> ## Documentation Index
> Fetch the complete documentation index at: https://docs.noxint.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Agent workflows
> Three complete jobs, run live against production: every request, every response, and the credit ledger at each step
The API and MCP server are in production today, grounding the chat
analyst's market answers. The discovery surface is already public: run
`curl https://noxint.ai/api/v1` right now, with no key, and the contract
answers. Key minting and paid access open in beta after launch; credit
packs are rolling out with launch. [Launch status](/token/status) tracks
exactly what is on.
Single calls prove an endpoint works. Workflows prove an agent can do a job.
Everything below was run against the production gateway on 2026-07-16;
responses are trimmed, never altered. Prices are a snapshot of that morning.
## 1. The positioning sweep
The question every derivatives desk asks at the open: where is positioning
stretched right now? Two calls.
**Step 1: screen the core tier for extremes.** `rank` with the
`extreme_count` metric scores each asset by how many of its metrics sit in
their own historical tails.
```bash theme={null}
curl -H 'Authorization: Bearer nx_your_key' \
'https://noxint.ai/api/v1/rank?metric=extreme_count&direction=top&limit=5'
```
```json theme={null}
{
"rows": [
{ "asset_id": "crypto:bitcoin-cash", "symbol": "BCH", "score": 3, "extreme_metrics": ["funding_rate_8h_pct", "oi_change_24h_pct", "return_24h_pct"] },
{ "asset_id": "crypto:0g", "symbol": "0G", "score": 2, "extreme_metrics": ["liq_intensity_pct_of_oi_24h", "oi_change_24h_pct"] },
{ "asset_id": "crypto:bless", "symbol": "BLESS", "score": 1, "extreme_metrics": ["liq_imbalance_24h"] },
{ "asset_id": "crypto:bnb", "symbol": "BNB", "score": 1, "extreme_metrics": ["funding_rate_8h_pct"] },
{ "asset_id": "crypto:btw", "symbol": "BTW", "score": 1, "extreme_metrics": ["liq_imbalance_24h"] }
]
}
```
`X-Credits-Charged: 5`. The screen ranks only symbols with fresh inputs at
scan time and reports its scanned and excluded counts in a coverage block,
so the agent knows how wide the net was. Bitcoin Cash leads with three
simultaneous extremes, one of them funding. The agent stores the canonical
`asset_id` and drills exactly one domain.
**Step 2: drill the extreme.**
```bash theme={null}
curl -H 'Authorization: Bearer nx_your_key' \
'https://noxint.ai/api/v1/funding?id=crypto:bitcoin-cash'
```
```json theme={null}
{
"funding": {
"rate_8h_pct": { "value": -0.021, "pctl": 8.9, "pctl_1y": 6.6 },
"apr_pct": -23.02,
"bars_since_sign_flip": 8,
"venue_hot": { "venue": "hyperliquid", "rate_8h_pct": -0.0296, "rate_pctl": 5.2 },
"venues": 4,
"by_venue": [
{ "venue": "binance", "rate_8h_pct": -0.0204, "rate_pctl": 13 },
{ "venue": "bybit", "rate_8h_pct": -0.0185, "rate_pctl": 10.8 },
{ "venue": "okx", "rate_8h_pct": -0.0238, "rate_pctl": 7.4 },
{ "venue": "hyperliquid", "rate_8h_pct": -0.0296, "rate_pctl": 5.2 }
],
"next_funding_at": "2026-07-16T16:00:00Z"
}
}
```
`X-Credits-Charged: 3`. The read is unambiguous: shorts are paying 23% APR
to stay short, the rate sits in the 9th percentile of its 90-day history and
the 7th of the last year, all four venues agree, and the sign flipped only
eight bars ago. Crowded, fresh, unanimous. Whatever the agent decides to do
with that, it decided from ranked facts, and it knows to check back after
the 16:00 funding settle.
**The whole sweep: 8 credits, eight cents, two calls.**
## 2. From ticker to filed facts
An equity dossier, starting from nothing but the word "apple".
**Step 1: resolve, free.** `resolve?q=apple` returns `best: null`, because
"apple" is genuinely contested: Apple Inc. on Nasdaq, an OTC filer named
Apple iSports, and two Solana tokens with the ticker `APPLE`. The ranked
matches carry warnings instead of a silent guess. The agent takes the
equity: `eq:0000320193:aapl`.
**Step 2: the situation.** `read?id=eq:0000320193:aapl` returns the
headline (price $327.50, market cap $4.84T, P/E `"43.9"` as an exact
string), stamped `filings_indexed_through: 2026-07-11`. Five credits,
assessment included.
**Step 3: the filed statements.**
```bash theme={null}
curl -H 'Authorization: Bearer nx_your_key' \
'https://noxint.ai/api/v1/financials?id=eq:0000320193:aapl&statements=income&period_kind=quarter&periods=2'
```
```json theme={null}
{
"periods": [
{ "id": "Q2FY2026", "form": "10-Q", "accession": "0000320193-26-000013", "filed_at": "2026-05-01", "restated": false },
{ "id": "Q1FY2026", "form": "10-Q", "accession": "0000320193-26-000006", "filed_at": "2026-01-30", "restated": false }
],
"values": {
"revenue": { "unit": "USD", "by_period": ["111184000000", "143756000000"] },
"net_income": { "unit": "USD", "by_period": ["29578000000", "42097000000"] },
"eps_diluted": { "unit": "USD_per_share", "by_period": ["2.01", "2.84"] }
}
}
```
Revenue to the dollar, two quarters side by side, each tied to the accession
number of the 10-Q it came from. Three credits.
**Step 4: who is selling.** `events?types=insider` returns the recent Form 4
tape plus a summary of the trailing 90-day window: zero open-market buys,
one sale, net -116 shares across two unique insiders. Three credits.
**The whole dossier: 11 credits.** Ticker to SEC-grade facts for eleven
cents, and every number in it carries its own provenance.
## 3. The monitoring loop
Live data agents die by polling: too fast burns money, too slow misses the
move. The contract schedules the loop for you.
1. `read?id=crypto:bitcoin` with an `Idempotency-Key`. The response carries
`next_update_at: 2026-07-16T09:45:19Z` and an `ETag`.
2. Sleep until `next_update_at`. Not a guess: the engine told you when the
next change can exist.
3. Re-request with `If-None-Match`. Unchanged data answers `304` and costs
zero credits. Changed data bills the operation's rate, and only then does
your agent re-reason. Watch `price` at 1 credit; `read` on change.
4. If the request times out mid-flight, resend it with the same
`Idempotency-Key`: transient failures release the hold, so the retry
runs once and settles once.
A watch loop over one asset pays per actual change in the data, not per
poll. Over MCP there is no conditional re-poll, so apply step 2 twice as
strictly: cache the last result and never re-call before `next_update_at`.
Free to try today, before keys open: the `docs` and `schema` operations
answer keyless, and `resolve`, `coverage`, and `usage` cost zero credits
once you hold a key. The two jobs above total nineteen cents end to end.