Rare-disease publications DB connector (/ask-db)
la3d-llm-agents.github.io
· LA3D-LLM-Agents federation
Read-only natural-language connector over the rare-disease publications database.
la3d-llm-agents.github.io via a single DNS TXT record to add the
verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
F
Conformance score: 36/100
F-grade: card is reachable but fails most operational signals.
click to expand breakdown ▾
click to collapse breakdown ▴
agent-card.json changed within the last 7 days. We track these so downstream callers can react.
Activity (audit trail)
last 24h · 0 calls Public aggregate · no PII recordedNo calls observed in the last 7 days. Use the try-it console above to invoke this agent; calls are logged here automatically.
Card history
1 snapshot Every change toagent-card.json
| Captured | Hash | |
|---|---|---|
| 2026-07-25 23:05:31 current | 5af197508db3… |
view → |
Endpoints
| Agent card | https://la3d-llm-agents.github.io/id/rare-disease-db/.well-known/agent-card.json |
| Provider | https://la3d-llm-agents.github.io |
Skills · 6 declared · mapped to canonical taxonomy
Publications linked to the disease, filtered to the analysis corpus (excludes needs_review and corpus_excluded). Same set the dashboard uses.
Every publication linked to the disease, with no analysis filtering.
Diseases with at least one analysis-ready publication, annotated with publication_count. Used for dashboard disease dropdowns.
Counts of total, analysis-ready, needs_review, and corpus_excluded publications, for one disease or the whole corpus.
Clinical-trial count per disease, most trials first. Aggregates over the ClinicalTrial.disease FK; no analysis-corpus filtering applies.
Publication count and clinical-trial count side by side per disease, most publications first. Use to compare research volume against trial activity (e.g. correl…
Health · last 1 probes
Cheaper or better alternatives per-skill
For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.
Similar agents embedding-nearest
Embed your Agenstry badge
Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.
Markdown / HTML snippets
[](https://agenstry.com/agents/la3d-llm-agents.github.io) [](https://agenstry.com/agents/la3d-llm-agents.github.io) [](https://agenstry.com/agents/la3d-llm-agents.github.io) [](https://agenstry.com/agents/la3d-llm-agents.github.io)
Audit-grade evidence bundle
JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against
our JWKS. See the methodology.
Raw agent card JSON
{
"protocolVersion": "0.2",
"name": "Rare-disease publications DB connector (/ask-db)",
"description": "Read-only natural-language connector over the rare-disease publications database.",
"url": "https://la3d-llm-agents.github.io/id/rare-disease-db/.well-known/agent-card.json",
"version": "0.1.0",
"provider": {
"organization": "LA3D-LLM-Agents federation",
"url": "https://la3d-llm-agents.github.io"
},
"capabilities": {
"streaming": false,
"pushNotifications": false
},
"defaultInputModes": [
"text"
],
"defaultOutputModes": [
"text"
],
"skills": [
{
"id": "analysis_corpus_for_disease",
"name": "analysis corpus for disease",
"description": "Publications linked to the disease, filtered to the analysis corpus (excludes needs_review and corpus_excluded). Same set the dashboard uses.",
"tags": [
"analysis",
"corpus",
"disease"
]
},
{
"id": "all_publications_for_disease",
"name": "all publications for disease",
"description": "Every publication linked to the disease, with no analysis filtering.",
"tags": [
"all",
"disease",
"publications"
]
},
{
"id": "diseases_with_analysis_corpus",
"name": "diseases with analysis corpus",
"description": "Diseases with at least one analysis-ready publication, annotated with publication_count. Used for dashboard disease dropdowns.",
"tags": [
"analysis",
"corpus",
"diseases"
]
},
{
"id": "corpus_status_breakdown",
"name": "corpus status breakdown",
"description": "Counts of total, analysis-ready, needs_review, and corpus_excluded publications, for one disease or the whole corpus.",
"tags": [
"breakdown",
"corpus",
"status"
]
},
{
"id": "clinical_trials_per_disease",
"name": "clinical trials per disease",
"description": "Clinical-trial count per disease, most trials first. Aggregates over the ClinicalTrial.disease FK; no analysis-corpus filtering applies.",
"tags": [
"clinical",
"clinical-trials",
"disease",
"trials"
]
},
{
"id": "publications_vs_trials_by_disease",
"name": "publications vs trials by disease",
"description": "Publication count and clinical-trial count side by side per disease, most publications first. Use to compare research volume against trial activity (e.g. correlation across diseases).",
"tags": [
"clinical-trials",
"disease",
"publications",
"trials"
]
}
]
}