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.
Digs through SEC filings, FRED releases, and arXiv papers by hand before every strategy review.
Cross-references market structure, macro regime, and academic literature across three different browser tabs.
Loses track of which papers replicate and which are p-hacked.
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.
MarketAnalyst opens with funding-rate, open-interest, and on-chain flow context, MacroEconomist layers in the Fed reaction function and DXY signal, and the two hand off sequentially. A cron trigger inside Melaya Agents lands the brief before Monday's desk review with no manual kickoff.
MarketAnalyst resolves a ticker to its CIK and pulls recent 10-K, 10-Q, and 8-K filings plus Form 4 insider trades; DataScientist checks the numbers against XBRL company facts for anything worth turning into a feature.
LiteratureSpecialist pulls recent q-fin papers from arXiv and scores each one's replication quality (pre-2015 US equities papers replicate at roughly 30%, by this persona's own backstory), before DataScientist turns a validated finding into a feature proposal with a formula, a data source, and an expected decay half-life.
MacroEconomist pulls the current regime from FRED series (GDP, CPI, the 10-year yield) and cross-checks same-day equity quotes and options positioning, before MarketAnalyst folds the read into the on-chain picture.
A PM reaches the same crew's last output from a Melaya Assistant session, asks a follow-up, or triggers DataScientist to re-run the feature pass against fresh data, without opening the underlying pipeline. When a data vendor or journal page has no API, Melaya Browser Control takes over the browser tab and reads it the way a person would, with every extraction step pausing for approval before it's logged.
useCases.list.research.workflows.5.body
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.
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.
Sets the macro frame with Fed reaction function, DXY trend, global liquidity cycle, and a 30 day calendar of events that move position sizing.
Reads recent quantitative finance papers, scores replication quality, and always surfaces one contradicting paper so the thesis is tested before it ships.
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.
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.
General purpose search, fetch, and local file reads for all four personas. Read only by default, so no persona can write outside its scoped bundle.
MarketAnalyst and DataScientist pull 10 K, 10 Q, 8 K, and Form 4 data straight from EDGAR. Read only surface, so no write gate is needed.
MacroEconomist queries FRED for rates, inflation prints, and release calendars with the series id cited in every chart. Read only, no HITL needed.
LiteratureSpecialist scans recent q fin papers with replication scoring. Pairs with openalex_tools and semantic_scholar_tools for cross venue coverage.
Tracks citation graphs and follow on work so LiteratureSpecialist can stress test a thesis against later refutations. Read only.
Lightweight price, options, and chart pulls for MarketAnalyst when a paid feed is not authorized. Read only.
Builds the per workflow vector store from prior notes, won thesis memos, and house coverage. Powers rag_retrieve and cross run memory. Indexing is HITL gated when new corpora are added.
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