Domains

Every kind of production traffic,
from medicine to entertainment.

We take production telemetry from every domain — clinical reasoning, legal drafting, financial analysis, code review, customer support, marketing copy, research workflows, entertainment and creative. If a real team is running a real model against it in production, it has a place in the research corpus.

MedicineClinical notes, diagnostic reasoning, medical Q&A, drug interactions.321Kproduction traces · ~7 hops
LegalContracts, jurisprudence, compliance review, discovery analysis.215Kproduction traces · ~12 hops
FinanceEquity research, risk modeling, compliance, transaction analysis.962Kproduction traces · ~9 hops
CodeCode review, refactoring, incident triage, system design.8.2Mproduction traces · ~5 hops
Science & researchLiterature synthesis, experimental design, statistical analysis.542Kproduction traces · ~8 hops
Customer supportTicket triage, intent classification, first-touch resolution.19Mproduction traces · ~3 hops
Marketing & contentCopy ideation, A/B variants, brand-voice transfer.4.1Mproduction traces · ~4 hops
Entertainment & creativeStory drafting, character dialogue, gaming NPCs, image-prompt iteration.31Mproduction traces · ~2 hops
Browser & computer useAgentic web tasks, UI automation, DOM interaction, computer-use sessions.143Kproduction traces · ~6 hops
What the corpus looks like

Production traces,
by vertical.

Full agent traces — system prompt, attached exports, tool calls, subagents, and completion. Samples are redacted; the corpus contains millions per vertical.

tracesess_ep_a4f9e2b1…2026-05-22T14:32ZDeepSeek-V34m 18s · 16 steps
⌜ system prompt · click to collapse
## Role
Clinical decision-support — ******* Health ED triage tier. NOT a diagnostic system. Recommendations require attending co-sign before any order is signed.

## Hard rules
1. Never invent a lab value. If it's not in the attached FHIR bundle, say so.
2. Cite every recommendation to a document ID (LCD #, pathway §, formulary row).
3. Defer to the on-call attending for anything outside the active ACS / sepsis / stroke pathways.
4. Never use external knowledge of branded protocols — only the internal pathway PDFs you have.
5. Output redactions: any PHI in the FHIR bundle must remain redacted in your response.

+1,247 lines redacted
⌝ 6 documents attached
  • fhir_bundle_pt_a4f9e2b1_2026-05-22T14:32:00Z.ndjson +2,184L
  • hl7_orm_o01_lab_orders.txt +47L
  • epic_chart_review_last_90d.xml +1,847L
  • dicom_metadata_only_ECG_12L.json +94L
  • cms_lcd_l34522_chest_pain.pdf +1,104L
  • internal_acs_pathway_v3.2.md +418L
user · turn

got a 65yo male in ed, chest pain started like 20min ago radiating to left arm. ecg shows st depression v4-v6, trop came back 0.32. whats the play here, acs pathway? need citations for lcd

U
Dee
+0ms · trace.start

medicine-agent · prod-us-east-1

+420ms · thinking

ED attending described ST depression V4-V6 + trop 0.32 → high-risk NSTEMI picture. Need to confirm against the full lab panel before drafting ACS pathway. Pulling recent observations for trop, hgb, creatinine, WBC, albumin — egfr matters for heparin dosing.

+1,847 lines of reasoning
▸ fhir.search()+5.8s · 308ms
{
  patient: "a4f9e2b1",
  resourceType: "Observation",
  code: ["2093-3", "718-7", "2160-0", "6690-2", "1751-7"],
  _count: 100,
  _sort: "-date",
  _include: "Observation:performer"
}
{
  resourceType: "Bundle",
  type: "searchset",
  total: 47,
  link: [
    { relation: "self", url: "/Observation?patient=a4f9e2b1&_count=100" },
    { relation: "next", url: "/Observation?patient=a4f9e2b1&_offset=100" }
  ],
  took_ms: 308,
  source: "epic.fhir.r4",
  served_by: "epic-fhir-prod-04",
  etag: "W/\"2284912-rev17\"",
  entry: [
    {
      resource: {
        resourceType: "Observation",
        id: "obs_2284912",
        status: "final",
        category: [{ coding: [{ code: "laboratory" }] }],
        code: { coding: [{ system: "http://loinc.org", code: "2093-3",
                            display: "Troponin I [Mass/volume] cardiac" }] },
        subject: { reference: "Patient/a4f9e2b1" },
        effectiveDateTime: "2026-05-22T14:18:00Z",
        valueQuantity: { value: 0.32, unit: "ng/mL",
                         system: "http://unitsofmeasure.org", code: "ng/mL" },
        interpretation: [{ coding: [{ code: "H", display: "High" }] }],
        referenceRange: [{ low: { value: 0.0 }, high: { value: 0.04 } }],
        performer: [{ reference: "Practitioner/p_44211" }],
        encounter: { reference: "Encounter/enc_a4f9e2b1_v18" },
        issued: "2026-05-22T14:21:14Z"
      }
    },
    {
      resource: {
        resourceType: "Observation", id: "obs_2284913", status: "final",
        code: { coding: [{ code: "718-7", display: "Hemoglobin" }] },
        valueQuantity: { value: 13.4, unit: "g/dL" },
        referenceRange: [{ low: { value: 13.5 }, high: { value: 17.5 } }],
        interpretation: [{ coding: [{ code: "L" }] }],
        effectiveDateTime: "2026-05-22T14:18:00Z", issued: "2026-05-22T14:21:14Z"
      }
    },
    {
      resource: {
        resourceType: "Observation", id: "obs_2284914", status: "final",
        code: { coding: [{ code: "2160-0", display: "Creatinine" }] },
        valueQuantity: { value: 1.21, unit: "mg/dL" },
        referenceRange: [{ low: { value: 0.7 }, high: { value: 1.3 } }],
        effectiveDateTime: "2026-05-22T14:18:00Z"
      }
    },
    { resource: { resourceType: "Observation", id: "obs_2284915", code: { coding: [{ code: "6690-2", display: "WBC" }] }, valueQuantity: { value: 11.2, unit: "10*3/uL" }, interpretation: [{ coding: [{ code: "H" }] }] } },
    { resource: { resourceType: "Observation", id: "obs_2284916", code: { coding: [{ code: "1751-7", display: "Albumin" }] }, valueQuantity: { value: 3.9, unit: "g/dL" } } },
    …42 more
  ]
}
+11.5s · thinking

Trop 0.32 ng/mL is 8× upper limit. Hgb 13.4 borderline-low (relevant for bleed risk with DAPT). Creatinine 1.21 → eGFR ~62 — keep that for heparin dosing. WBC mildly elevated, consistent with acute insult. This is enough to commit to NSTEMI workup. Spawning clinical-reasoner subagent to handle the cite-locking in parallel while I draft orders.

+2,104 lines of reasoning
⊕ subagent.spawn+15.4s

clinical-reasoner · budget=32k · model=opus-4.7

▸ rxnorm.interaction_check()+20.7s · 142ms
{
  drugs: [
    { rxcui: "1191",    name: "aspirin",     dose_mg: 325 },
    { rxcui: "1116632", name: "ticagrelor",  dose_mg: 180 },
    { rxcui: "6809",    name: "metformin",   dose_mg: 1000 },
    { rxcui: "83367",   name: "atorvastatin", dose_mg: 80 }
  ],
  include_food: true,
  severity_min: "minor",
  patient_age: 65,
  patient_egfr: 62
}
{
  request_id: "rx_int_8e2f4a1",
  severity_max: "minor",
  interactions_total: 3,
  interactions: [
    {
      pair: ["ticagrelor", "metformin"],
      severity: "minor",
      mechanism: "pharmacokinetic",
      onset: "delayed",
      documentation: "fair",
      clinical_effect: "minor — no signif. AUC change observed",
      management: "no adjustment needed",
      references: [
        { type: "drug_label",  source: "fda_pi_brilinta_2024" },
        { type: "monograph",   source: "lexicomp:LXM4128" }
      ]
    },
    {
      pair: ["aspirin", "ticagrelor"],
      severity: "minor",
      mechanism: "additive bleeding risk (expected, DAPT)",
      management: "expected with DAPT — monitor for bleeding"
    },
    {
      pair: ["atorvastatin", "ticagrelor"],
      severity: "minor",
      mechanism: "CYP3A4 substrate competition",
      management: "no dose adjustment under 80mg atorvastatin"
    }
  ],
  contraindications: [],
  allergies_checked: ["sulfa", "nsaid"],
  egfr_warnings: [],
  pregnancy_warnings: { applicable: false }
}
▸ lookup_icd10() × 3+28.6s · 28ms
{ code: "I21.4", include_drg: true, include_hcc: true }
{
  code: "I21.4",
  description: "Non-ST elevation (NSTEMI) myocardial infarction",
  billable: true,
  category: "I21",
  chapter: "Diseases of the circulatory system (I00-I99)",
  effective: { from: "2023-10-01", to: null },
  drg_candidates: [
    { drg: 280, title: "Acute MI, discharged alive w/MCC",  rw: 1.624, gmlos: 5.1 },
    { drg: 281, title: "Acute MI, discharged alive w/CC",   rw: 1.012, gmlos: 3.6 },
    { drg: 282, title: "Acute MI, discharged alive w/o CC", rw: 0.715, gmlos: 2.4 }
  ],
  hcc_2026: { v28_hcc: "HCC-222", rxhcc: "RxHCC-186", coefficient: 0.227 },
  excludes1: ["I22.* (subsequent STEMI/NSTEMI)"],
  includes:  ["myocardial infarction, subendocardial",
              "myocardial infarction, nontransmural"],
  notes:     ["Use additional code, if applicable, for status post administration of tPA (rTPA)"]
}
▸ cms.lcd.match()+37.5s · 412ms
{
  pathway: "acs_chest_pain",
  facts: {
    trop_i: { value: 0.32, unit: "ng/mL", time: "2026-05-22T14:18Z" },
    ecg_findings: ["ST_depression_v4_v6", "no_q_waves", "rate_88"],
    age_years: 65,
    sex: "male",
    comorbid: ["HTN", "T2DM", "former_smoker_15_py"],
    grace_score: 142,
    timi_score: 4
  },
  mac: "Noridian_JF",
  effective_date: "2026-05-22"
}
{
  lcd: "L34522",
  title: "Cardiac Catheterization and Angiography",
  mac: "Noridian_JF",
  version: "R12 (eff. 2026-01-01)",
  criteria_met: 4,
  criteria_total: 4,
  required: [
    { id: "B.2", text: "Troponin I >99th %ile URL", met: true,  evidence: "obs_2284912 · 0.32 ng/mL · ref<0.04" },
    { id: "B.3", text: "Ischemic ECG changes",      met: true,  evidence: "ECG 14:30Z · ST depression V4–V6" },
    { id: "C.1", text: "Symptoms consistent w/ACS", met: true,  evidence: "presenting hx · onset <24h" },
    { id: "D",   text: "GRACE risk score > 140",    met: true,  evidence: "computed=142 (in-band intermediate-high)" }
  ],
  citations: ["L34522§B.2","L34522§B.3","L34522§C.1","L34522§D"],
  invasive_strategy_window: "early (<24h)",
  expected_modifier_28_required: false,
  noridian_lcd_url: "https://med.noridianmedicare.com/lcd/L34522",
  audit_token: "lcd_match_2284912_v12_a8f3"
}
▸ epic.note_template.fetch()+45.1s · 188ms
{ template_id: "ED_disposition_v6_acs", department: "ED", attending_role: true }
{
  template_id: "ED_disposition_v6_acs",
  version: 6,
  last_updated: "2026-04-12",
  format: "cda",
  cda_root: "2.16.840.1.113883.10.20.22.1.2",
  sections: [
    { code: "10164-2", title: "History of Present Illness",       required: true,  placeholders: 3 },
    { code: "29299-5", title: "Reason for Visit",                  required: true,  placeholders: 1 },
    { code: "30954-2", title: "Relevant diagnostic tests / labs",  required: true,  placeholders: 4 },
    { code: "11369-6", title: "History of immunizations",          required: false, placeholders: 0 },
    { code: "47519-4", title: "Procedures",                        required: true,  placeholders: 2 },
    { code: "8716-3",  title: "Vital Signs",                       required: true,  placeholders: 2 },
    { code: "10160-0", title: "Medications administered",          required: true,  placeholders: 0 },
    { code: "10183-2", title: "Hospital Discharge Medications",    required: true,  placeholders: 0 },
    { code: "78375-3", title: "Disposition (HP)",                  required: true,  placeholders: 2 }
  ],
  placeholders_total: 14,
  required_signers: ["attending_physician"],
  bypass_allowed_for: [],
  default_routing: ["chart","release_of_info","payer_portal"]
}
▸ ncqa.hedis.evaluate()+57.4s · 247ms
{ measure: "CMS90v9", patient: "a4f9e2b1", measurement_year: 2026 }
{
  measure: { id: "CMS90v9", title: "Functional Status Assessment for Heart Failure", version: 9 },
  patient: "a4f9e2b1",
  measurement_year: 2026,
  eligible: true,
  in_initial_population: true,
  denominator: true,
  numerator: false,
  exclusions_applied: [],
  attribution: {
    plan_id: "humana_hmo_4419",
    pcp:     "primary_care_pcp_4421",
    network: "in_network",
    attribution_method: "12mo_plurality_visits"
  },
  evidence_gaps: [
    { code: "Z02.6", required_by: "2026-12-31", suggested_action: "schedule FSA within 90 days" }
  ],
  star_impact: { plan: "humana_hmo_4419", contribution: "+0.04", current_stars: 4 }
}
+1m13s · thinking

Drug interactions all minor — expected for DAPT, no contraindications. ICD-10 I21.4 maps cleanly. LCD L34522 §B-D all met (trop, ECG, symptoms, GRACE>140). HEDIS measure flagged FSA gap but that's a 90-day follow-up, not blocking the disposition. Subagent should be wrapping. While I wait I'm building the order set: ASA 325 stat, ticagrelor 180 load, weight-based heparin (need pt weight from chart), atorvastatin 80 QHS, stat cardiology consult.

+2,682 lines of reasoning
↩ subagent.completereturned at +1m58s
subagent · output
  • confidence0.91
  • 6 citations locked
  • 412 tokens spent
▸ epic.orders.draft()+2m09s · 642ms
{
  patient: "a4f9e2b1",
  encounter: "enc_a4f9e2b1_v18",
  orders: [
    { code: "ASA_325_PO_x1",            class: "med",     priority: "stat" },
    { code: "TICAGRELOR_180_LOAD_PO",   class: "med",     priority: "stat" },
    { code: "HEPARIN_GTT_WEIGHT_BASED", class: "med",     priority: "stat",
      params: { weight_kg: 92.4, units_per_kg_bolus: 60, units_per_kg_hr: 12 } },
    { code: "ATORVASTATIN_80_PO_QHS",   class: "med",     priority: "routine" },
    { code: "CARDIOLOGY_CONSULT",       class: "consult", priority: "stat" }
  ],
  cosign_required: true,
  reason_for_order: "NSTEMI per LCD L34522 §B–D",
  problem_list_link: "I21.4"
}
{
  drafts: 5,
  status: "pending_attending_cosign",
  cosigner_routed_to: ["attending_oncall_44219"],
  best_practice_alerts: [
    { id: "BPA_1284", title: "Heparin weight-based dosing",
      severity: "info", action: "displayed", auto_applied: true },
    { id: "BPA_4221", title: "Statin intolerance check",
      severity: "info", action: "displayed", auto_applied: false }
  ],
  order_ids: [
    { id: "o_4291", code: "ASA_325_PO_x1",            status: "draft", expires: "2026-05-22T22:32Z" },
    { id: "o_4292", code: "TICAGRELOR_180_LOAD_PO",   status: "draft", expires: "2026-05-22T22:32Z" },
    { id: "o_4293", code: "HEPARIN_GTT_WEIGHT_BASED", status: "draft", expires: "2026-05-22T22:32Z" },
    { id: "o_4294", code: "ATORVASTATIN_80_PO_QHS",   status: "draft", expires: "2026-05-22T22:32Z" },
    { id: "o_4295", code: "CARDIOLOGY_CONSULT",       status: "draft", expires: "2026-05-22T22:32Z" }
  ],
  audit: { actor: "agent:sonnet-4.7", co_signer_required: true, hash: "9f2a…84e1" }
}
+2m20s · thinking

Orders drafted and queued for attending co-sign. BPAs displayed but not blocking. Now composing the disposition note: lead with the NSTEMI dx + LCD citations, then the 5 orders with the rationale per order, then the cath-lab handoff (early invasive < 24h per GRACE > 140). Attending only needs to co-sign — no extra context required since all citations point to L34522.

+3,014 lines of reasoning
Dee
+3m13s · assistant.completion

Consistent with NSTEMI per LCD L34522 criteria A–D. Initiate dual antiplatelet (ASA 325 + ticagrelor 180 load), high-intensity statin, weight-based heparin gtt. Pursue invasive strategy within 24h given GRACE > 140. Drafted four orders pending attending co-sign…

Dee
+4m18s · trace.end

14 tools · 1 subagent · PII pass ✓ · attending review queued

input
28,412
output
1,247
TTFT
520ms
tps
72
cost
$0.184

Samples shown are redacted excerpts from contributor traces. All PII is removed at ingest via three-pass redaction; tenant identifiers are masked. GOAT labs does not provide medical, legal, or financial advice. Model and vendor names are trademarks of their respective owners.

Contribute

Get cashback on your tokens,
advance the research.

We pay 5–15% of the original model's output-token price. The rate scales with trace complexity — function calls, external API lookups, multi-turn depth, and multi-agent activity all push the rate higher.

Get paid via:PayPalUSDTVenmoACH or Card
  1. 01

    Observability platform

    Bring a read-only API key from Braintrust, Langfuse, Datadog, Laminar, Arize, Helicone, LangSmith, and 10+ more. No code to write — we pull from your existing pipeline.

  2. 02

    Editor or CLI tool

    Connect Cursor, Claude Code, or OpenAI Codex in one click. We tail your usage endpoint and calculate cashback on every token.

Start contributingTalk to research
$25,000/mo
$500$500K
Estimated payout · annual3.00× multiplier
$31,500/yr$2,625/mo
≈ 10.5% of your total LLM bill.
bt_ · pk-lf- · dd_ · lmnr_
Estimate your monthly payouts
BraintrustBraintrustLangfuseLangfuseDatadogDatadogLaminarLaminarArizeArizePhoenixPhoenixHeliconeHeliconeLangSmithLangSmithWeaveWeaveGalileoGalileoOpikOpikLangTraceLangTraceHoneyHiveHoneyHiveTraceloopTraceloopLunaryLunary

— or connect your editor directly —

CursorClaude CodeCodex