# All New Improvements Beta ## April 2026 ### Script-Based Rerun Re-run any completed task on the same device without calling the LLM. Mahoraga records the execution trajectory and replays it as a self-healing script — adapting to minor UI shifts between builds. Reruns complete in ~1/3 of the original time with zero LLM overhead. [Read more](/content/blog/quash-rerun-memory-driven-mobile-test-automation/index.html) ## March 2026 ### Full Web App Testing Mahoraga comes to the browser. Describe a web flow in plain English and run it the same way you run mobile tests — same reports, same suites, one project for both. [Read more](/content/blog/web-based-mobile-testing-platform/index.html) ### iOS Device Testing Mahoraga now runs on iOS simulators. Upload an IPA, write the same plain English instructions, and execute on iOS — same reports, same suites, same workspace. [Read more](/content/blog/ios-mobile-testing-ai-automation/index.html) ### Windows Desktop App Quash runs natively on Windows 10/11 with full feature parity. Connect devices, run tests locally, and share the same workspace across Mac and Windows. [Read more](/content/blog/windows-app-mobile-testing-quash/index.html) ## February 2026 ### Megumi — AI Test Generation Agent Introducing Megumi, Quash's dedicated test generation agent inside the new Test Studio. Give it context — a PRD, a Figma file, a GitHub repo, or a plain English prompt — and Megumi generates structured test cases with instructions, expected results, and priority levels. - PRD upload — attach a spec and Megumi extracts flows, acceptance criteria, and edge cases - Figma integration — Megumi reads component names, states, and annotations from your designs - GitHub integration — Megumi generates targeted tests per pull request using real endpoints and field names Works conversationally, remembers the full session, and gets smarter about your app over time through Guidance. [Read more](/content/blog/ai-test-case-generation-prd-figma-code/index.html) ### Network Throttling Simulate 4G, 3G, 2G, or offline conditions on cloud device runs. ## January 2026 ### Web Playground Try Quash at quashbugs.com/playground — no account, no download. Type a prompt, watch Mahoraga execute on a real app, and see the report. [Read more](/content/blog/mobile-testing-web-playground-quash/index.html) ## December 2025 ### Self-Hosting (Enterprise) Deploy Quash's execution layer inside your own AWS, GCP, or Azure environment. Test data and recordings never leave your infrastructure. ### General Availability Quash is now generally available. Free tier at 100 runs/month, Pro with unlimited usage billing, Enterprise with SLAs and dedicated infrastructure. [Read more](/content/blog/journey-to-general-availability-quash/index.html) ### MCP Integration AI agents can now trigger test runs, poll results, and retrieve reports via Quash's MCP server. Fully autonomous QA pipelines — no human in the loop. ## November 2025 ### PDF Export for Reports Export any execution report as a formatted PDF with optional password protection. ### API Key Management & Audit Logs Scoped API keys per integration. Full audit log of every trigger and config change. ### Claude Opus 4.5 New model option in Settings → AI. Stronger reasoning for complex apps with deep navigation and conditional flows. ## October 2025 ### Backend Validations Verify API state during test execution. Define a validation once, reference it with @slug, and Mahoraga fires it inline — catching backend failures the UI won't show. [Read more](/content/blog/backend-validation-mobile-testing/index.html) ### Test Analytics Dashboard Pass/fail trends, flakiness scores, coverage by tag, and slowest tests in one view. ### Slack Notifications Get notified in Slack when a suite run fails — with a direct link to the report. ### Test Suites Group test cases and run them together — sequential or parallel. Schedule runs and get one unified report. ## September 2025 ### Flakiness Detection & Retry Mahoraga retries transient failures up to 3 times before marking a test as failed. Flakiness score now tracked per test. ### Parallel Execution — Up to 20 Devices Run up to 20 tests simultaneously. Results aggregate into one report with per-device breakdown. ### Scriptless Test Execution Write a test in plain English and Mahoraga executes it on a real device. No scripts, no selectors, no framework. Every run produces an AI-written summary, step screenshots, and a session recording. [Read more](/content/blog/from-scripts-to-intent-what-changed-in-mahoraga-v2/index.html) ## August 2025 ### Claude Sonnet 4 & Opus 4 Two new Anthropic models available. Sonnet 4 for speed, Opus 4 for deeper reasoning on complex flows. ### Mahoraga Execution Engine + Mac App Mahoraga is Quash's on-device agent. Auto-installs on Android devices, detects UI elements via accessibility APIs, executes test steps, captures screenshots, and records the full session. Ships with the native macOS app. [Read more](/content/blog/mahoraga-mac-app-mobile-testing/index.html) ### Execution Reports AI-written summary, flagged observations, step-by-step screenshots, and device recording. Shareable via public link. ### Workspace, Test Cases & Apps Shared workspace with apps, builds, credentials, test data, a test cases library, ad-hoc tasks, and role-based access. ### CI/CD Integration Trigger suite runs from GitHub Actions, CircleCI, Vercel, or Jenkins. Pass/fail gating and status badges. ### Multiple LLM Support Choose the model powering test generation like GPT-4o, Claude Sonnet, Gemini Pro. ### Test Case Generator — Early Access Describe a user flow in plain language and get a structured, editable test case. No setup, no repo, no design files needed. ### Self-Healing Execution When UI elements shift between builds, Mahoraga locates the correct element and continues. Healing events logged in the report. ### Android Testing — Intent-Driven Engine The foundation of Quash. Describe a flow in plain English and Mahoraga handles every interaction autonomously. No selectors, no scripts, no framework. Upload an APK, connect a device, and run. [Read more](/content/blog/android-mobile-testing-ai-automation?utm_source=chatgpt.com)