue**: YoY change, top 5 drivers, and 3 risks to watch.” * **Define outputs:**\ “Return **3 bullet insights**, **2 KPI scalars** (Revenue, Gross Margin %), and **1 chart** (YoY by month).” * **Ground definitions:**\ “Use **landed cost** = base + tariff + freight; treat Tier-1 as ‘priority suppliers’.” * **Constrain scope:**\ “Focus on **US Retail**, **last 6 months**, exclude returns.” * **Ask for checks:**\ “List **assumptions** you applied and show the **logic/SQL** used.” * **Request next steps:**\ “Add **Suggested Questions** I should ask next and recommend a **Data Studio** visual.” *** ### Example walkthrough (executive readout) 1. **Ask:** “Provide a one-page executive summary of **Q2 revenue**: YoY growth, top 3 drivers, and 2 risks; include a small table of the top 10 SKUs by GM%.” 2. **OneShot returns:** * **Executive Summary** (narrative + bullets) * **KPI scalars** (Revenue, GM%, YoY%) * **Driver analysis** (categories/regions/vendors) * **Top 10 table** (preview or full) * **Suggested Questions** (e.g., “Drill into underperforming region”, “Show mix shift”) 3. **Review & Approve:** Check the **assumptions/logic** panel; ensure date ranges/filters are correct. 4. **Publish/Pin/Share** or **Open in Data Studio** to materialize the table/chart on **full data** and reuse the visual. *** ### Data scope & performance (how results are computed) * **Scalars:** calculated on **full data** whenever feasible (authoritative numbers for comms). * **Tables/charts:** OneShot attempts a **full run** when within guardrails; if heavy, it will **render a preview** and offer **Promote to full data** or **Open in Data Studio** to materialize at scale. * **Clear indicators** show whether an artifact is **Preview** or **Full** so you know what you’re sharing. *** ### Quality checks before you **Approve** * **Metric definitions** match your business lexicon (measures/dimensions, KPI formulas). * **Filters/timeframe/currency** reflect the intended audience. * **Preview vs Full:** promote visuals that must be production-grade; keep exploratory views in preview. * **Narrative accuracy:** executive summary aligns with the evidence in the supporting views. *** ### Moving work forward * **Approve → Publish:** Create a Message in the Channel. * **Pin** key findings for visibility. * **Share** a view-only link with stakeholders. * **Clone** to tailor the message for different audiences. * **Open in Data Studio / GenViz** to turn the outputs into reusable **cards, summary tables, and charts** that run on full data. *** ### Troubleshooting * **Takes too long / times out:** Narrow scope (recent period, fewer dimensions) or request a **preview** visualization. * **Narrative feels off:** Restate/lock definitions, specify the comparison basis (YoY vs QoQ), and ask the agent to list **assumptions**. * **Missing artifact:** Explicitly ask for it (“Include a 10-row table with Supplier, Orders, Landed Cost, Tariff %”). * **Heavy visuals needed:** Approve, then **Open in Data Studio** to materialize on full data. # May 31, 2026 Meet Claude Opus 4.8, now the default model, plus real-time workspace navigation. This release adds Claude Opus 4.8 and improves the reliability of your workspace navigation. #### New **Claude Opus 4.8.** Anthropic's most capable model, offering its deepest reasoning with faster output, is now available across the business intelligence experience and is the default selection in the model picker. It is fully localized across all supported languages. #### Improved **Real-time sidebar.** Channels and dataverses in the sidebar now update in real time and stay consistent across your workspace, so your navigation always reflects your latest changes. #### Fixed **Channel switching.** Resolved an issue where switching between channels could display an error while loading the conversation. Moving between channels is now reliable. # January 9, 2026 #### ✨ Features * Add `json_data` field to `JsonToClassResponse` for direct dict access * Add `json-repair` library for handling malformed LLM JSON responses * Add tracing and error handling to `json_to_class` function #### 🔧 Refactoring * Refactor message-window to use `json_to_class` for robust JSON parsing * Use `json_data` instead of `json_string` for dict operations #### 🐛 Bug Fixes * Add qs override to address CVE security alert * Use json\_data for dict access and add error tracing in message-window #### 📦 Dependencies * Add `json-repair` 0.55.0 * Add `cachetools` and upgrade `pymongo` * Upgrade `google-cloud-bigquery`, `google-genai`, `sentry-sdk` * Update Python dependencies #### 🧪 Testing * Add comprehensive unit tests for `json_to_class` function * Add tests for `json_data` field in `JsonToClassResponse` * Expand E2E test coverage for core workflows #### 🔄 CI/CD * Upgrade Node.js version from 22 to 24 in Playwright * Upgrade GitHub Actions and add project documentation #### 🔒 Cleanup * Remove debug logging for `REDIS_URI` # January 6, 2026 **Release Highlights** Greetings from the **Beye.ai** team! 👋\ This release is a major step forward for AI powered dashboarding, bringing richer card generation, a smoother message window experience, and a wide set of reliability and quality improvements across the platform. *** **✨ New Features** • **AI Powered Dashboarding** — Generate dashboards with smarter, more complete dashboard cards designed to turn conversations into actionable views\ • **Improved Message Window Experience** — Refined chat processing and display blocks for clearer answers and a more consistent conversation flow\ • **Upgraded Dashboard Components** — Enhanced dashboard cards, prompts, and visualizations for a more polished and usable analytics experience\ • **New Dashboard Prompt Library** — Introduced versioned prompt chains for dashboard generation so improvements can ship faster and more safely over time **🛠️ Enhancements** • **Faster, simpler API connectivity** — Streamlined request handling and removed a legacy networking dependency for a lighter, more maintainable stack\ • **Stronger SQL coverage across engines** — Improved query handling and syntax support for broader compatibility and fewer surprises\ • **More resilient integrations** — Updates to cloud data access, secret handling, and data processing utilities to improve stability at scale\ • **Smoother charts and dashboards** — Better chart tooltips, dashboard card rendering, and caching for a snappier UI\ • **Expanded localization** — Updated translations across English, Arabic, German, Spanish, and French for a more consistent experience **🐛 Bug Fixes** • Improved error handling and safer fallbacks across data and query workflows\ • More consistent behavior in message window blocks and dashboard loading scenarios **🧪 Tests** • Significant test expansion across core API modules\ • New coverage for AI helpers and message window behavior\ • Improved testing utilities to catch regressions earlier **📦 Chores** • Dependency updates across backend and web apps for security and performance\ • Configuration and build system refresh for a smoother release pipeline\ • Monitoring and health check updates for better operational visibility *** Thanks for your continued feedback and partnership. Together we are making **Generative BI** more powerful, more dependable, and easier to operationalize every week. 😊 # October 7, 2025 **Release Highlights — v0.463.0** Greetings from the **Beye.ai** team! 👋\ This update brings precision exports, smarter model options, faster variable search, and subtle UI cues that make analytics feel more fluid. Here is the customer-facing roundup. 🚀 *** **✨ New Features** • **Precision Excel export** — Download exactly what you see at the cell level, with the file name automatically reflecting the selected cell\ • **More model choices in visuals** — New options in visualization prompts, including support for the latest GPT-5 Pro and Codex family models\ • **Faster variable picking** — Debounced search and improved field and value filters in Playground variables\ • **Inline data type icons** — Clear Bool and Timestamp badges across tables and message views for quicker scanning\ • **Simpler message routing** — Channel binding streamlined for more predictable behavior **🛠️ Enhancements** • File downloads are delivered with a modern response flow for greater reliability and consistency **🐛 Bug Fixes** • Model parameters are applied only where supported for greater compatibility\ • Decimal values render consistently in JSON-backed views to avoid rounding surprises **🧪 Tests** • New coverage for dataverse field filtering\ • Extensive SQL validation tests to catch issues earlier **📦 Chores** • Dependency and tooling refresh across the stack for stability and performance\ • Noisy internal warnings have been quieted for cleaner logs *** Thanks for your continued feedback and partnership. Together we are making **Generative BI** faster, clearer, and more dependable every week. 😊 # October 6, 2025 **Release Highlights — v0.462.0** Greetings from the **Beye.ai** team! 👋\ This release deepens our Iterative AI experience, sharpens context engineering, and adds a streamlined Salesforce-to-warehouse pipeline—plus lots of polish and reliability upgrades. Here’s the customer-facing roundup. 🚀 *** **✨ New Features** * **Iterative AI, now clickable** – Jump back to earlier answers, revisit branches, and re-enter a prior step in the conversation thread with a tap. * **Richer Dataverses** – Cleaner UI and descriptive context fields help the AI understand dimensions and terminology for more accurate, on-topic answers. * **Upgraded Iterative AI Prompts** – “Conversational analyst” responses now provide more strategic, data-referenced guidance. * **Model Evaluation Option** – Added a leading frontier model to our evaluation framework to test fit with our mixture-of-experts approach. * **Salesforce → Warehouse Pipeline** – A new ingestion path moves Salesforce data into your warehouse for analysis, with efficient staging and loading. * **Message Controls** – Stage and select AI chat messages before sending; backend message handling supports additional metadata for smoother workflows. **🛠️ Enhancements** * **Faster Building Blocks** – Searchable variables panel, accordion column editor, and clearer tooltips. * **Refined Layout & Typo­graphy** – Better spacing, readability, and two-way bindings for a more responsive feel. * **Label & UX Tweaks** – Updated model labels/messages, improved send-message flow, dynamic status and elapsed-time displays. * **Governance Hooks** – Finer-grained logging and permission checks around AI features. **🔒 Reliability** * **Graceful Rate-Limit Handling** – Automatic retries for third-party model rate limits. * **Hardened Ingestion** – Safer Salesforce paths and better artifact organization. * **Up-to-date Stack** – Dependency upgrades across the board. **🧪 Tests** * End-to-end coverage for Salesforce utilities and staging. * Validation for Parquet upload/load flows. * Identifier and SOQL validation checks to prevent malformed queries. *** Thanks for your continued feedback and partnership. Together we’re making **Generative BI** more strategic, reliable, and collaborative every week. 😊 # September 29, 2025 **Release Highlights — v0.460.0** Greetings from the **Beye.ai** team! 👋\ This release adds a consultative answer path, real time workspace presence, and smoother system initiated actions, plus polish across guidelines, auth, and reliability. Here is the customer facing roundup. 🚀 *** **✨ New Features** • **Slack run alerts:** Receive notifications in Slack when data workflows start, succeed, or fail\ • **Consultative answers:** A non SQL response option that gives concise guidance grounded in your metadata and context\ • **System sessions:** Secure system initiated actions with proper authorization for automation and background tasks\ • **Presence indicators:** Online and offline badges across messages, channels, and member lists for faster collaboration **🛠️ Improvements** • **Safer analytics defaults:** Updated SQL and dashboard guidelines for clearer time handling, safer calculations, and visualization ready outputs\ • **Goal context anchoring:** Goals can briefly set context when it is relevant to the conversation\ • **Clearer labels and flows:** Refined account and menu labels for less guesswork **🐛 Bug Fixes** • More reliable refresh when adding messages so updates appear consistently\ • Prevented early exits during refresh scenarios **📚 Documentation** • Added the consultative path to our flow and revised output specifications for expected formats **🌍 Localization** • New keys and updated warnings across English, German, Arabic, and Spanish and French for Thinking and Thought strings **🔧 Refactor** • Centralized session creation and authorization for consistent handling across system APIs\ • Connection refresh now includes workspace, dataverse, and connection identifiers for clarity **🧪 Tests** • Clearer wording for LLM test cases to reflect expected behavior **📦 Chores** • Slack integration setup and dependency updates across backend and web\ • General dependency and tooling refresh including auth, monitoring, editors, and TypeScript ESLint\ • Added proof of concept dependencies for a future Salesforce integration *** Thanks for partnering with us. Your feedback keeps **Generative BI** getting smarter every week. 😊 # August 18, 2025 #### August 18, 2025 **Release Highlights — v0.441.0** **Release Highlights** Greetings from the **Beye.ai** team! 👋\ This release introduces powerful AI modes for business workflows, real-time workspace presence, and a host of polish across the experience. Here’s the customer-facing roundup. 🚀 *** **✨ New Features** * **Iterative AI Mode (Guided Workflows)** – Purpose-built, step-by-step context engineering to tackle operational and supply-chain analyses using taught methodologies. Great for multi-step “why/what-if” investigations that build on prior answers. * **One-Shot AI Mode (Rapid Answers)** – A streamlined, single-prompt path for quick fact-finding and fast visuals when you know exactly what you need. * **Revamped Message Window** – Cleaner responses, better routing, richer context building, and reliable fallbacks so conversations stay on track. * **Presence & Collaboration** – See who’s **online/offline** across your workspace with status badges on messages, channels, and member lists. * **Guided Visualization Prompts** – Structured prompts help you request the right chart the first time; paired with **automatic SQL formatting** for readable, consistent queries. * **Faster Workspace Setup** – A simplified create/update flow and clearer workspace labels make getting started (or reorganizing) a breeze. * **Agent Step Insights** – Hover on AI replies to view per-step timing, offering lightweight transparency into how answers were assembled. **🛠️ Improvements** * **Safer Data Connections** – Tighter scoping for BigQuery connections. * **Snappier UI** – Skeleton loaders for “in-progress” blocks and refined Markdown/SQL display for smoother reading. * **Clarity Pass** – Updated account and menu labels to reduce guesswork and improve navigation. **🌍 Localization** * New phrases and updated warnings across **English**, **German**, and **Arabic** so every message matches your chosen language. **⚙️ Under the Hood** * Streamlined build and dependency management for faster, more reliable releases. * Broader caching improvements and tooling updates that keep performance crisp. *** Thanks for your continued feedback and partnership. Together we’re making **Generative BI** faster, clearer, and more collaborative every week. 😊 # August 4, 2025 #### August 4, 2025 **Release Highlights — v0.438.0** Greetings from the **Beye.ai** team! 👋\ Today’s update focuses on giving you more control over large data sets, richer conversational context, and even smarter analytics prompts—while we keep performance and reliability humming behind the scenes. 🚀 *** **✨ New Features** * **Flexible Table Views** – Pick the page size that works for you (10, 25, 50+ rows) with an easy selector on every data table. * **Message Time-Stamps** – Chat threads now show a subtle clock icon and footer so you can see exactly **when** each message was sent. * **Helpful Conversation Starters** – Admin and chat APIs now surface suggested follow-up questions and support paginated results for smoother scrolling. * **Power Prompt Library** – A full set of ready-made prompt chains and templates lets you spin up advanced business-analytics or conversational AI flows in seconds. * **Self-Updating AI Prompts** – Behind-the-scenes versioning ensures you’re always running the latest prompt configurations without manual updates. **🛠️ Improvements** * **Tuned Caching** – Smarter cache logic handles more data types and respects expiration rules, keeping dashboards fast and fresh. * **Modular AI Chains** – Refactored natural-language pipelines make it easier (and faster) for the platform to combine variables and context on the fly. * **Streamlined Data Retrieval** – Cleaner channel and message interfaces reduce load times, while SQL utilities better preserve row-limit logic. * **CI / CD Polish** – Faster build triggers and artifact handling keep releases rolling out smoothly. **🐛 Bug Fixes** * Squashed text-display typos and localization inconsistencies. * Fixed rare serialization issues that could affect cached lists. **📚 Documentation & Style** * Added step-by-step guides for prompt versioning, pre-commit hooks, and local setup. * New translations and warning messages across the app. * Minor code-style clean-ups for long-term maintainability. **⚙️ Under the Hood** * Dependency upgrades on both frontend and backend for the latest security patches. * Expanded automated test suites covering cache logic, SQL helpers, and UI components. *** Thanks for being part of our journey! Your feedback powers every release and helps make **Generative BI** better each week. 😊 # July 28, 2025 #### July 28, 2025 **Release Highlights — v0.436.0** Greetings from the **Beye.ai** team! 👋\ Today’s release brings a sleeker interface, richer localization, and a smoother sign-in flow. Here’s the customer-facing roundup. 🚀 *** **✨ New Features** * **Smart Tables** – Data tables now display branded loading, error, and “no data” states and refresh themselves faster after changes. * **Full-Spectrum Localization** – Hundreds of new phrases translated across admin panels, ELT workflows, and user settings; English, Arabic, and German are now fully covered end-to-end. * **Branded Avatars** – Message windows now show crisp company and user avatars for a friendlier chat experience. **🛠️ Enhancements** * **Unified Sessions** – A single, streamlined sign-in/session handler keeps you logged in seamlessly across the entire app. * **Quicker Dashboards** – Smarter caching delivers fresher data and faster load times. * **UI Polish** – Refined tooltips, sidebars, and tables for better readability and accessibility. **🐛 Bug Fixes** * Corrected minor text errors and ensured every message respects your chosen language. * Fixed edge-case layout quirks in tooltips, sidebars, and data tables. **⚙️ Under the Hood** * Centralized authentication logic reduces complexity and boosts reliability. * Dependency and toolchain upgrades keep the platform secure and snappy. * Expanded test coverage on caching utilities catches issues before they reach you. *** Thanks for partnering with us! Your feedback keeps **Generative BI** getting smarter every week. 😊 # July 23, 2025 #### July 23, 2025 **Release Highlights — v0.431.0** Greetings from the **Beye.ai** team! 👋\ This week’s full deploy (7/23) and two fast-follow hotfixes (7/24 & 7/25) add powerful new capabilities, polish the experience, and tighten reliability. Here’s the customer-facing recap. 🚀 *** **✨ New Features** * **File Management** – Delete ELT files directly from the table, complete with confirmation dialogs and graceful error handling. * **Paginated ELT Status Board** – A new Convex-powered table lets you page through large ELT job histories without slowing down. * **Multilingual Experience** * Users can now set their preferred **language**, synced end-to-end. * **Arabic** joins **English** and **German** as fully supported UI languages. * **Role-Based Admin Settings** – A dedicated workspace admin panel that appears only for authorized users. * **Smarter Chat Context** – Extended chat history retrieval gives the Gen-BI agent richer context for answers. * **Locale-Aware URLs** – Every in-app link now respects the user’s language and region for consistent routing. * **Searchable Select Boxes** – Quickly locate options with inline filtering. **🛠️ Enhancements** * **End-to-End Localization** – Hundreds of UI strings across messaging, dashboards, and settings are now fully translatable. * **Dashboard & Markdown Rendering** – Faster load times, clearer error states, and more robust SQL execution inside markdown blocks. * **Template Variables** – Text templates now leverage user attributes *and* recent chat history for more personalized replies. * **Navigation & Sidebar** – Links and labels adapt automatically to the active locale and user role. * **Environment-Aware Logging** – Rich detail in development; quiet in production. * **Error Resilience** – Added early-return guards for missing dashboard content and improved fallback messaging. **🐛 Bug Fixes** * Removed edge-case crashes in dashboard and message components when underlying content fails to load. * Hardened SQL markdown blocks against invalid queries, surfacing clear error messages instead of generic failures. **🔧 Hotfixes** * **7/24 – Variable Health Monitor** * New Airflow DAG periodically checks mission-critical environment variables and logs discrepancies. * Secret/variable retrieval API now returns both **value** *and* **source** for easier debugging. * **7/25 – Documentation Boost** * Expanded **SQL date-query guidelines** with best-practice patterns for rolling windows, YTD, ambiguous months, and more. **📦 Dependency Updates & Housekeeping** * Upgraded security linters and introduced `autoflake` for cleaner code. * Refreshed VS Code workspace configs; removed obsolete files. * Internal refactors replaced custom markdown parsing with a dedicated renderer and centralized localization logic. *** Thanks for partnering with us! Your feedback keeps **Generative BI** getting smarter every week. 😊 # April 28, 2025 Release v0.416.0 Greetings from the Beye.ai team! 👋 We've got some exciting updates to share with you in this release. Let's dive in! 🚀 ### ✨ Enhancements #### **Date Locale Configuration** * At a user level, you can now go to user settings and update the format of dates when using our Generative BI application. Default is system settings, but it can be overrided. **Improved SQL Skill with our Generative BI Agent** * Ability to handle week, month, quarter definitions when filtering data from different SQL dialects. **Inventory Balancer - Advanced Skill Update** * Add more columns for data explainability (pre/post change comparisons) Filtering of Data on GenViz Dashboards * Prepping GenViz dashboard config and general cleanups to allow for clickable content to filter down data ### 🔐 Security * Latest Security Patches * We've installed the latest security patches and packages to keep your data safe and secure. ### 🐛 Bugs * General Improvements * Thanks to your valuable feedback, we've squashed some bugs to enhance the overall performance of the platform. As always, we love hearing from you! Don't hesitate to reach out with any feedback or suggestions. Let's keep making Beye.ai better together! 😊 # February 18, 2025 Release v0.401.0 Greetings from the Beye.ai team! 👋 We've got some exciting updates to share with you in this release. Let's dive in! 🚀 ### ✨ Enhancements #### **Enhanced File Uploader Experience** * You can now upload multiple files simultaneously while continuing other work within your workspace. This improvement streamlines workflows and enhances efficiency. **Improved Executive Summary with our Generative BI Agent** * We've enhanced the Executive Summary feature by incorporating additional metadata. This provides richer insights, highlights key takeaways, and flags potential data quality issues that could impact results. **Inventory Balancer - Advanced Optimization** * Retailers can now leverage an advanced inventory optimization tool that ensures stock is allocated efficiently across stores. The feature considers factors such as distance, store types, configurations, and other key attributes to optimize inventory distribution. ### 🔐 Security * Latest Security Patches * We've installed the latest security patches and packages to keep your data safe and secure. ### 🐛 Bugs * General Improvements * Thanks to your valuable feedback, we've squashed some bugs to enhance the overall performance of the platform. As always, we love hearing from you! Don't hesitate to reach out with any feedback or suggestions. Let's keep making Beye.ai better together! 😊 # November 25, 2024 Release v0.373.0 Greetings from the Beye.ai team! :wave: We've got some exciting updates to share with you in this release. Let's dive in! :rocket: ## :sparkles: Enhancements **Short-term Memory for Smarter Interactions** * Beye.ai now remembers your recent exploratory questions when searching for answers in your data. * This allows you to build on your inquiries, enabling deeper insights without having to repeat or reframe your previous queries. * Perfect for iterative analysis, making your data exploration more fluid and intuitive. **Interactive Dashboarding with our Generative BI Agent** * Build dashboards dynamically and no-code, using only natural language. * As you interact with the Analyst AI, it uses short-term memory to adapt and refine your queries, helping you craft tables, cards, and charts seamlessly. * No need to get the perfect prompt on the first try—just keep building and iterating as you go. **Improved Data Orchestration Layer** * Enhanced security and flexibility in managing your data flows. * Automatically process files, apply business logic, append or truncate data systematically, and update the semantic layer in real-time as new data flows in. * Ensures reliable and secure data movement from your systems of record to actionable insights. ## :closed\_lock\_with\_key: Security * Latest Security Patches * We've installed the latest security patches and packages to keep your data safe and secure. ## :bug: Bugs * General Improvements * Thanks to your valuable feedback, we've squashed some bugs to enhance the overall performance of the platform. As always, we love hearing from you! Don't hesitate to reach out with any feedback or suggestions. Let's keep making Beye.ai better together! 😊 # November 18, 2024 Release v0.372.0 Greetings from the Beye.ai team! :wave: We've got some exciting updates to share with you in this release. Let's dive in! :rocket: ## :sparkles: Enhancements **Retail Locations Inventory Balancer Advanced Skill** * This new skill leverages advanced machine learning to optimize inventory allocation and interstore transfers. * Automatically balance inventory based on projected sales demand, ensuring optimal sell-through while reducing stockouts and overstock. **ELT Layer Integration via the UI** * Simplify your data pipeline! Beye.ai now supports an event-driven ELT layer directly in the platform. * Process files, apply business logic transformations, and even perform lightweight CRUD operations with AI assistance—all within the platform. **Measure and KPI Definitions in Dataverse** * Define and manage KPIs like sell-through, gross margin, and in-stock percentage in a centralized Measure Glossary. * Beye.ai models will understand and apply these definitions consistently across your analytics and queries. **Updated Shareable Links** * Share interactive, full-screen content with external stakeholders. * Content remains secure with role-based access controls, ensuring the right people have the right access. ## :closed\_lock\_with\_key: Security * Latest Security Patches * We've installed the latest security patches and packages to keep your data safe and secure. ## :bug: Bugs * General Improvements * Thanks to your valuable feedback, we've squashed some bugs to enhance the overall performance of the platform. As always, we love hearing from you! Don't hesitate to reach out with any feedback or suggestions. Let's keep making Beye.ai better together! 😊 # November 9, 2024 Release: v0.370.0 Greetings from the Beye.ai team! :wave: We've got some exciting updates to share with you in this release. Let's dive in! :rocket: ## :sparkles: Enhancements * Dashboard Refresh Capability * You can now refresh your dashboards to fetch the latest data from the Dataverse. The dashboard content will auto-refresh, and the refresh date will be displayed for your convenience. * Custom Message Titles * Organize your content better with custom titles for messages. Don't want the prompt to display in the channel? No problem! Add custom tags or titles to your messages. This is especially helpful for promoted, pinned, or favorited content, making it easier to identify. * Automatic Y-Axis Formatting * The Y-axis now auto-formats to whole numbers. Less clicks, more efficiency—just the way we like it! * Updated Shareable Links Branding * We've refreshed the branding for shareable links, now offering a full-screen content view for a better experience. * Enhanced Telemetry * We've added more telemetry to understand how we can improve your user experience and focus on what matters most to you. ## :closed\_lock\_with\_key: Security * Latest Security Patches * We've installed the latest security patches and packages to keep your data safe and secure. ## :bug: Bugs * General Improvements * Thanks to your valuable feedback, we've squashed some bugs to enhance the overall performance of the platform. As always, we love hearing from you! Don't hesitate to reach out with any feedback or suggestions. Let's keep making Beye.ai better together! 😊