Three pains every sales and BD team hits weekly. Each one is what your reps actually complain about, not what a feature page would call them.
Manual QA on real devices is slow and expensive, so it happens less often than a real release schedule needs.
Push notifications, deep links, and onboarding flows ship broken because nobody walked every path on every phone.
Every pipeline below is a shape you wire on the canvas using the crew and tools further down. Not a feature we ship for you, a pattern you configure.
Melaya Device Control installs, opens, and taps through the app on a paired Android device: onboarding, push notification, deep link, one screenshot per step. FrontendEngineer walks the journey and UIUXDesigner flags what regressed against the last run.
If the app ships a web dashboard alongside it, Melaya Browser Control walks it in a real Chrome or Edge session in the same run, so a founder gets one report instead of two separate tools.
Run two build variants on paired devices in parallel and get side-by-side screenshots of the same screen, instead of two testers' notes from two different days. TechLead reads the evidence and calls the difference.
A solo founder already running Claude Code or Cursor connects to api.melaya.org/mcp over OAuth 2.1, grants melaya:phone (8,711 tools), and asks the assistant to walk the app on the paired device after every deploy.
DevOpsEngineer schedules the walk to run on every build and files the step log and screenshots to Jira, Linear, or Notion, so a PM sees pass or fail without asking.
Real personas from the tech_team crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.
Plans the journey coverage and reads the evidence per build.
Walks the app UI screen by screen and captures each step.
Wires runs into your release cadence and files the reports.
Compares variants side by side and flags what regressed.
Every tool below is a real shared tool from the Melaya bundle. Allowlist per agent; HITL-gate the writes; revoke any of them in one click.
Drives your app on a real device: taps, swipes, screenshots, step logs.
Files what it finds where your team already works.
Turns run evidence into a searchable record per build.
Reads configs and logs alongside the on-device run.
Every pipeline ships with three layers of knowledge access. Mix and match per agent on the canvas. No shared vector space with another tenant, no surprise reads, no opaque retrieval.
includeContextPer-pipeline documents appended to specific agents' input on every run. The ICP brief, playbook, pricing sheet, or won-deal email corpus. Whatever needs to be there before the agent thinks. You pick which personas get which docs.
rag_retrieveA scoped tool granted per-agent. When the agent decides it needs more depth, it queries the workflow's vector store on demand. Same knowledge base as Static context, accessed only when the model asks for it.
pipeline_memoryPipeline-level state that carries from one run to the next. Yesterday's research is in scope for today's follow-up. The crew remembers what it already prospected, what got approved, what was sent. The audit log is the second-order knowledge base.
A real, paired Android device. Agents tap, swipe, and screenshot the actual app the way a user would, not an emulator's simulated input.
Yes, by opening the app or a deep-link URL directly (phone_open_app, phone_open_url) and walking the resulting screen, capturing a screenshot at each step.
Yes. Melaya Browser Control walks the web side in a real Chrome, Edge, or Brave session, so a hybrid product gets one testing pass instead of two separate tools.
Run both on paired devices and get side-by-side screenshots per screen for the same run, read by the UIUXDesigner and TechLead personas for a call on what regressed.
No. A founder or PM can trigger the walk from the Melaya app, or from Claude Code or Cursor over the MCP server, and read the evidence without a dedicated tester.
A step log and a screenshot per step, filed to Jira, Linear, or Notion if connected, so every build has replayable evidence.
Sandbox tier is free with no card. Join the waitlist and we will email you the moment a slot opens.
← Back to every use case