{"schema_version":"1","site":"https://decosa.ai","id":"medicare-call-record","num":"59","name":"Medicare sales-call record","tool_name":"Review a Medicare sales call","short":"Medicare call record","blurb":"QA and a signed record for recorded Medicare Advantage and Part D sales calls. On the call it answers yes, no or unclear, with a quote and a time: the TPMO disclaimer and whether it came before benefits were discussed, the Scope of Appointment, \"free\" for a $0 premium, claiming to be Medicare, gifts, pressure, and the steps of an enrollment. Every benefit the agent states is checked against the plan's Summary of Benefits. Signed record with the retention dates of the 1 Jun 2026 rule.","status":"live","labels":{"industry":["healthcare","sales-marketing"],"job":["review","attest"],"input":["voice","text"],"deploy":["selfhost"],"status":"live","output":["record","data"],"data":["phi","pii"],"hardware":"gpu-96","licence":"permissive"},"industries":["healthcare","sales-marketing"],"runs_in":["selfhost"],"part_of":[],"built_from":["diarize","typed-judgment","grounding","signed-record"],"models":"MOSS-Transcribe-Diarize · Qwen3.8-27B","where":"Self-host for real calls (hosted demo: synthetic role-plays only)","hardware":"1× RTX PRO 6000 (96 GB) for Qwen3.8-27B and the diarizer; the call-sheet items and the record need no GPU","final_artifact":"A QA checklist of typed answers with quotes and times, the call-sheet items, each benefit claim with its verdict against the plan facts, and a signed record with its retention dates.","self_host_first":true,"verification":{"receipt_coverage":"full","summary":"Receipt per model call; every yes backed by a quote found in the transcript; each benefit claim judged against the plan facts with the span cited; signed hash-chained record with retention dates","manual_qa":{"hosted":{"date":"2026-09-26","result":"pass","p50_ms":7468,"p95_ms":null,"runs":null,"receipts_per_run":15,"cost_per_run_usd":0.0058},"selfhost":{"date":"2026-09-26","result":"pass","method":"fresh clone of decosa-api into a clean directory on our server, api image built from docker/api/Dockerfile, compose api service with a named data volume, direct route, local signing; torn down after","notes":"The assembly prompt's smoke tests ran against the already-running local Qwen3.8-27B vLLM (127.0.0.1:8114, network_mode host instead of the compose llm service): tb1-showcase flagged the disclaimer timing, \"free\", the final-expense pitch and the $3,000 dental claim (contradicted), 15 attested receipts, record verified, retention 2029-11-05 / 2032-11-05, 3.8 s; the pasted cold call flagged Medicare, free, unsolicited, no SOA and the dental claim; no consent gave 400."},"known_limits":["Hosted verification ran on the pre-release server (decosa-api the pre-release branch on our server, gateway route). The production API gets this vertical when the branch merges.","Measured on 17 short synthetic role-plays written by the building agent, with clean TTS audio. Not measured on real sales calls (20-60 minutes, accents, transfers, Spanish) or with an independent reviewer's labels.","Claims the plan facts do not mention come back flagged even when true (2-3 on a clean drug-plan call); give the full Summary of Benefits.","ASR errors become claim errors: \"eyewear\" heard as \"in-store\" was flagged in one audio run.","Audio intake (/medicare/transcribe) is self-host only. The hosted demo's audio samples were transcribed on our server and are bundled."],"nightly_covers":null},"nightly":"https://api.decosa.ai/verify/status"},"eval_summary":{"metrics":[{"name":"Per-rule accuracy, test B run 1 (never used to change anything)","value":"40/40","unit":null,"n":40,"split":"heldout","note":"Run 2: 40/40"},{"name":"Per-rule accuracy, test run 4","value":"101/101","unit":null,"n":101,"split":"test","note":"Run 1 (before the one code change): 101/101"},{"name":"Planted typed answers found, test run 4","value":"9/9","unit":null,"n":9,"split":"test","note":"Test B: 2/2; audio: 9/9 (also on the re-voiced audio)"},{"name":"Call-sheet items, test run 4 / test B run 1","value":"79/79 / 31/32","unit":null,"n":111,"split":"test","note":"Test run 1, before the needs change: 77/79"},{"name":"Benefit claims graded right (good ok, bad flagged), test run 4","value":"25/25 / 4/4","unit":null,"n":29,"split":"test","note":"Test B: 8/8 / 2/2; audio (re-voiced 26 Sep 2026 with Decosa house voices) runs 1 and 2: 18/19 / 2/3, both misses on t9 where the diarizer split a line and the scorer paired claims with the wrong gold lines (first build: 19/19 / 3/3 and 18/19 / 3/3)"},{"name":"False alarms on clean calls, test run 4 / test B run 1","value":"3 of 87 / 0 of 42","unit":null,"n":129,"split":"test","note":"All 3 are claims the plan facts do not mention"},{"name":"Cited time inside the spoken gold line, audio run 1","value":"28/29","unit":null,"n":29,"split":"test","note":"Audio re-voiced 26 Sep 2026 with Decosa house voices (Kokoro-82M) and re-run: 21/29 within 3 s of the line's start; run 2: 29/29. First build (macOS voices): 29/29, 16/29 within 3 s"}],"dataset":"17 synthetic scripted Medicare sales calls with fictional agency, plans and people, written from 42 CFR 422/423 subpart V: 3 dev, 10 test, 4 test B, plus 8 of them as TTS audio (Decosa house voices, Kokoro-82M, each allowed by the consent ledger) run through the diarizer.","held_out":true,"caveats":["The same author wrote the scripts, the labels, the prompts and the code; the labels are one reading of the rule text.","17 short scripted calls with clean TTS audio; real sales calls (long, accents, transfers, Spanish) are not measured.","One code change (the premiums needs topic) was made after test run 1, so test is not fully held out for that item; test B was never used to change anything. The scorer's audio matching was refined after the audio runs, before this write-up.","Benefit claims are judged against the plan facts given, not the plan's filed benefits.","Answer probabilities and claim confidences come from tables fit on other domains and are not calibrated for sales calls."],"date":"2026-09-26","doc_url":"https://decosa.ai/metrics/evals/medicare-call-record"},"stack":{"summary":"For third-party marketing organizations (agencies, FMOs, call centres), independent agents and plan broker-oversight teams. Give it the sales call (audio on your own box, or a transcript), a call sheet (when the call was placed and who asked for it, your plan counts, the Scope of Appointment) and the plan's Summary of Benefits as text. On the call it answers yes, no or unclear, each with a quote and its time: the TPMO disclaimer, a Scope of Appointment read on the call, \"free\" for a $0 premium, claiming to be Medicare, calling an Advantage plan a supplement, gifts, pressure, and for an enrollment the enrollment notice, a clear yes and where the Summary of Benefits is. In code: whether the disclaimer came before benefits were discussed (the rule since 1 Jun 2026), its numbers, the SOA's date and scope, non-health products, cold calls, and the needs topics and pre-enrollment checklist before an enrollment. Every premium, copay, allowance or giveback the agent states is judged against the Summary of Benefits. Everything is sealed in a signed, hash-chained record with the retention dates. It is QA triage for a compliance reviewer, not a compliance verdict.","tagline":"A recorded Medicare Advantage or Part D sales call checked against the CMS marketing rules, each answer quoted with its time, every benefit claim checked against the plan's Summary of Benefits, sealed in a signed record.","deployment":"self-host-first","regulatory_note":"Checked 26 Sep 2026 against eCFR (title 42 current to 24 Sep 2026) and the Federal Register. Medicare Advantage and Part D communications and marketing, 42 CFR 422.2260-422.2274 and 423.2260-423.2274, as amended by the CY2027 final rule (91 FR 17384, 6 Apr 2026, effective 1 Jun 2026; CMS's tip sheet 12237-P applies the marketing changes to CY2027 marketing from 1 Oct 2026). Encoded: the TPMO disclaimer, now said before any discussion of benefits (was: within the first minute) and without the SHIP reference (422.2267(e)(41)); the Scope of Appointment agreed and recorded before a personal marketing appointment, no 48-hour wait any more, no products beyond its scope, valid 12 months (422.2264(c)(3), 422.2274(b)(3)); no non-health products such as annuities (422.2263(b)(4); life insurance is treated as non-health here, our reading); no unsolicited calls (422.2264(a)); no \"free\" for a $0 premium or reduced cost sharing, no claim of Medicare endorsement or misleading use of the Medicare name, no implying a plan is a supplement (422.2262(a)(1)); no cash or non-nominal gifts (422.2263(b)); the needs topics before an enrollment (422.2274(c)(12)), the pre-enrollment checklist reviewed and the Summary of Benefits location given on a telephonic enrollment (422.2267(e)(4), (e)(5)); the telephonic SOA elements from the MCMG (16 Mar 2022). Retention: marketing and sales calls recorded in full and kept 6 years, in audio for years 1-3 and audio or a complete and accurate transcript for years 4-6 (422.2274(g)(2)(ii) as amended; 10 years before 1 Jun 2026); the enrollment portion of a telephonic enrollment is the enrollment form and stays under the 10-year record rule (422.504(d); 91 FR 17463-17464). \"Pressure tactics\" is not a defined term; it is checked as misleading conduct (422.2262). Recording consent is state law (e.g. California Penal Code 632). Sales calls carry PHI: HIPAA applies to plans and their business associates. QA triage, not legal advice.","components":[{"id":"llm","role":"Two extractions (products, first benefit discussion, enrollment steps; the agent's benefit claims), one typed yes/no/unclear check per question, and one grounding judgment per benefit claim against the plan facts","name":"Qwen3.8-27B (NVIDIA NVFP4)","hf_repo":"nvidia/Qwen3.8-27B-NVFP4","license":"Apache-2.0","params":"27.8B","quant":"NVFP4 (MLP) + FP8 (attention/GDN), FP8 KV cache, MTP speculative decoding k=3","vram_gb":57,"memory_gb_estimate":null,"engine":"vLLM 0.29.0","receipt_coverage":"strong","in_hosted_demo":true,"tiers":["standard"],"alternative_to":null},{"id":"asr","role":"Recording to a timed, speaker-labelled transcript (POST /medicare/transcribe, self-host; the demo's audio samples were transcribed with it)","name":"MOSS-Transcribe-Diarize 0.9B","hf_repo":"OpenMOSS-Team/MOSS-Transcribe-Diarize","license":"Apache-2.0","params":"0.9B","quant":"BF16","vram_gb":null,"memory_gb_estimate":null,"engine":"transformers (trust_remote_code) + moss_transcribe_diarize package (decosa-api services/diarize)","receipt_coverage":"partial","in_hosted_demo":false,"tiers":["standard","best","lite"],"alternative_to":null},{"id":"llm-lite","role":"Lite tier: the same extractions, checks and claim judge on a 48 GB card","name":"Gemma 4 26B A4B (instruction-tuned)","hf_repo":"google/gemma-4-26B-A4B-it","license":"Apache-2.0 (model card also links the Gemma 4 licence page)","params":"25.2B","quant":"BF16 weights; FP8 at load time (vLLM --quantization fp8) to fit a 48 GB card","vram_gb":null,"memory_gb_estimate":null,"engine":"vLLM 0.29.0 (Gemma4ForConditionalGeneration is in its model registry)","receipt_coverage":"none","in_hosted_demo":false,"tiers":["lite"],"alternative_to":null},{"id":"llm-best","role":"Best tier: a larger model for long calls and hard cases","name":"DeepSeek-V4-Flash (NVIDIA NVFP4)","hf_repo":"nvidia/DeepSeek-V4-Flash-NVFP4","license":"MIT","params":"284B","quant":"NVFP4 experts + FP8 (about 159-176 GB of weights)","vram_gb":192,"memory_gb_estimate":null,"engine":"vLLM B12X community build, TP2 on 2x RTX PRO 6000, MTP draft fixed by the kit's patches","receipt_coverage":"none","in_hosted_demo":false,"tiers":["best"],"alternative_to":null},{"id":"glm-wanted","role":"Second judge, from another family","name":"GLM-5.3-Flash","hf_repo":"zai-org/GLM-5.3-Flash","license":"MIT","params":"321B","quant":"NVFP4 on NVIDIA (nvidia/GLM-5.3-Flash-NVFP4, about 170-186 GB, unconfirmed); MLX 4-bit on a Mac (165 GB)","vram_gb":null,"memory_gb_estimate":170,"engine":"SGLang SM120 build, TP2 on 2x 96 GB (vLLM is broken on sm_120 for this model, and the SGLang build hung on our server), or mlx-lm on a Mac with 192 GB or more","receipt_coverage":"none","in_hosted_demo":false,"tiers":["wanted"],"alternative_to":null}],"tiers":[{"id":"lite","label":"Lite · one 48 GB card","summary":"The same checks and claim judge on a smaller mixture-of-experts model. Faster and cheaper; accuracy on this task unknown.","components":["llm-lite","asr"],"hardware":"1x L40S or RTX 6000 Ada 48 GB (not measured)","quality_evidence":[{"metric":"typed checks correct / claims graded right","value":"not measured yet","source":null}],"latency_note":"not measured yet","in_hosted_demo":false,"receipt_coverage":"partial","receipt_note":"Direct route: calls are attested by the box's key; no gateway receipts.","hosting":null},{"id":"standard","label":"Standard · the hosted demo, one 96 GB card","summary":"Qwen3.8-27B extracts, answers every typed check and judges every benefit claim; MOSS-Transcribe-Diarize turns recordings into transcripts; the call-sheet items are code. Every model call receipted.","components":["llm","asr"],"hardware":"1x RTX PRO 6000 Blackwell 96 GB","quality_evidence":[{"metric":"held-out test B, 4 synthetic calls: typed checks / call-sheet items / claims graded right / false alarms on the 2 clean calls","value":"40/40 / 31/32 / 10/10 / 0 of 42","source":"decosa-api docs/evals/medicare-call-record.md, measured on our server 2026-09-26, gateway route, run 1 (run 2 the same); prompts frozen on a 3-call dev split; data, labels and prompts written by the building agent"},{"metric":"test set, 10 calls: typed checks / planted typed answers / call-sheet items / good claims ok / bad claims flagged","value":"101/101 / 9/9 / 79/79 / 25/25 / 4/4","source":"decosa-api docs/evals/medicare-call-record.md, measured on our server 2026-09-26, gateway route, run 4, after one code change made on test run 1 (77/79 call-sheet items before it)"},{"metric":"false alarms on the 4 clean test calls (flag or review)","value":"3 of 87 (claims the plan facts do not mention)","source":"decosa-api docs/evals/medicare-call-record.md, measured on our server 2026-09-26, gateway route, run 4"},{"metric":"on diarized TTS audio, 8 calls: typed checks / call-sheet items / claims graded right / cited time inside the spoken line","value":"81/81 / 63/63 / 20/22 / 28/29 (run 2: 20/22 claims, 29/29)","source":"decosa-api docs/evals/medicare-call-record.md, measured on our server 2026-09-26 on audio re-voiced 26 Sep 2026 from macOS voices to Decosa house voices (Kokoro-82M) (the first build: 22/22 and 21/22 claims, 29/29), gateway route, asr runs 1 and 2"}],"latency_note":"measured under shared gateway load: seconds per call, about a minute at the slowest; longer on the re-voiced audio runs, a busier gateway","in_hosted_demo":true,"receipt_coverage":"strong","receipt_note":null,"hosting":null},{"id":"best","label":"Best · two 96 GB cards","summary":"A larger model for long calls and many benefit claims. Not measured on this task.","components":["llm-best","asr"],"hardware":"2x RTX PRO 6000 Blackwell 96 GB","quality_evidence":[{"metric":"typed checks correct / claims graded right","value":"not measured yet","source":null}],"latency_note":"not measured yet","in_hosted_demo":false,"receipt_coverage":"none","receipt_note":"Not a hosted model: direct route, calls attested by the box's key.","hosting":null},{"id":"wanted","label":"Wanted · two large judges from different families","summary":"DeepSeek-V4-Flash and GLM-5.3-Flash each read the file, and a finding stands when they agree; disagreements go to the reviewer. Patient calls stay on your own hardware, never on community providers. Not served yet.","components":["llm-best","asr","glm-wanted"],"hardware":"Your own hardware: 2x 96 GB cards for DeepSeek-V4-Flash plus 2x 96 GB for GLM-5.3-Flash, or one Mac Studio with 512 GB holding both 4-bit builds (156 + 165 GB, sizes from our Mac; not run together yet). Estimate.","quality_evidence":[{"metric":"typed checks correct / claims graded right","value":"not measured yet","source":null}],"latency_note":"not measured yet","in_hosted_demo":false,"receipt_coverage":"none","receipt_note":"On your own hardware its calls are attested by the box's key only: not a hosted model there, so no gateway receipts. Never sent to community providers.","hosting":"own-hardware"}],"alternates":[],"services":[{"name":"decosa-api","port":8445,"image":"${DECOSA_REGISTRY}/decosa-api:0.1.0","purpose":"Transcript, call-sheet and plan-facts intake, the checks, the call-sheet items, signing and the HTTP API (/medicare/*). No GPU. Binds 127.0.0.1 by default."},{"name":"decosa-llm","port":8000,"image":"${DECOSA_REGISTRY}/decosa-llm:0.1.0","purpose":"vLLM OpenAI endpoint for Qwen3.8-27B. Internal to the compose network."},{"name":"decosa-diarize","port":8092,"image":null,"purpose":"Optional, self-host only: MOSS-Transcribe-Diarize for transcripts made from recordings (DECOSA_MEDICARE_AUDIO=1). No published image yet; built from services/diarize."}],"tools":[{"name":"decosa call engine: F&I disclosure record (46) and collections call QA (55)","url":"https://decosa.ai/apps/collections-call-qa","license":"AGPL-3.0-or-later (decosa-api)","purpose":"Transcript intake, answer parsing and quote matching; imported, not copied."},{"name":"decosa grounding check (vertical 17)","url":"https://decosa.ai/apps/grounding","license":"AGPL-3.0-or-later (decosa-api)","purpose":"The sentence judge and evidence spans behind each benefit-claim verdict."},{"name":"decosa typed-judgment (vertical 24)","url":"https://decosa.ai/apps/typed-judgment","license":"AGPL-3.0-or-later (decosa-api)","purpose":"The stated-confidence probability for each typed check."},{"name":"decosa record (vertical 07) and POST /record/verify","url":"https://decosa.ai/apps/record","license":"AGPL-3.0-or-later (decosa-api)","purpose":"The hash chain, signed checkpoints and the Ed25519-signed record; anyone can re-check it."},{"name":"42 CFR part 422 subpart V and part 423 subpart V, eCFR","url":"https://www.ecfr.gov/current/title-42/part-422/subpart-V","license":"public law","purpose":"The source of every rule; each checklist item links its section."},{"name":"CY2027 MA and Part D final rule, 91 FR 17384 (Federal Register)","url":"https://www.federalregister.gov/documents/2026/04/06/2026-06600/medicare-program-contract-year-2027-and-certain-contract-year-2026-policy-and-technical-changes-to","license":"public law","purpose":"The 1 Jun 2026 changes: disclaimer timing, SOA timing, 6-year retention with transcripts in years 4-6."},{"name":"cryptography (Python)","url":"https://cryptography.io/","license":"Apache-2.0 OR BSD-3-Clause","purpose":"Ed25519 signatures on the record and the speech receipts."}],"hardware":[{"tier":"1x RTX PRO 6000 Blackwell 96 GB","fits":true,"notes":"Measured: the hosted demo's Qwen3.8-27B runs on one of these cards on our server; the diarizer runs on the other card there."},{"tier":"1x L40S / RTX 6000 Ada 48 GB","fits":null,"notes":"Not measured. FP8 Qwen3.8-27B with a shorter context, or Gemma 4 26B A4B (lite)."},{"tier":"CPU only","fits":true,"notes":"Transcript parsing, the call-sheet items, the signed record and verification need no GPU; the call checks and the claim judge need the model."}],"latency":[{"lane":"check of a 7-19 line sales call with plan facts, quiet shared gateway","typical_ms":4450,"source":"decosa-api docs/evals/medicare-call-record.md, measured on our server 2026-09-26, gateway route (test B run 2 median 4.4 s; audio runs medians 6.0-6.2 s)"},{"lane":"the same, busy shared gateway","typical_ms":14650,"source":"decosa-api docs/evals/medicare-call-record.md, measured on our server 2026-09-26, gateway route (test run 4 median 14.7 s, slowest 60.8 s; test B run 1 median 31 s)"},{"lane":"transcribe a 43-118 s recording (self-host)","typical_ms":5000,"source":"measured on our server 2026-09-26, MOSS-Transcribe-Diarize on an RTX PRO 6000 (5.2 s for 64 s of audio)"}],"benchmark":null,"notes":[]},"buyer_facts":[{"label":"What it checks","value":"On each recorded sales call: the TPMO disclaimer and whether it came before benefits, a Scope of Appointment read on the call, \"free\" for a $0 premium, claiming to be Medicare, an Advantage plan called a supplement, gifts, pressure, and for an enrollment the notice, a clear yes, where the Summary of Benefits is, the needs topics and the pre-enrollment checklist. From the call sheet: the SOA's date and scope, non-health products, cold calls, the disclaimer numbers. Every benefit claim against the Summary of Benefits."},{"label":"What it does not do","value":"It gives no compliance verdict. It checks benefit claims against the plan facts you give, not the plan's filed benefits: a partial Summary of Benefits produces false flags. It does not check the written SOA form, SMIDs, the Star Ratings document, the plan's outbound enrollment verification, agent licensing, compensation or lead-generation data sharing."},{"label":"Record-keeping dates","value":"The record carries the dates the rule sets since 1 Jun 2026: audio for 3 years, audio or a complete and accurate transcript to year 6 (42 CFR 422.2274(g)(2)(ii)), and 10 years for the enrollment portion of a telephonic enrollment. A machine transcript counts as complete and accurate only after a person checks it; the record takes that attestation."},{"label":"Consent","value":"Every run needs a statement that the call was recorded with the consent the law requires (some states need every party's). The statement goes into the signed record, and a check looks for the recording notice on the call."},{"label":"Data retention","value":"Nothing on the server. Transcripts, call sheets, plan facts and records live in memory for the request, and logs carry counts and timings only. You keep the signed record with the recording until its retention dates."},{"label":"What leaves the box (hosted demo)","value":"The transcript and the plan facts go to Qwen3.8-27B through our gateway, which is Decosa-operated. The call sheet is processed in code and not sent to the model. The gateway's receipts hold hashes, not text. Self-hosted, nothing leaves."},{"label":"Model calls per call","value":"Two extractions, 8 or 9 typed checks and one grounding call per benefit claim (up to 12): 13 to 19 calls on the eval calls; the smoke sample used 15 calls and 15,120 tokens, about $0.006."}],"hosted_now":{"needs":["qwen3.8-27b"],"off":[],"live_by_default":true,"live_status":"https://api.decosa.ai/status"},"data_handling":{"page":"/data#medicare-call-record","self_host":{"level":"confidential","leaves":"nothing","summary":"Runs on your machine; nothing is sent to Decosa or a third party by default."},"hosted":{"level":"operator-processed","demo_only":true,"summary":"Hosted demo on sample or public data only; self-host for real data.","gpus":"operator-contracted","third_parties":[],"retention":"Nothing on the server. Transcripts, call sheets, plan facts and records live in memory for the request, and logs carry counts and timings only. You keep the signed record with the recording until its retention dates.","used_for_training":false,"encrypted_while_processed":false},"sealed_tier":{"applies":false,"note":"The sealed tier (raw chat only, never use-case pipelines) is paused at launch (/docs/sealed-tier)."},"external_calls":[]},"console":{"href":"/clinics/medicare-call-record","input":"medicare","lanes":[{"id":"call","title":"On the call","kind":"list"},{"id":"sheet","title":"From the call sheet","kind":"list"},{"id":"claims","title":"Benefit claims","kind":"list"},{"id":"record","title":"Signed record","kind":"json"}],"samples":[{"n":1,"id":"tb1-showcase","title":"Tb1 showcase","deep_link":"/clinics/medicare-call-record?sample=1&autorun=0"},{"n":2,"id":"t6-cold-call-pressure","title":"T6 cold call pressure","deep_link":"/clinics/medicare-call-record?sample=2&autorun=0"},{"n":3,"id":"t8-enroll-missing-elements","title":"T8 enroll missing elements","deep_link":"/clinics/medicare-call-record?sample=3&autorun=0"},{"n":4,"id":"t9-supplement-gift-giveback","title":"T9 supplement gift giveback","deep_link":"/clinics/medicare-call-record?sample=4&autorun=0"},{"n":5,"id":"t7-outside-scope-life","title":"T7 outside scope life","deep_link":"/clinics/medicare-call-record?sample=5&autorun=0"},{"n":6,"id":"t1-clean-enroll-hmo","title":"T1 clean enroll hmo","deep_link":"/clinics/medicare-call-record?sample=6&autorun=0"},{"n":7,"id":"t3-clean-pdp-enroll-soa-on-call","title":"T3 clean pdp enroll soa on call","deep_link":"/clinics/medicare-call-record?sample=7&autorun=0"},{"n":8,"id":"t4-clean-free-allowed","title":"T4 clean free allowed","deep_link":"/clinics/medicare-call-record?sample=8&autorun=0"}],"deep_link_params":{"sample":"1-based index into samples, or a sample id","autorun":"1 = start the run once the sample is loaded; 0 (default) = only preselect","reduce-motion":"1 = turn off animations"}},"api":{"base":"https://api.decosa.ai","contract":"/api/contract.json","contract_markdown":"/api/contract.md","reference":"/docs/api","keys":"/account/keys"},"prompts":{"hosted":"/prompts/medicare-call-record-hosted.md","selfhost":"/prompts/medicare-call-record-selfhost.md","assemble":"/prompts/medicare-call-record-assemble.md","mac":null},"rehearsal":{"bundle":"/samples/medicare-call-record.zip","bundle_url":"https://decosa.ai/samples/medicare-call-record.zip","folder":"/samples/medicare-call-record/","expected":"/samples/medicare-call-record/expected.json","files":["/samples/medicare-call-record/expected.json","/samples/medicare-call-record/inputs/call-sheet.json","/samples/medicare-call-record/inputs/consent.json","/samples/medicare-call-record/inputs/plan-facts.json","/samples/medicare-call-record/inputs/transcript.txt"],"bytes":4075,"checks":["the TPMO disclaimer itself was said (only late)","benefits were discussed before the TPMO disclaimer","\"free premiums\" is flagged with a time","the free flag points at a time in the call","the final-expense life pitch is flagged","the $3,000 dental claim is flagged against the plan facts","a check without a consent statement is refused","the audio is kept three years after the call","audio or a complete transcript is kept six years after the call","the signed record verifies","a record with its flag count changed no longer verifies","every model call has a signed receipt"],"licence":"Synthetic role-play written from 42 CFR 422/423 subpart V: Prairie Lantern Benefits, Northfield Harbor Health Plan, the plan and every person are fictional. Part of decosa-api, which will be released under AGPL-3.0-or-later; until then the source is on request.","about":"A role-played sales call from a fictional agency (Prairie Lantern Benefits) for a fictional HMO, with its call sheet and the plan's Summary of Benefits. The agent pitches \"free premiums\" and a $3,000 dental allowance before the TPMO disclaimer, then a final-expense life policy. The disclaimer timing, the word free, the non-health pitch and the dental claim (the plan facts say $1,500) must be flagged, and the signed record must verify with the 1 Jun 2026 retention dates.","run":{"containers":"docker compose exec api python scripts/rehearse.py medicare-call-record","checkout":"python scripts/rehearse.py medicare-call-record --bundle medicare-call-record.zip --base-url http://127.0.0.1:8445","mac":".venv/bin/python scripts/rehearse.py medicare-call-record"},"guidance":"Set up with a coding agent (we recommend Claude Code with Claude Opus 5.5; any capable coding agent works) on mock data only, run the rehearsal until every check passes, then run your own data locally yourself. Never give the agent real data during setup."},"hardware_fit":{"check":"/self-host/hardware?use=medicare-call-record","data":"/api/hardware.json","tiers":[{"id":"lite","gpu_gb":44,"basis":"estimate","unknown":[]},{"id":"standard","gpu_gb":61.6,"basis":"estimate","unknown":[]},{"id":"best","gpu_gb":196,"basis":"estimate","unknown":[]},{"id":"wanted","gpu_gb":388,"basis":"estimate","unknown":[]}],"mac":null},"links":{"page":"/clinics/medicare-call-record","json":"/use-cases/medicare-call-record.json","metrics":"/metrics/medicare-call-record","console":"/clinics/medicare-call-record","console_sample":"/clinics/medicare-call-record?sample=1&autorun=0","stack":"/clinics/medicare-call-record#stack","try_live":"/clinics/medicare-call-record","watch":"/clinics/medicare-call-record","build":"/clinics/medicare-call-record#build","self_host":"/clinics/medicare-call-record#self-host","prompts":{"hosted":"/prompts/medicare-call-record-hosted.md","selfhost":"/prompts/medicare-call-record-selfhost.md","assemble":"/prompts/medicare-call-record-assemble.md","mac":null}}}