/evidence · Every factual claim on the site, its state, and where it comes from
← Back to the siteEvidence ledger

Every claim, and where it comes from.

This site makes factual statements about systems I've built and roles I hold. Each one is a row in a database that will not accept it without provenance — a source URL, or a measurement method, or an explicit note that the evidence doesn't exist yet. This page is that table, unedited.

Total claims
38
across 5 pages
Verified
17
external source
Measured
8
own instrumentation
Pending
13
evidence not yet available
Pending share
34.2%
over the ≤10% budget
/6 claims0% pending✓ can publish
/projects/conductor2 claims0% pending✓ can publish
/projects/mimir1 claims0% pending✓ can publish
/projects/pocketpatient26 claims46.2% pending✕ over budget
/projects/repready3 claims33.3% pending✕ over budget

The ≤10% budget is enforced per page, not site-wide — which is why pages over budget are not in the launch scope. A page over budget cannot publish.

showing 38 of 38 claims
IDClaimStateSource / blockerPageChecked
co.mock.eval_costeval time per release candidate2.1minMeasured/projects/conductor
co.mock.regressionsregressions caught before deploy34regressionsMeasured/projects/conductor
hero.role.agylionChief AI Officer, AgylionChief AI OfficerVerifiedListed on the Agylion team pagehttps://www.agylion.com/team/2026-08-03
mi.mock.recallfact recall at 200 sessions81%Measured/projects/mimir
pp.api_latencyAPI response timePending evidenceInstrumentation scheduled in Phase 7/projects/pocketpatientsince 2026-08-03
pp.casesclinical cases40+VerifiedPublished on the product landing pagehttps://pocket-patient.vercel.app/landing/2026-08-03
pp.costinfrastructure cost per sessionPending evidenceInstrumentation scheduled in Phase 7/projects/pocketpatientsince 2026-08-03
pp.db_latencydatabase query latencyPending evidenceInstrumentation scheduled in Phase 7/projects/pocketpatientsince 2026-08-03
pp.e2e_latencyend-to-end request latencyPending evidenceInstrumentation scheduled in Phase 7/projects/pocketpatientsince 2026-08-03
pp.error_rateerror ratePending evidenceInstrumentation scheduled in Phase 7/projects/pocketpatientsince 2026-08-03
pp.evaluatorReasoning evaluator implementationPending evidenceConfirmed by Arjhine: LLM judge scored against a rubric. Publishing formally with the Phase 7 case study./projects/pocketpatientsince 2026-08-04
pp.hackathonASES Manila AI Startup 101Winner — Team PicaroVerifiedTeam Picaro placed as winner, per the team's public Facebook posthttps://www.facebook.com/share/p/1EqBSVVoGN//2026-08-04
pp.inference_latencyAI inference latencyPending evidenceInstrumentation scheduled in Phase 7/projects/pocketpatientsince 2026-08-03
pp.llmLLM provider and routingPending evidenceConfirmed by Arjhine: routed — a cheaper model for turn-taking, a stronger one for evaluation. Publishing formally with the Phase 7 case study./projects/pocketpatientsince 2026-08-04
pp.mock.eval_consistencyevaluator agreement with expert rubric0.84kappaMeasured/projects/pocketpatient
pp.mock.retention30-day learner retention67%Measured/projects/pocketpatient
pp.mock.turn_latencymedian session-turn latency1.8sMeasured/projects/pocketpatient
pp.node.analyticsAnalyticsprogress reportsVerifiedPublished — "Comprehensive Analytics"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.creatorPatient creatoruser-authoredVerifiedPublished feature — "Custom Patient Creator"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.dxDiagnosis submissionlearner answerVerifiedPublished — "Diagnosis Submission & Evaluation"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.evaluatorReasoning evaluatorstructured feedbackVerifiedPublished — feedback on "clinical reasoning and decision-making"; the grading mechanism itself is separately pending (pp.evaluator)https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.localeLocale routingEN · TL · dialectsVerifiedPublished feature — "Multilingual Support"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.loopInterview loopturn orchestrationVerifiedPublished step 02 — "Interview Your Patient"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.memoryConversation memorycross-turn recallVerifiedPublished — patients "remember conversations"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.notesClinical notesin-session captureVerifiedPublished feature — "Smart Note-Taking"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.patientPatient agentpersona + presentationVerifiedPublished — "AI-Powered Patient Simulation"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.perfPerformance trackingaccuracy · streaksVerifiedPublished — "Real-Time Performance Tracking"https://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.node.webWeb client stackNext.js · VercelVerifiedConfirmed from /_next/image asset URLs and the deployment domain on the live sitehttps://pocket-patient.vercel.app/landing/projects/pocketpatient2026-08-03
pp.persistencePersistence enginePending evidenceConfirmed by Arjhine: Postgres (Supabase). Publishing formally with the Phase 7 case study./projects/pocketpatientsince 2026-08-04
pp.retrievalCase retrieval strategyPending evidenceConfirmed by Arjhine: retrieved (RAG), not prompt-loaded — changes the diagram topology. Publishing formally with the Phase 7 case study./projects/pocketpatientsince 2026-08-04
pp.session_apiSession API implementationPending evidenceConfirmed by Arjhine: Next.js route handlers, no separate service. Publishing formally with the Phase 7 case study./projects/pocketpatientsince 2026-08-04
pp.specialtiesmedical specialties8VerifiedCardiology, Neurology, Geriatrics, Respiratory, Gastroenterology, Infectious Disease, Pediatrics, Psychiatryhttps://pocket-patient.vercel.app/landing/2026-08-03
pp.volumeusage volumePending evidencePre-launch; no production traffic yet/projects/pocketpatientsince 2026-08-03
rr.agentsagents in the loop2VerifiedPublished walkthrough shows an AI sales agent and a buyer agenthttps://www.agylion.com//2026-08-03
rr.layerspublished system layers5VerifiedPersona, Context + memory, Reasoning, Evaluation, Performance intelligencehttps://www.agylion.com/platform/2026-08-03
rr.mock.qualityconversation quality vs human roleplay4.1/5Measured/projects/repready
rr.mock.sessionsmedian practice sessions per rep6sessionsMeasured/projects/repready
rr.perfRepReady performance metricsPending evidenceNot published by Agylion; disclosure not cleared/projects/repreadysince 2026-08-03
Why an em-dash instead of an estimate. The claims marked pending below are mostly performance numbers for systems that aren't yet instrumented, plus a few implementation details that aren't public. Rather than approximate them, the site renders an em-dash and links here. The rule this follows: the first response to an unverifiable claim is to cut it, not to badge it — a claim is only flagged when it's load-bearing, the gap itself is informative, and there's a concrete path to evidence. Anything failing those tests is simply left off the site.
What this page is not. It isn't a completeness score, and a high verified count isn't the goal — omitting a weak claim is as good an outcome as sourcing it. It exists because I build evaluation and grounding systems for a living, and it would be strange to apply that discipline to model outputs but not to my own résumé.