Melaya Mobile · QA & Demos

Automate mobile regression and demos on real phones.Same coverage, fewer hours.

SaaS teams record a golden-path demo once and let an agent replay it on demand, live on a real device, for prospects or docs. QA agencies run regression suites across client apps in parallel, on physical phones, with recordings and pass/fail reports per run. Same coverage, a fraction of the hours.

01
// What breaks today

Manual workflows cost more than the agent does.

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.

  1. 01

    Product demos, onboarding walkthroughs, and mobile regression suites all burn human hours on the same scripted paths, release after release.

02
// Pipelines you can build

Agent workflows: compose, approve, replay.

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.

P01

Golden-path demos on demand

Record a golden-path demo once and let an agent replay it on demand, live on a real device, for prospects or docs.

P03

Evidence per run

Recordings and pass/fail reports per run. Same coverage, a fraction of the hours.

03
// The multi-agent crew

Demo and regression crew

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.

Tech Lead

TechLead

Owns the golden paths and signs off the pass/fail criteria.

Frontend Engineer

FrontendEngineer

Walks each client app screen by screen on real hardware.

DevOps Engineer

DevOpsEngineer

Schedules parallel suites and ships the per-run reports.

UI/UX Designer

UIUXDesigner

Keeps demo runs presentable and flags visual regressions.

04
// Scoped tools

Tool allowlists: only the actions you grant.

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.

shared/tools/phone/

Replays demos and regression paths on physical phones, step by step.

phone_open_appphone_get_screen_treephone_tapphone_screenshotphone_batch
shared/tools/project_mgmt/

Files failures and reports where the team already works.

jira_create_issuelinear_create_issuenotion_create_page
shared/tools/msoffice/

Turns runs into client-ready reports.

word_createexcel_write_data
shared/tools/core/

Reads specs and logs alongside the device runs.

file_readgrep_search
05
// Three knowledge layers

The crew reads what you give it.

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.

L1

Static context

includeContext

Per-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.

L2

RAG retrieval tool

rag_retrieve

A 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.

L3

Cross-run memory

pipeline_memory

Pipeline-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.

07
// FAQ

AI agent questions we get every week.

How do demos stay current?

Record the golden path once. The agent replays it on a real device on demand, so every demo runs on the live build.

What does a regression run produce?

Recordings and pass/fail reports per run, on physical phones, across client apps in parallel.

Can n8n or Zapier run mobile regression tests on a real phone?

No. n8n, Zapier, and Make execute predefined trigger-action steps against APIs, and a phone screen has no API. Melaya's Device Control operates a real Android phone: opens the app, reads the screen, taps and types. Zapier and Make still win on connector breadth for simple linear automations.

Why not just write Appium scripts for regression testing?

Scripts encode selectors, so one renamed element breaks the suite and an engineer repairs code instead of testing. Melaya's agents read the screen like a tester, replan around minor UI changes, and log full run traces per step. For stable, developer-owned suites, scripted frameworks remain a reasonable choice.

Can Melaya test an app that has no API or test hooks?

Yes. Melaya's Device Control operates a real Android phone with no API, SDK, or instrumentation required. The phone tool bundle replays demos and regression paths step by step on physical hardware, while the core bundle reads specs and logs alongside the device run. Your build stays untouched.

Can an agent file a bug or send a report without approval?

No. Melaya applies human-in-the-loop approval on every write. The project_mgmt bundle stages each failure ticket for sign off before filing, the msoffice bundle stages client reports the same way, and the phone pauses for on-device approval before publishing anything from the device.

What evidence do QA agencies get for client audits?

Every run produces full run traces: per-step screenshots, recordings, timestamps, and typed failure reasons. The DevOps Engineer persona schedules parallel suites and ships per-run reports, the msoffice bundle turns runs into client-ready documents, and the project_mgmt bundle files failures where the client team already works.

How does Melaya decide whether a regression run passed?

Melaya applies deterministic-first evaluation: rule-based checks run before any model-graded judgment, so a pass is reproducible. The Tech Lead persona owns the golden paths and signs off the pass or fail criteria, and per-step model routing across 23 providers keeps grading measured as cost per accepted result.

How do I set up a golden-path demo that replays on demand?

Record the golden path once, then let the demo and regression crew replay the run on a real device whenever a prospect or doc needs a live walkthrough. On Melaya's canvas of agents, tools, triggers, and approval gates, the Frontend Engineer persona walks each screen and the UI/UX Designer keeps runs presentable.

Do client builds have to leave our infrastructure?

No. Melaya runs in the cloud or on your local runner, and Device Control drives a physical phone you own, not a third-party device farm. Sensitive steps can route to local models through per-step model routing across 23 providers, so a client build under NDA stays on your hardware.

Build saas teams & qa agencies pipelines on Melaya.

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
Join the community
// Cookies
Melaya uses a small set of first-party cookies that are strictly necessary to authenticate you, maintain your session, and protect the platform from abuse. We do not use advertising cookies, cross-site trackers, or third-party analytics by default. The full cookie list is in our Privacy Policy.