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.
Log into a dozen game accounts every morning just to claim a daily reward.
Grind the same quest chain, resource run, or leveling loop for hours, for minutes of actual play.
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.
Device Control opens the game, logs in, completes the daily quest chain, and collects resources on each account you manage, tapping and swiping the way a player would. OperationsManager owns the loop definition and the per-account schedule.
You build the loop once in the visual builder, DataOperations tracks resources and levels per account in a local ledger via database/sqlite_query, and the agent repeats the sequence on schedule while you watch progress live.
IncidentManager holds anything that spends real money at the approval gate. The run pauses and waits for you, and stops outright if something looks off, like an unexpected screen or a failed step.
ReportingAnalyst streams a run summary to Discord or Telegram after each session, so you know what happened across every account without tapping through each one yourself.
Real personas from the operations crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.
Owns the loop definitions and the per-account schedules.
Tracks resources, levels, and results per account.
Streams live progress and writes the run summaries.
Stops the run when something looks off and holds the spend gate.
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.
Runs the game on your real device: logins, quests, collection, leveling.
Keeps a local ledger of accounts, runs, and results.
Pings you when a run finishes or needs your approval.
The approval gate on anything that spends real money.
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.
No. IncidentManager holds anything that spends real money at the approval gate; the run waits for you.
As many as you scope apps for. The loop runs per account on its own schedule, tracked by DataOperations.
It drives the real app through Device Control's accessibility layer, the way a player taps and swipes, not a memory-injection bot. Every run leaves a replayable log.
IncidentManager stops the run and flags it instead of tapping through blind.
Yes. ReportingAnalyst posts the run summary to Discord or Telegram after each session.
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