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.
Pulls Census, BLS, and CDC numbers into a spreadsheet by hand every reporting cycle, one agency portal at a time.
Re-writes the same SoQL, series-ID, or geography query every time a public dataset refreshes.
Validates messy CSV and JSON exports from government agencies before anything downstream can trust them.
Cross-references trade, employment, and macro datasets that live in five agencies with five different query languages.
Builds a one-off chart or export instead of a pipeline that runs the same way next month.
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.
DataScientist schedules a pull of Census ACS5 demographics alongside BLS employment and CPI series, and lands the result in a shared database instead of a local download folder. MarketAnalyst adds the market read on top of the same numbers.
DataScientist queries CDC's Socrata-backed datasets, such as weekly flu activity or overdose death rates by state, on a schedule, and profiles the output before it reaches a dashboard. No API key is required for CDC; a free Socrata app token just raises the rate limit.
DataScientist blends UN Comtrade trade-flow data with FRED macro series and EIA oil and gas benchmark prices into one cross-agency dataset, instead of three separate exports stitched together by hand.
Every extraction runs through JSON and CSV validation and a quick statistical profile before it lands in the database, so a malformed agency export never silently corrupts the report downstream.
The same pipeline runs on a cron trigger inside Melaya Agents, MarketAnalyst summarizes what changed since last run, and a human analyst reads the output in Melaya Assistant instead of re-running five separate agency queries by hand. Cross-run memory carries forward what last week's pull found.
Real personas from the research_team crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.
Proposes new features with a formula, data source, decay half life, pseudo code, and a statistical test design that an engineer can implement the same day.
Builds the market structure brief with funding rates, open interest, on-chain flows, and a stated bullish, bearish, or neutral regime call with named risks.
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.
Pull ACS5 demographics and population estimates. A free Census API key unlocks the full daily quota; anonymous calls cap at 500 a day per IP.
Query single or multiple BLS employment and CPI series by series id. Works without a key at reduced limits.
Search and query CDC's Socrata-backed public-health datasets, like weekly flu activity or overdose death rates by state. No credentials required for standard volume.
Pulls UN Comtrade trade-flow data by partner and product.
Cross-checks the macro backdrop against FRED series.
Pulls EIA oil and gas benchmark prices.
Validate every extraction with JSON and CSV linting and a statistical profile before it lands downstream, so a malformed agency export never silently corrupts a report.
Land the validated pull in a shared table instead of a local download folder. sql_query and sql_schema are scoped per agent.
Run the pipeline on a cron trigger and post the summary to Slack once MarketAnalyst summarizes what changed.
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.
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