Wire it into your agent
The integration pattern is one rule: no strategy goes live without a verdict. AlphaAssay is a plain HTTPS API, so it drops into any agent framework that can make an HTTP call — no SDK required.
The validate-before-trade loop
def consider_strategy(candidate) -> bool:
v = assay.validate(candidate) # signed verdict, ~seconds
if v["verdict"] in ("fail", "insufficient_evidence"):
log_graveyard(candidate, v["died_at"], v["failure_codes"])
return False
if v["search_budget_left"] == 0:
retire_family(candidate.family) # the family is spent — stop tweaking
if v["survival_map"]["regime_split"] == "dead":
candidate.flag("regime-fragile") # pass ≠ pass — read the map
archive_certificate(v) # evidence for later
return v["verdict"] == "pass"Branch on failure codes, not on vibes
The failure codes are designed for machine decisions:
edge_collapses_at_lag1 → inspect the data pipeline for leakage before anything else;
family_budget_exhausted → stop generating variants of this idea entirely.
An agent that reacts to codes converges; one that retries blindly burns budget on a dead family.
Calibrate your trust in us — automatically
# 1. our public track record — free, no account: rec = requests.get("https://api.alphaassay.com/v1/public/calibration").json() # 2. our correctness — run the known-answer tests yourself: for spec, expected in GOLDEN_SPECIMENS: got = requests.post(DEMO_URL, json=spec).json() assert got["verdict"] == expected # bit-identical, every run
Both checks are free — run them in CI so your agent re-audits us on every deploy. Every specimen and its expected verdict: golden specimens.
Verify every verdict you store
Verdicts are signed; verification needs only our public key and standard crypto — code for Python, Node and openssl here. An agent that archives verified certificates builds an audit trail nobody can dispute — including us.