Una implementación de cliente completa y claramente sintética para cuentas por cobrar de ERP: incorporación de fuentes, datos canónicos, aplicación de pagos, deducciones, cobros, controles, benchmarking de KPI, acceso MCP, revisión de excepciones multiagente, observabilidad, UAT, migración e hipercuidado.
Todos los archivos de estilo SAP S/4HANA, Oracle Fusion y NetSuite en este repositorio son simulaciones generadas. No son exportaciones reales ni integraciones en vivo. El movimiento de KPI es un benchmark de implementación controlada sobre datos sintéticos, no un impacto en el cliente.
El workbench comienza con la configuración del cliente y tres formatos de origen incompatibles, no con una tabla analítica limpia. Aplica puertas de validación, conserva los remanentes de pago, enruta excepciones, prioriza cobros, muestra objetivos no cumplidos y produce los artefactos que un equipo de implementación utilizaría desde el descubrimiento hasta la puesta en marcha.
La arquitectura mantiene deliberadamente la conciliación financiera determinista y auditable. Los agentes manejan trabajo con alto grado de juicio: investigación de excepciones, diagnóstico de calidad de datos, planificación de cobros y monitoreo posterior a la puesta en marcha. No pueden contabilizar en un ERP, emitir un reembolso, cancelar deuda ni modificar datos maestros.
flowchart LR
A["Three simulated ERP export sets"] --> B["Configuration-driven adapters"]
B --> C["Seven canonical receivables tables"]
C --> D["Validation control gate"]
D --> E["Deterministic cash matching"]
E --> F["Exception and collections queues"]
F --> G["MCP evidence tools"]
G --> H["Supervisor agent"]
H --> I["Cash Application Agent"]
H --> J["Data Quality Agent"]
H --> K["Collections Agent"]
I --> L["Human approval gate"]
J --> L
K --> L
E --> M["Controlled KPI benchmark"]
M --> N["Go Live Monitor Agent"]
O["OpenTelemetry traces"] -.-> B
O -.-> E
O -.-> H
O -.-> NRelated MCP server: finance-engines-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
o2c-workbench --project-root .
streamlit run app.pyLa ejecución reproducible seed-42 crea 1,908 registros canónicos, detecta 18 transacciones bancarias duplicadas intencionales como advertencias y deja cero errores de validación. Abra el panel estático o use la aplicación Streamlit.
El servidor utiliza el MCP Python SDK actual y expone herramientas, recursos y prompts estructurados. Los clientes locales deben usar stdio; los clientes desplegados pueden usar Streamable HTTP.
o2c-mcp --transport stdio
o2c-mcp --transport streamable-http --port 8000Herramientas: get_implementation_summary, investigate_payment, get_collection_priority y run_controlled_benchmark. Recursos: o2c://configuration, o2c://benchmark y o2c://observability.
La ruta predeterminada es offline y determinista, de modo que un revisor pueda reproducir los traspasos y los controles sin cuenta ni clave de API. Produce output/agent_decisions.csv, output/agent_control_summary.json y spans de OpenTelemetry.
Una revisión opcional respaldada por modelos usa el OpenAI Agents SDK con traspasos de especialistas y salida estructurada:
pip install -e ".[ai]"
export OPENAI_API_KEY="..."
o2c-agent-review SAP-P001-09 --project-root .La ruta de modelos no es necesaria intencionalmente para los KPI del benchmark. Puede recomendar, pero no puede ejecutar acciones financieras controladas.
config/ — configuración de implementación, mapeos, tolerancias, ponderaciones, rutas, controles, objetivos de KPI, límites de agentes.
data/raw/ — exportaciones simuladas de ERP generadas y etiquetadas visiblemente.
data/canonical/ — clientes normalizados, facturas, pagos, remesas, deducciones, promesas y actividades.
src/o2c_workbench/ — adaptadores, conciliación, cobros, controles, agentes, MCP, observabilidad, lógica de KPI.
output/ — evidencia del benchmark, colas, trazas y paneles.
docs/ — diseños de procesos, mapeo, controles, RTM, 28 casos UAT, migración, monitoreo, capacitación y base de investigación.
deliverables/ — libro de trabajo de implementación.
demo/ — recorrido de implementación narrado de cinco minutos y guion.
KPI | Estado actual | Estado futuro configurado | Variación |
Tasa de conciliación automática | 10.0% | 80.7% | +70.7 pp |
Tasa de revisión manual | 90.3% | 21.9% | -68.5 pp |
Efectivo no aplicado | $2,192,667 | $550,209 | -$1,642,459 |
DSO | 115.9 días | 51.6 días | -64.3 días |
CEI | 8.7% | 75.7% | +67.0 pp |
Cuentas por cobrar vencidas | 69.5% | 44.9% | -24.6 pp |
Tiempo de procesamiento | 67.7 horas | 13.0 horas | -54.7 horas |
Cuatro objetivos ambiciosos siguen sin cumplirse, por lo que el monitor recomienda una luz verde condicional, no una celebración. Eso es realismo intencional de implementación: proceder solo con controles de aprobación humana e hipercuidado centrado en el efectivo no aplicado y los sobrepagos residuales.
pytest -qConsulte la base de investigación para conocer las fuentes primarias que fundamentaron los casos de pago, la elección del transporte MCP, los traspasos de agentes y las convenciones de telemetría.
Return the configured collection score evidence for one synthetic invoice.
| Name | Required | Description | Default |
|---|---|---|---|
| invoice_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates it returns read-only evidence, so side effects are not impliedasi. No annotations are present, but as a getter, the behavior is somewhat inferable. It does not specify errors, auth, or configuration dependencies.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single precise sentence with no filler. It conveys the operation, target, and scope efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a simple getter and the output schema exists, but it lacks usage guidance, alternatives, and explanation of what 'configured collection score evidence' actually contains.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Even though the parameter schema is only a raw string, the description ties the operation to 'one synthetic invoice', which effectively identifies the invoice_id parameter and explains its scope.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the operation ('Return'), the resource ('configured collection score evidence'), and the scope ('for one synthetic invoice'). This distinguishes it from the sibling tools, which target implementation summaries and payment investigation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'for one synthetic invoice' gives a clear invocation context. However, it does not explicitly describe when to choose this tool over the sibling tools or mention any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return controlled benchmark KPIs, data-quality status, disclaimers, and agent readiness.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the behavioral burden. It states that the tool returns a summary, implying a read-only operation, and lists the types of content returned. However, it does not disclose prerequisites (e.g., whether a benchmark must already exist), data freshness, or any side effects, which leaves some ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence conveys the tool's purpose with no filler. Every phrase earns its place by naming a distinct output category.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there are no parameters and an output schema exists, the description is largely complete. It lists the key output categories and indicates the tool's role as a summary provider. It could be slightly stronger by explicitly linking it to run_controlled_benchmark, but that is not essential for calling it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so schema coverage is trivially 100%. The description correctly avoids inventing parameter semantics and instead focuses on what the output contains, which is appropriate for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Return') and identifies a precise set of resources: controlled benchmark KPIs, data-quality status, disclaimers, and agent readiness. This clearly differentiates it from siblings like run_controlled_benchmark, which is the execution counterpart rather than the summary retrieval tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to call this tool versus its siblings. There is no explicit statement such as 'use after running a controlled benchmark' or 'use instead of investigate_payment'; the intended usage must be inferred from the name and resource list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return matching evidence and exception routing for one synthetic payment.
| Name | Required | Description | Default |
|---|---|---|---|
| payment_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It says the tool returns evidence and exception routing, but it does not disclose whether this is a read-only operation, whether it requires special permissions, or what side effects (if any) exist. The presence of an output schema mitigates some ambiguity, but the description alone is thin.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It is appropriately sized for a simple one-parameter tool, though it could have added a brief usage note without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has one parameter and an output schema, so the description does not need to explain return values. However, it lacks any context about when to use this tool, what 'exception routing' means, or how it relates to the sibling tools. For a tool with no annotations, this is a moderate gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It names the single parameter implicitly ('one synthetic payment' maps to payment_id) but does not explain the expected format, constraints, or how the parameter affects the result. With only one parameter, the gap is small, but the description adds minimal semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Return') and resource ('matching evidence and exception routing for one synthetic payment'), which clearly identifies the tool's function. It does not explicitly distinguish it from siblings, but the resource is specific enough that an agent can infer its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get_implementation_summary or run_controlled_benchmark. The description implies it is for investigating a single synthetic payment, but it does not state exclusions or conditions that would route an agent to a sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Regenerate synthetic source exports and controlled benchmark outputs; never connects to a genuine ERP.
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses a key behavioral trait: it never connects to a genuine ERP, which is valuable context beyond the schema. However, with no annotations provided, the description carries the full burden and doesn't disclose other behaviors like whether it overwrites existing outputs, how long it takes, or what the output schema contains.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded with the action and resource, and the critical safety qualifier ('never connects to a genuine ERP') is included. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one optional parameter and an output schema, the description is mostly adequate. However, it doesn't explain what 'controlled benchmark outputs' means in practice, what the output schema contains, or any side effects (e.g., overwriting files). The sibling tools suggest this is part of a larger workflow, but the description doesn't position it within that workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It mentions 'seed' implicitly through 'regenerate' (deterministic regeneration), but doesn't explain the seed parameter's role or how it affects outputs. The single parameter is simple, so the gap is minor, but the description adds no explicit parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('regenerate') and resource ('synthetic source exports and controlled benchmark outputs'), and distinguishes itself from a genuine ERP connection. It is clear what the tool does, though it doesn't explicitly name sibling tools for differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool is for synthetic/controlled benchmark scenarios and explicitly notes it never connects to a genuine ERP, which suggests when it should be used. However, it doesn't explicitly state when to use it versus alternatives like get_implementation_summary or investigate_payment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_collection_priorityget_implementation_summaryinvestigate_paymentrun_controlled_benchmarkScored across 4 tools
Each tool targets a clearly distinct function: summary/KPIs, payment investigation, collection priority, and benchmark regeneration. There is no meaningful overlap or ambiguity between them.
All names use lowercase snake_case and follow a verb_object pattern, but the verb set is mixed (get, investigate, run). This is still predictable and readable, with only minor stylistic variance.
Four tools is a tight, well-scoped surface for a synthetic O2C benchmark workbench. Each tool serves a distinct purpose without unnecessary bloat or missing core functionality.
The tool set covers the main workflows: viewing benchmark status, investigating a payment, checking collection priority, and regenerating outputs. A minor gap is the lack of explicit discovery tools for available synthetic payment or invoice identifiers, but this may be addressed through the summary.
Governed retail, FMCG, and CPG operational tools: runs, cases, approvals, audit-ready execution.
Tesorio's order-to-cash tools — query customers, invoices, receivables, payments, and more.
Quote-to-cash tools: parse invoices and POs, match POs to invoices, collection emails, billing math.
Paid deterministic data-quality and execution-verification tools for AI agents.
