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.
Reconciles NAV by hand across every exchange and custody provider before month close, one CSV export at a time.
Chases funding-rate costs and slippage that the backtest never priced in, strategy by strategy.
Rebuilds VaR, CVaR, and stress scenarios in a spreadsheet every time a position changes.
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.
FinancialController pulls exchange balances and book positions, reconciles NAV to the cent, and flags any break over $100 with a documented root cause. CFO reviews the reconciled numbers against the budget before sign-off. The pipeline writes flagged breaks into a workbook and posts the summary to the finance channel.
FPnLAnalyst decomposes each strategy's P&L into alpha, beta, transaction cost, funding, slippage, and carry, and isolates the funding-rate cost that backtests usually under-estimate. Live equity and FX context comes from Alpha Vantage; RiskManager cross-checks any anomaly against the strategy's VaR budget before it reaches the CFO.
TreasuryManager checks single-venue concentration against the 25/30% NAV limits, pulls Treasury Fiscal Data for the macro cash-rate backdrop, and proposes idle-capital yield reallocation with a risk-adjusted comparison. Any rebalance above the CFO's approval threshold pauses the run and waits for a human decision.
ComplianceOfficer builds a searchable knowledge base from raw trade logs to check for wash-trading and spoofing patterns, while TaxStrategist models unrealized gains under FIFO, HIFO, and specific-ID lot selection and flags every harvesting opportunity before the deadline. InvestorRelations drafts the one-page LP letter from the same numbers.
ChiefFinancialSynth folds every workstream into a Financial Health Score and a board summary that leads with the worst finding, never buries it under good news. A CFO reaches the same crew from a Melaya Assistant session to ask a follow-up or trigger a re-run when new exchange data lands, no dashboard hopping, and the crew's schedule (cron, webhook, or app event) keeps the report current without a manual kickoff.
useCases.list.finance.workflows.5.body
Real personas from the finance_team crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.
Owns NAV, daily reconciliation, and audit readiness. Flags every variance over one hundred dollars with a documented root cause inside twenty-four hours.
Decomposes results into drivers (gross, transaction costs, funding, slippage, carry) and explains any line that drifts more than fifteen percent off plan.
Tracks cash across banks, custodians, and stablecoin issuers. Enforces concentration limits and keeps six months of operating expense in liquid reserves.
Calculates VaR and CVaR, runs stress scenarios, and enforces non-negotiable circuit breakers on rolling drawdown.
Watches trading and treasury activity for wash patterns, velocity anomalies, and audit-trail gaps. Tracks license and filing deadlines per jurisdiction.
Models tax position under FIFO, HIFO, and Specific ID, surfaces harvesting opportunities before year-end, and maps jurisdiction exposure for each entity.
Writes the one-page LP letter with benchmarks in line one. States underperformance plainly and benchmarks against the buy-and-hold baseline every time.
Owns capital allocation, budget review, and a ninety-day rolling cash flow forecast. Approves every deployment over one hundred thousand dollars.
Synthesizes every workstream into a board-ready one-pager with a Financial Health Score and a single strategic action.
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 equities, FX, and macro context for variance attribution and treasury hedging notes. Read-only, no HITL gate needed because nothing writes.
Reach US Treasury fiscal data for runway and cash positioning models. Read-only by design.
Read from the ledger, billing, and treasury databases for close, variance, and audit work. sql_query is scoped per agent and DSN-gated, never granted to drafting personas.
Read trial balances and budget workbooks, write the close pack, and produce the board deck. Every write to a shared path is HITL-gated by default.
Build the per-workflow knowledge store from chart of accounts, policy memos, prior board packs, and auditor PBC lists. Powers all three knowledge layers.
Read auditor and lender threads, prepare LP letters and bank confirmations, and stage every send for the CFO. gmail_send is HITL by default for this crew.
General research, structured fetch, and Slack drops for the Monday close digest. pause_for_human is the explicit HITL primitive any workflow can call.
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