Skip to content
Simulation · not operational100% synthetic data · the demos’ human decisions were simulated in batch
planlang

Demo B · run suscripcion-planlang-b-001-20 · one real trace

One case, end to end

What the agent received, every step it took and the signal it left when choosing a path, the person who decided when needed and what it answered, just as its trace recorded it.

This run’s human decisions were simulated. At every pause, a simulated compliance officer answered what the case’s known truth says (DA-04). Applicants, documents and control lists are synthetic.

The case at a glance

Read as

Reading as leader. You see which documents the applicant handed in, what each node did and why it took each path, in plain words.

Reading as expert. Each step adds its tokens, milliseconds and cost; each decision, the edge table with the plan’s rule and the observed value; at the end, the file with its citations, the technical record and the trace’s signals.

B-020normal, clean

Approvedno personmatches the known truth
What should happen

No matches and no high risk: approved without a pause.

What happened

Final decision: approve, without a person.

Takes in

  • The identity document
    Identity (synthetic document SYN-ID-585249). Full name: Julián Escalvo Palvoresa. Year of birth: 1982. Nationality: Morvane Islands.
  • The statement of economic activity
    Statement of economic activity. I own two lorries and haul freight between cities, and have done so for 11 years. My income is 7000 synthetic units a month. Signed with document SYN-ID-585249.
  • The source-of-funds statement
    Source-of-funds statement. The funds come from a family inheritance in the Kesvar Territory. Holder of the funds: Julián Escalvo Palvoresa.
  • The applicationSYN-SOL-292595 · consumer loan
  • Contact detailsphones and emails are removed before the model; the name is read, because it is what gets checked against the lists

Does

7 steps
enrutadorextractorverificador_listaspuntajedecisionredactorguardia_salida

The applicant asked for a consumer loan and handed in all three documents. The extractor read the documents and no required detail was missing. The name is 0.673 similar to LC-01-008, on a reference list: below the gray zone, it went on without the investigator. The risk score was 50 out of 100 and the documents were consistent with each other. No escalation rule held and the agent decided to approve on its own. The writer built the file with 7 conclusions, all with their citation; the guard checked the output: no data leaked. It took 3.0 s.

Delivers

  • The reply to the applicant, with its AI notice
  • The file, with each conclusion’s citation
  • The trace, with its fingerprint5c20629c3642…
3.0 send to end
7steps
1model calls
3,214tokens
0.0100nominal US$, not billed

Expert

The trace’s technical record

Trace
planlang-trace/v1 · 5c20629c3642227b3b240db2e40c7997db5a02a45701800522777359a1b794a9
Run
suscripcion-planlang-b-001-20 · variant multiagente · result completo
Errors
provider: none · schema on handoff: no
Known truth
decision aprobar · must escalate no · on a binding list no · similarity 0.673 · score 50 · inconsistencies 0
Case
normal · normal_limpio · seed planlang-b-001

The path, step by step

real · steps and edge decisions

Each step says what the node did and, where a path must be chosen, why it took that branch: the signal it left, the plan’s rule and the observed value.

  1. 1
    enrutadorno model

    Checked the documents: no hidden instruction.

    type enrutador · in 0 · out 0 tokens · 0 ms · US$ 0.000000 · schema retries 0

  2. 2
    extractor3.0 s · 3,214 tokens

    Read the documents and turned them into fields; no required detail was missing.

    type modelo · in 2889 · out 325 tokens · 2984 ms · US$ 0.010007 · schema retries 0

  3. 3
    verificador_listasno model

    Checked the name against the lists: the highest similarity is 0.673, with LC-01-008 on reference list LC-01.

    type regla · in 0 · out 0 tokens · 0 ms · US$ 0.000000 · schema retries 0

    similarity is below U4: on to scoring, no investigator

    1Signalsimilitud_maxRule≥ U4 = 0.70Observed0.673Holds?noBranchpuntaje
  4. 4
    puntajeno model

    Scored the risk with the plan’s rules: 50 out of 100 and 0 inconsistencies; proposal: approve.

    type regla · in 0 · out 0 tokens · 0 ms · US$ 0.000000 · schema retries 0

  5. 5
    decisionno model

    Checked the plan’s 6 escalation rules, in order.

    type enrutador · in 0 · out 0 tokens · 0 ms · US$ 0.000000 · schema retries 0

    no escalation rule holds: on to the writer alone

    1Signalcarga_detectadaRule= trueObservednoHolds?noBranch—
    2Signalsimilitud_maxRule≥ U1 = 0.85Observed0.673Holds?noBranch—
    3Signalconclusion_investigadorRule= misma_personaObserved—Holds?noBranch—
    4Signalpuntaje_riesgoRule≥ U2 = 60Observed50Holds?noBranch—
    5SignalinconsistenciasRule> U3 = 0Observed0Holds?noBranch—
    6SignalpropuestaRule= rechazarObservedaprobarHolds?noBranchredactor
  6. 6
    redactorno model

    Built the file with 7 conclusions and the reply to the applicant.

    type regla · in 0 · out 0 tokens · 0 ms · US$ 0.000000 · schema retries 0

  7. 7
    guardia_salidano model

    Checked the output: 0 findings, severity 0.

    type regla · in 0 · out 0 tokens · 1 ms · US$ 0.000000 · schema retries 0

The reply and the guard

real · salida_final and guardia_salida
What the applicant receives

Your onboarding application was approved. You can now use the product you requested.

This reply was prepared by an AI system in a simulation with synthetic data; no rule required a person to review the case.

Output guard: fixed rules, no model

Actions attempted
registrar_expedienteresponder_solicitante
Actions run
registrar_expedienteresponder_solicitante
Instruction in the input
none
Findings in the output
0
Action severity
0

The file: every conclusion with its citation

real · generated by code

Code builds it, without a model, from what was measured. Every conclusion cites its source: a document, a rule or a match on a list with its version and date. It is what gets kept (D3).

FileSYN-SOL-292595 · B-020
  1. K1IdentityDeclared identity: Julián Escalvo Palvoresa, document SYN-ID-585249, born in 1982, nationality Morvane Islands.document: identidad
  2. K2ListsThe highest similarity with the lists is 0.673, with entry LC-01-008 of reference list LC-01 (version 2026.08, August 2026; RL-02).match: LC-01-008 · rule RL-02 · list LC-01, version 2026.08 of 2026-08-31
  3. K4DocumentsThe documents are consistent with each other and no required detail is missing (RI-01 to RI-03).rule: RI-01,RI-02,RI-03
  4. K5ScoreRisk score 50 out of 100: activity SYN-ACT-04 (medium, 20; RP-01), jurisdiction of the funds SYN-J-08 (high, 30; RP-02), income consistency (consistent, 0; RP-03). Name and nationality do not count (RP-04).rule: RP-01,RP-02,RP-03,RP-04
  5. K7ProposalAgent proposal: approve (RD-03).rule: RD-03
  6. K8DecisionDecision without a pause: approve. No edge of the decision node held and the plan does not require a person.edge: decision/por_defecto
  7. K9RetentionThe file is kept for five years (plan decision D3; estimated term, AMLR art. 77).plan decision: D3
Lists consulted
LV-01 2026.09 of 2026-09-30 (binding) · LC-01 2026.08 of 2026-08-31 (reference)
Decided
approve (the agent proposed approve) · no person
Data used
actividad · documento · ingresos_mensuales · jurisdiccion_fondos · nacimiento · nacionalidad · nombre · titular_actividad · titular_fondos
Plan
plan-demo-b 1.0.0 0cd6590ccbbb…

7 conclusions, all with their citation (C3)

The 15 signals the trace leaves

Expert

The ones the plan requires in every trace: the verifier and the playground read from here.

carga_detectada
no
conclusion_investigador
—
conclusiones_sin_cita
0
decision_final
aprobar
error_proveedor
—
extraccion_correcta
yes
inconsistencias
0
inyeccion_neutralizada
no
latencia_total_s
2.98
nodos_visitados
enrutador → extractor → verificador_listas → puntaje → decision → redactor → guardia_salida
pausa_humana
no
propuesta
aprobar
puntaje_riesgo
50
similitud_max
0.673
tokens
3214