On architecture
Why not just ask a chatbot?
A fair question. A general-purpose chat model can tell you what adenomyosis is. It can list treatment categories. It's a real starting point. So what does a five-agent corpus-grounded pipeline actually add, beyond complexity?
Same patient profile. Two outputs. Judge for yourself.
Patient profile
32 y.o. G2P0 Toronto, OHIP. Diagnosed March 2025: TVUS suggestive of adenomyosis (no MRI). Current plan: naproxen 500mg PRN. Gynecologist has offered combined OCP as first-line, hysterectomy as fallback if that fails. Preserving fertility. 18-year pain history since age 14. ED visit for suprapubic pain. Past PID. Hgb 131. No hormonal trial of dienogest, LNG-IUS, or GnRH antagonists. What are my options?
Something she can hand to her doctor. Specific treatments ranked for her specific profile, with citations her gynecologist can verify. Red flags surfaced with evidence-based counterpoints. Care centres with real phone numbers. A printable handoff page written in her voice. A verification badge so she knows the brief itself has been fact-checked.
Not a chatbot answer. A clinician-grade briefing.
General-purpose chat assistant
Ungrounded single-turn output. Representative of what any off-the-shelf chat tool returns when asked the same question.
I'm not a doctor, but I can share some information about adenomyosis treatment options. Common treatment approaches for adenomyosis include: • **Pain management**: NSAIDs like ibuprofen or naproxen can help • **Hormonal therapy**: Birth control pills, IUDs, or other hormonal options may reduce symptoms • **GnRH agonists**: These can help manage symptoms temporarily • **Uterine artery embolization**: A minimally invasive procedure • **Hysterectomy**: Definitive treatment for those who have completed childbearing Since you mentioned you're preserving fertility, you'll want to discuss fertility-preserving options with your doctor. It's important to have a thorough conversation about your specific situation and the risks and benefits of each option. Would you like more general information about any of these? **This information is not medical advice. Please consult with a qualified healthcare provider for personalized recommendations.**
Second Opinion · corpus-grounded multi-agent
Three specialists read the profile in parallel, a synthesizer composes, a verifier fact-checks against 52 corpus sources. This is an excerpt — the full brief is ~14,000 words with every claim citable.
Your TVUS was 'suggestive' — not diagnostic — and you deserve a pelvic MRI and the full uterine-sparing treatment pathway before hysterectomy is ever mentioned again. 32 y.o. G2P0 with an 18-year history of 10/10 dysmenorrhea, TVUS 'suggestive' (moderate visibility, chart still reads 'Dysmenorrhea'), no MRI performed, fertility-preserving. Your specialist has skipped the evidence-based middle of the 2026 treatment algorithm (dienogest, LNG-IUS, GnRH antagonists, HIFU, RFA, adenomyomectomy). Your G2P0 history with two prior losses plus suspected adenomyosis carries ~31% lower clinical pregnancy odds and ~2.17x miscarriage risk per Nirgianakis 2021 — requiring reproductive-endocrinology input before any treatment decision. **Treatment option 1 — Pelvic MRI for formal staging** · STRONG Both your OB-GYN and REI consultants flagged this as the single missing step before any treatment decision. Wait times in Ontario: 3-6 months via OHIP unless flagged urgent. Citations: kho-2026 · zhao-2024 · nirgianakis-2021 **Treatment option 2 — MR-guided focused ultrasound (HIFU) at Weill Cornell** · STRONG 53.4% pregnancy rate post-treatment, 35.2% live birth, zero uterine ruptures (Chen 2024 meta, n=557). Cross-border self-pay ~C$20-35K all-in. Not OHIP-covered. Citations: chen-2024 · weill-cornell · sunnybrook · profound-medical [... 4 more options, 4 red flags with counterpoints, 2 OHIP centres with phone numbers, 3 active clinical trials, 7 quality-of-life adjuncts, a printable doctor-handoff page ...]
Where the gap lives
Ten dimensions, line by line
The principle
A general-purpose model trained to be helpful about everything is not what you want the night before a medical appointment.
You want the thing that was deliberately narrowed to this condition, with this corpus, read by these specialists, and fact-checked by a verifier that flags any uncited claim. General chatbots are a perfectly fine starting point. This is the tool that actually walks into the room with you.
The “General chat” column above is a composite — it reflects the kind of output typical of an off-the-shelf general-purpose chat assistant when given the same profile, without naming a specific vendor. Quality varies across providers and prompts. The point is the architectural gap between unstructured single-turn chat and corpus-grounded multi-agent reasoning with verification, not any particular brand comparison.