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.
Read a hundred SEC filings a quarter looking for the one insider transaction that matters.
Track FRED macro releases across a dozen series without a single dashboard.
Scan arXiv and OpenAlex for the paper behind a pitch deck's claimed breakthrough.
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 resolves a ticker to its CIK via sec_edgar_tools/edgar_ticker_to_cik, pulls the recent filing list with edgar_recent_filings, and checks Form 4 insider activity with edgar_insider_form4, all through the real SEC EDGAR API, not a scraped summary.
MacroEconomist pulls the actual observation series with fred_tools/fred_series_observations and checks upcoming release dates with fred_release_dates, so a thesis is timed against real data, not a hunch.
LiteratureSpecialist searches arXiv (arxiv_search, arxiv_by_author) and OpenAlex (openalex_search_works, openalex_work_citations) to check whether a pitch deck's cited breakthrough is real, recent, and actually cited by anyone else.
DataScientist builds a targeted investor shortlist with openvc/openvc_search_investors, matched on sector, stage, geography, and check size straight from OpenVC's public database (no API key), then pulls a single fund's full public profile with openvc_get_fund before an introduction goes out.
MarketAnalyst resolves and reads a founder's LinkedIn profile and feed with social_linkedin/linkedin_resolve_profile and linkedin_browse_feed, and the diligence trail gets indexed with knowledge/build_knowledge_from_text so the next person on the deal team can search it instead of re-reading it.
useCases.list.vc-investor.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 category read for a deal with funding rounds, comparable revenue multiples, on-chain or product usage signals, and a named TAM ceiling with stated risks.
Proposes a falsifiable KPI definition per deal, normalizes cohort and retention math across decks, and writes the pseudo code a portfolio dashboard can run on a schedule.
Reads academic and industry research that supports or contradicts a thesis, scores replication quality, and always surfaces one paper that argues against the deal.
Sets the capital cycle frame with Fed reaction function, DXY trend, and a 30 day calendar of macro events that move venture pricing and sector timing.
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 search, structured fetch, and local file reads for all four personas. pause_for_human is the explicit HITL node that holds every memo, send, and LP draft until you approve.
MarketAnalyst pulls public comparable filings, S 1 prospectuses, and insider Form 4 data for category benchmarks. Read only, so no write gate is needed.
MacroEconomist queries FRED for rates, venture funding indices, and release calendars with the series id cited in every macro paragraph of the memo. Read only.
LiteratureSpecialist scans recent papers in the deal's technical category, scores replication quality, and lists one contradicting paper per thesis. Read only.
Tracks citation graphs around a founder's prior research or a category claim so LiteratureSpecialist can name the original work behind a pitch's footnote.
Pull product launch coverage, hiring page snapshots, and category news for the market map. Scoped per agent to an allowlist you set, never grants drafting personas a write tool.
Search LinkedIn for founder backchannel targets, prior employer connections, and operator references. Read only in this bundle, no write tool is granted, so nothing can DM a reference without you.
Build the per workflow knowledge store from past memos, pass notes, founder updates, and your thesis document. Powers Static context, rag_retrieve, and Cross-run memory.
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