Assuremind Studio

AI-powered codeless UI & API test automation framework

Describe tests in plain English. AI generates Playwright code. Run anywhere.

Why Assuremind?

| Capability | What it does | |-----------|-------------| | Zero coding | Write steps in plain English — AI generates Playwright code automatically | | MCP-sighted generation | AI sees real page elements via Playwright MCP accessibility snapshots (~90-95% accuracy) | | 3 suite types | UI (browser automation) · API (HTTP tests) · Audit (Playwright + Lighthouse) | | 5-level self-healing | Broken selectors are auto-fixed by AI during runs — smart retry → AI regen → multi-selector → visual → decompose | | 12 AI providers | Anthropic · OpenAI · Gemini · Groq · DeepSeek · Together · Qwen · Perplexity · Ollama · Bedrock · Azure OpenAI · Custom | | Device emulation | iPhone, Pixel, iPad, Galaxy — full Playwright device descriptors from UI or --device CLI flag | | Studio UI | Browser-based editor, run dashboard, reports, healing review, git control center — with dark mode | | RAG memory | AI learns from every run — retrieves similar past steps & healing fixes for smarter generation | | Test Recorder | Record tests by clicking in a real browser — locators verified against Playwright's accessibility tree, zero AI cost | | Cost-optimised | Template engine + code cache + RAG handle ~80% of steps with zero AI calls | | CI-ready | npx assuremind run --all --ci — exit code 0/1, works with any pipeline | | File-based | Plain JSON storage, fully Git-friendly, no database |

Quick Start

npm install assuremind
npx assuremind init        # folders, config, Playwright browsers
npx assuremind studio      # opens http://localhost:4400

Requirements: Node.js >= 18 · macOS / Linux / Windows

Configure AI Provider

Edit .env — pick one provider:

# Anthropic                       # OpenAI                         # Google
AI_PROVIDER=anthropic             AI_PROVIDER=openai               AI_PROVIDER=google
ANTHROPIC_API_KEY=sk-ant-...      OPENAI_API_KEY=sk-...            GOOGLE_API_KEY=AIza...
ANTHROPIC_MODEL=claude-sonnet..   OPENAI_MODEL=gpt-4o              GOOGLE_MODEL=gemini-2.5-pro

See .env.example for all 12 providers including Gemini, OpenAI, Anthropic, Ollama (local/free), etc.

CLI

npx assuremind run --all                                    # run everything
npx assuremind run --type ui --tag smoke                    # filter by type + tag
npx assuremind run --suite "Login" --browser chromium       # run a suite
npx assuremind run --all --device "iPhone 15 Pro" --ci      # mobile + CI mode
npx assuremind generate --story "User resets password"      # AI generates full suite
npx assuremind apply-healing --yes                          # accept all healed selectors
npx assuremind validate                                     # check config health
npx assuremind doctor                                       # system diagnostics

| Flag | Description | |------|-------------| | --all | Run every suite | | --type <ui\|api\|audit> | Filter by suite type | | --suite <name> | Partial name match | | --tag <tag> | Filter by tag | | --device <name> | Emulate device (e.g. "iPhone 15 Pro", "Pixel 7") | | --browser <list> | chromium firefox webkit | | --ci | CI mode — exit code reflects pass/fail | | --headed | Show browser window | | --no-healing | Disable self-healing |

Full reference → docs/CLI-REFERENCE.md

Studio UI

Start with npx assuremind studio — opens at http://localhost:4400.

Dashboard · Smart Tests · Test Editor · Run Config · Reports · Variables · Self-Healing · Step Library · Git Control · Settings · Docs

Full walkthrough → docs/STUDIO.md

MCP Integration

AI sees real page elements during code generation via the official @playwright/mcp server. Enabled by default.

| Mode | Accuracy | Latency | Config | |------|----------|---------|--------| | Blind (MCP off) | ~50-70% | Fastest | mcp.enabled: false | | Snapshot-driven | ~90-95% | +2-5s first page | mcp.enabled: true (default) | | Act-then-script | ~98-100% | +5-10s/step | mcp.actThenScript: true |

• MCP is only used during code generation — test execution is never affected
• Silent fallback — if MCP fails, generation continues blindly without error
• Configure in Settings → MCP Integration or autotest.config.json

Test Recorder

Record tests by interacting with your application in a real browser — zero AI, zero cost, zero guesswork.

Click Record in the Test Editor, perform your actions, and stop. Each interaction becomes a step with verified Playwright code, ready to run.

How it works

1. A headed Chromium browser opens your app's URL
2. Every click, fill, and navigation is captured in real time — including inside iframes
3. Locators are resolved against Playwright's accessibility tree — the recorder tries 6 strategies (data-testid, getByRole, getByLabel, getByPlaceholder, getByText, CSS) and verifies each with count() === 1
4. Iframe-aware — elements inside iframes automatically generate page.frameLocator('#iframe').getByRole(...) code with the correct frame chain
5. Assertions via keyboard shortcuts: Shift+Click (element visible), Ctrl+Shift+U (URL), Ctrl+Shift+T (page title)
6. On stop, each action is added as a step with pre-generated Playwright code — no AI call needed

What makes it stand out vs other recorders

| Feature | Selenium IDE | Playwright Codegen | Assuremind Recorder | |---------|-------------|-------------------|---------------------| | Locator quality | CSS/XPath | Good | Best — 6 strategies, verified against live page | | Accessibility tree | No | Partial | Full — every locator checked via Playwright API | | Iframe support | Partial | Manual | Auto — detects iframes, generates frameLocator() code | | Assertions | Manual | Manual | Shift+Click (hard), Ctrl+Shift+Click (soft), URL & title shortcuts | | Plain-English steps | No | No | Yes — human-readable instructions auto-generated | | Self-healing after | No | No | Yes — 5-level AI healing cascade | | RAG memory | No | No | Yes — recorded steps feed the learning loop | | Cost | Free | Free | Free |

Biggest pain points in test automation — solved

| Pain Point | How the Recorder Solves It | |-----------|---------------------------| | Writing tests is slow | Record a full test in 30 seconds | | Selectors break constantly | Locators verified against Playwright's accessibility tree in real time | | AI costs money | Recording + code generation = $0, zero AI calls | | Non-technical testers can't write tests | Anyone who can click a browser can create tests | | Assertions are hard to write | Shift+Click for hard, Ctrl+Shift+Click for soft, Ctrl+Shift+U for URL, Ctrl+Shift+T for title | | Hard vs soft assertions | Soft assertions (expect.soft()) let the test continue — all failures reported at end | | Recorded tests are fragile | 6-strategy locator resolution + post-run 5-level self-healing | | Apps use iframes (SAP, Salesforce) | Auto-detects iframe context, generates frameLocator() chains — no manual frame handling |

RAG Memory (Retrieval-Augmented Generation)

The AI learns from every test run, building semantic memory that improves accuracy over time — zero setup required:

| Corpus | What it stores | When it's used | |--------|---------------|----------------| | Code Corpus | Instruction-to-code mappings from successful runs | During generation — similar past steps are retrieved as AI examples or used directly (score >= 0.90) | | Healing Corpus | Past healing events (error + fix pairs) | During self-healing — proven past fixes are injected into the repair prompt | | Error Catalog | Recurring error patterns per URL | During generation — the AI is warned about known-bad selectors to avoid |

Zero cost, zero database — uses local TF-IDF embeddings and file-based JSON storage (results/.rag/). Enabled by default — works automatically from the very first run.

How it improves over time

• Run 1 — memory is empty, AI generates code normally
• Run 2+ — RAG kicks in silently: similar instructions are retrieved instead of making API calls (free + faster), healing uses proven past fixes
• Run 10+ — most common steps are served from RAG memory at zero cost, self-healing resolves issues on the first attempt

Consumer FAQ

| Question | Answer | |----------|--------| | Do I need to configure anything? | No. RAG is ON by default with zero setup. | | Does it cost anything? | No. TF-IDF embedder runs locally. RAG direct hits replace paid AI calls. | | Does it slow down my tests? | No. RAG lookup is <1ms. It actually speeds up generation. | | Does it work in CI/CD? | Yes. Cache results/.rag/ between CI runs to persist memory. | | How do I share memory across team? | Commit results/.rag/ to Git or use a CI cache step. | | How do I reset memory? | Delete the results/.rag/ folder. |

When to use Settings → RAG Memory

Most users never need to touch RAG settings. The Settings card exists for power-user scenarios:

| Scenario | Action | |----------|--------| | Debugging a flaky test | Turn OFF Code Corpus — forces fresh AI generation | | Healing keeps suggesting a bad fix | Turn OFF Healing Corpus — clears bad fix influence | | Major app redesign | Turn OFF RAG entirely — old memory is now misleading | | Error warnings are outdated | Turn OFF Error Catalog — stops avoiding selectors that are fine now | | Want deterministic CI runs | Disable RAG in CI config, keep ON locally |

Self-Healing

When your app's UI changes (button renamed, element moved, DOM restructured), tests break. Instead of failing immediately, Assuremind automatically attempts to fix the broken selector through a 5-level cascade — fully automated, no manual intervention needed:

| Level | What happens | Example | AI Cost | |-------|-------------|---------|---------| | 1 | Smart retry — waits for the element with exponential backoff | Element was loading slowly; retry finds it after 2s | Free | | 2 | AI regeneration — AI rewrites the Playwright code using current page context | #login-btn removed → AI generates page.getByRole('button', { name: 'Sign In' }) | 1 call | | 3 | Multi-selector — AI generates 5 alternative selector strategies, tries each | Tries role → label → placeholder → text → CSS until one works | 1 call | | 4 | Visual analysis — takes a screenshot, AI visually locates the element | Button has no text/role but AI sees it in the screenshot | 1 call | | 5 | Decompose — breaks the failing step into 3-5 simpler micro-actions | "Fill login form and submit" → separate fill email + fill password + click submit | 1 call |

If all 5 levels fail, the step is marked failed and saved to the healing report for your review.

How you use it

1. During test runs — healing happens automatically. If Level 2 fixes a broken #login-btn, your test passes and continues.
2. After the run — healed selectors are saved as pending suggestions (not auto-applied to source files).
3. Review & accept — in Studio → Self-Healing page, or from CLI:

   npx assuremind apply-healing        # interactive review: accept/reject each fix
   npx assuremind apply-healing --yes  # accept all in CI

4. Accepted fixes are written back to your .test.json files — next run uses the healed code permanently.

CI/CD tip: Add npx assuremind apply-healing --yes as a post-test step so healed selectors are committed back automatically. Enable healing.autoPR in Settings to auto-create a GitHub PR with the fixes.

CI/CD

# GitHub Actions
- name: Run tests
  env:
    AI_PROVIDER: google
    GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
    GOOGLE_MODEL: gemini-2.5-pro
  run: npx assuremind run --all --ci

Also supports GitLab CI and Jenkins — or use the built-in CI Config Generator in Studio (Run Config → Generate CI Config).

Exit code 0 = all passed · 1 = failures.

Documentation

| Resource | Location | |----------|----------| | Getting started | docs/GETTING-STARTED.md | | Studio walkthrough | docs/STUDIO.md | | CLI reference | docs/CLI-REFERENCE.md | | Contributing | CONTRIBUTING.md | | All AI providers | .env.example | | Built-in docs | Studio → Docs page |

License

MIT — see LICENSE for details.

Built by DVH