Solutions/Apps & businesses
CoinGraph for DAO treasuries and vaults.
A treasury has rules (minimum liquidity, no mint authority, exit slippage caps) but no one checks them continuously, and governance votes carry no evidence.
When it runs: Before a rebalancing vote, and on a schedule to catch drift.
Pays: Hire the Coworker on Sokosumi per Task, with escrow, or an API key.
A real answer
“Check a treasury in ADA, LINK and SOL against four rules”
COMPLIANT
Every asset passes every rule, with a proof id per asset ready to attach to the proposal. Exit slippage priced on live order books.
How it fits
What changes with the check in place.
01
Write the policy once; Treasury Steward checks every asset against it: COMPLIANT or BREACH, per asset.
02
Exit slippage priced on live order books, so the number in the proposal is the number the market would give.
03
A proof id per asset, ready to attach to the vote.
The first step
One call. Then decide what to keep.
No account to start: x402 pays per call, MCP is free during the preview. Design partners get a key, a contract and a direct line to the founder.
curl -X POST https://coingraph.ai/api/v1/agents/treasury-steward \
-H 'content-type: application/json' \
-d '{"assets":[{"token":"cardano","value_usd":4000},{"token":"chainlink","value_usd":3000},{"token":"solana","value_usd":2000}],
"policy":{"min_depth_usd":500000,"max_exit_slippage_pct":1,"allow_mint_authority":false}}'Other audiences
Trading agents
Right before every order, and when sizing a position.
AI wallets
When the user, or the wallet's assistant, is about to sign a swap or a send.
Funds & desks
Continuously, with a push when something crosses a threshold.
Exchanges & listing
Listing review, periodic re-review, and incident response.
Compliance
Before onboarding a counterparty, and before any outbound transfer.
Research tools
Whenever a user asks about a token.
People
Every morning, and before a trade.
Other AI agents
Whenever its task touches a token or a wallet.