Conector de Bruknow para Claude

Última actualización: 19 de octubre de 2026

El conector permite que Claude trabaje con tu espacio de trabajo de Bruknow. Pídele en lenguaje natural que revise un flujo y arregle lo que esté roto, que averigüe por qué un bot no le responde a un cliente, o que abra un ticket con nuestro equipo de soporte cuando no pueda resolver algo por sí mismo.

También puedes conectarlo desde ChatGPT o Gemini. Esta página usa Claude en sus ejemplos; todo lo que describe funciona igual desde ChatGPT y Gemini.

1. Qué necesitas

Una cuenta de Bruknow. El conector está incluido en todos los planes.
Una cuenta de Claude. El uso de Claude lo cobra Anthropic según tu propio plan de Claude; Bruknow no cobra por el conector.
En los planes Team y Enterprise de Claude, un Owner de la organización de Claude agrega primero el conector; después cada miembro se conecta con su propia cuenta de Bruknow.
Para conectar desde ChatGPT, un plan de pago de ChatGPT. El uso de ChatGPT lo factura OpenAI según tu propio plan.
Para conectar desde Gemini, una cuenta de Google que pueda usar Gemini en la web. El uso de Gemini se rige por tu propio acuerdo con Google.

2. Cómo conectar

Desde Claude

En Claude, abre Configuración y luego Conectores.
Elige Bruknow en el directorio. Si no te aparece, elige Add custom connector y pega esta dirección: https://bruknow.com/mcp
Claude te envía a Bruknow para iniciar sesión.
Revisa el espacio de trabajo que aparece en la pantalla de aprobación. Si perteneces a más de un espacio de trabajo, el conector funciona con el que se muestra ahí.
Elige qué puede hacer Claude: ver tu espacio de trabajo y, si quieres que edite flujos y abra tickets, hacer cambios. Luego aprueba.

Desde ChatGPT

ChatGPT se conecta a Bruknow como un servidor MCP personalizado, que requiere un plan de pago de ChatGPT. En los planes Business y Enterprise, es posible que un administrador del espacio de trabajo de ChatGPT tenga que permitir primero los servidores MCP personalizados.

En ChatGPT, abre Plugins, elige Agregar y luego Agregar servidor MCP personalizado.
Ponle el nombre Bruknow, deja OAuth como autenticación y pega esta dirección en Conexión: https://bruknow.com/mcp
Marca Entiendo y quiero continuar, y luego elige Crear como plugin.
ChatGPT te envía a Bruknow para iniciar sesión. Revisa el espacio de trabajo, elige qué puede hacer ChatGPT y aprueba.

Desde Gemini

Los conectores personalizados se agregan desde Gemini en la web, no desde la app del teléfono.

En gemini.google.com, abre Personalizar y luego Conectores.
Elige Personalizado, pega esta dirección como URL del servidor MCP y elige Siguiente: https://bruknow.com/mcp
Gemini te envía a Bruknow para iniciar sesión. Revisa el espacio de trabajo, elige qué puede hacer Gemini y aprueba.

Claude, ChatGPT y Gemini nunca pueden hacer más de lo que tú puedes: cada solicitud se verifica contra tu rol en el espacio de trabajo en el momento en que se hace.

3. Qué puede hacer Claude

Entender tus flujos

Listar tus flujos y mostrar cómo está armado uno: sus pasos, qué lleva de uno al siguiente y la configuración completa de cualquier paso.
Ejecutar la revisión integrada de Bruknow e informar saltos rotos, callejones sin salida, pasos inalcanzables, variables sin definir y archivos multimedia faltantes.
Mostrar en qué punto los clientes reales abandonan un flujo y cuándo se publicó cada versión.

Crear y arreglar flujos

Crear un flujo, agregar, cambiar y quitar pasos y las conexiones entre ellos, y cambiar la configuración general y las variables del flujo.
Crear un archivo nuevo de Google Sheets o Excel, con las columnas que elijas, en la cuenta de Google o Microsoft que conectaste a Bruknow, para que un flujo registre ahí cada cita, prospecto o pedido. El archivo queda en tu Drive o OneDrive.
Probar un flujo manteniendo una conversación con él.
Publicar un flujo cuando se lo pidas.

Ajustar tus asistentes de IA

Leer las instrucciones, las reglas y el playbook de conversación de un asistente, y cambiarlos.
Publicar un asistente cuando se lo pidas, en todos los flujos que lo usan, y volver a una versión anterior si un cambio no funcionó.

Trabajar con tu CRM

Buscar un contacto y leer sus datos, notas, negocios y actividad reciente.
Resumir un pipeline etapa por etapa y listar los negocios abiertos, ganados, perdidos o estancados.
Agregar un comentario a un negocio y mover un negocio a otra etapa cuando se lo pidas. Mover un negocio ejecuta las automatizaciones de esa etapa, igual que en el tablero.
Listar tus formularios web y leer, filtrar y resumir lo que respondieron las personas.

Resolver dudas de soporte

Explicar por qué un bot no responde: suscripción, cuotas, un canal desconectado o en pausa, un canal sin flujo publicado o un cliente pausado por un operador.
Revisar la conversación de un cliente: dónde se detuvo, el camino que siguió y qué la está frenando.
Leer y resumir una conversación, buscar una palabra o frase en las conversaciones recientes y listar a los clientes que escribieron y siguen esperando respuesta.
Listar los mensajes que no se pudieron entregar y qué significa el error del proveedor.
Mostrar tu plan, tu consumo frente a sus límites, tus canales y tus plantillas de WhatsApp con su estado de aprobación.

Empezar desde cero

Configurar contigo un primer bot: elegir una plantilla inicial, crear el asistente y su flujo a partir de lo que le cuentes a Claude sobre tu negocio, probarlo, publicarlo cuando lo indiques y mostrarte dónde se conecta un canal. En Claude, elige el prompt “Set up my business” del conector de bruknow, o simplemente pídelo.

Escribir plantillas de WhatsApp

Leer una plantilla completa, incluido el motivo por el que WhatsApp la rechazó.
Escribir una plantilla nueva como borrador para que la revises: encabezado, cuerpo, pie y botones, con un ejemplo para cada variable.
Enviar un borrador a WhatsApp para su aprobación cuando lo pidas. Solo el propietario del espacio de trabajo puede hacerlo, un envío no se puede deshacer y Claude nunca cambia ni reemplaza una plantilla que ya está aprobada, pendiente o rechazada.

Enviar campañas de WhatsApp

Mostrar tus campañas y sus resultados: entregados, leídos, respondidos y fallidos, con lo que significa cada fallo.
Preparar una campaña contigo: una plantilla aprobada enviada a los contactos que tienen las etiquetas que elijas. Claude primero muestra a cuántas personas llega, quiénes quedan fuera, la programación y lo que consume de tu plan, y no envía nada.
Crear la campaña solo después de que apruebes esa vista previa. Nunca empieza antes de 15 minutos después de crearla, así que todavía puedes cancelarla; Claude también puede pausar, reanudar o cancelar una campaña cuando lo pidas.

Trabajar con tu calendario

Mostrar lo que hay en tu calendario y cuándo estás libre, incluidas tus reservas y los horarios ocupados de tu calendario de Google u Outlook conectado.
Listar tus tipos de reunión con sus enlaces de reserva y los horarios que siguen disponibles en cada uno.
Agendar una reunión y cancelarla cuando lo pidas. Tu calendario conectado invita a los asistentes, y cada miembro del equipo trabaja solo con su propio calendario.

Responder preguntas sobre tus números

Informar cómo le va a tu equipo de soporte: chats respondidos, resueltos y abandonados, cuánto esperan los clientes, calificaciones y sentimiento, comparados por agente, cola, departamento o canal.
Resumir los resultados de una encuesta de satisfacción: el puntaje, la tendencia, cada pregunta y lo que escribieron los clientes.
Mostrar los pulgares arriba y abajo y las calificaciones de fin de chat que los clientes dejaron en tu chat web, y qué respuestas no les gustaron.

Contactar a nuestro equipo

Mostrar tus tickets de soporte y lo que respondió nuestro equipo, abrir un ticket nuevo y responder uno.

4. Qué puedes pedirle

Ayúdame a configurar mi negocio. Tengo una panadería que recibe pedidos por WhatsApp.

Revisa mi flujo de Ventas y dime qué está roto. Después arréglalo, pero no lo publiques.

Un cliente nos escribió ayer por WhatsApp desde el +57 300 111 2233 y el bot nunca respondió. ¿Por qué?

Agrega a mi flujo de Pedidos un paso que pregunte la ciudad del cliente antes de dar el precio, pruébalo y muéstrame la conversación.

¿Cuáles de mis plantillas de WhatsApp fueron rechazadas y por qué?

Escribe una plantilla de WhatsApp que le avise a un cliente que su pedido está listo, con un botón para confirmar la recogida. Muéstramela antes de enviarla.

¿En qué punto abandonan los clientes mi flujo de Reservas?

¿Quién lleva más de una hora esperando respuesta y qué preguntó cada uno?

¿Qué negocios llevan más tiempo en Propuesta enviada y qué fue lo último que le dijimos a cada uno?

¿Cómo le fue a mi equipo de soporte esta semana en comparación con lo que dijeron los clientes en la encuesta de satisfacción?

¿Qué pidieron las personas en mi formulario de Contacto este mes? Agrupa las respuestas y dame una tabla.

¿A cuántas personas llegaría mi plantilla Promo si la envío a todos los que tienen la etiqueta VIP? No envíes nada todavía.

¿Qué tengo el jueves? Búscame media hora libre en la tarde y agenda una llamada con [email protected].

5. Cómo se protegen tus flujos

Los cambios van al borrador. Tus clientes siguen recibiendo la versión publicada de un flujo o de un asistente hasta que se publique. Claude solo publica cuando tú lo pides.
Todo o nada. Un conjunto de cambios se revisa primero; si uno de ellos no es válido, no se guarda ninguno.
Sin sobrescribir tu trabajo. Si alguien cambió el flujo en el constructor después de que Claude lo leyó, el cambio de Claude se rechaza y Claude vuelve a leer el flujo.
Las pruebas no llegan a tus clientes. De forma predeterminada, una prueba se detiene antes de cualquier paso que envíe un mensaje, llame a otro sistema, escriba en tu CRM o agende un evento en el calendario, y te dice dónde se detuvo. Esos pasos solo se ejecutan si tú estás de acuerdo.
Las pruebas con IA no tienen costo para ti. Una prueba en la que responden tus pasos de IA usa una cuota diaria que paga Bruknow. Nunca se cobra a tu plan. Cuando se agota la cuota del día, Claude te avisa; contacta a nuestro equipo si necesitas más.
Las credenciales se quedan en Bruknow. Las claves de API, los tokens y las contraseñas guardados en tus flujos y canales nunca se envían a Claude.
Todo queda registrado. Cada cambio hecho a través del conector aparece en tu registro de actividad.

6. Cómo desconectar

En Bruknow, abre el menú bajo tu nombre y elige Aplicaciones conectadas, luego Desconectar. La aplicación pierde el acceso de inmediato. También puedes quitar el conector en Claude, ChatGPT o Gemini.

7. Si algo no funciona

Claude te pide iniciar sesión de nuevo. La conexión venció tras 90 días sin uso, fue desconectada o ya no perteneces a ese espacio de trabajo. Vuelve a conectar.
Tu rol no incluye esto. Pídele al propietario del espacio de trabajo que cambie tu acceso en la página Equipo.
A esta conexión no se le dio permiso para hacer cambios. Quita el conector en Claude y agrégalo de nuevo, dejando marcada la opción de hacer cambios en la pantalla de aprobación.
El flujo cambió desde que se leyó. Alguien lo guardó en el constructor. Pídele a Claude que lea el flujo de nuevo y repita el cambio.
Las pruebas con IA de hoy se agotaron. Las pruebas sin IA siguen funcionando y la cuota vuelve al día siguiente. Escríbele a nuestro equipo si necesitas más hoy.
El plan no lo permite. Los límites de tu plan aplican aquí igual que en Bruknow: la cantidad de bots, la cantidad de pasos de un flujo y los tipos de paso.

8. Referencia de herramientas

Estas son las herramientas que ve Claude, tal como el conector se las describe. Las herramientas marcadas como que cambian algo siempre te piden confirmación en Claude.

Herramienta		Qué hace
`bruknow_ping`	lee	Checks that the Bruknow connector is reachable and returns the connected workspace and the server time. Use it only to confirm the connection works.
`compare_ad`	lee	Compares one ad with its peers (the other ads in its ad set, campaign or the whole account) metric by metric: the ad's value, the peers' median, the percentage difference and its rank, for hook rate, hold rate, CTR, CPM, cost per result and cost per customer; plus the optimiser's own verdict (cost per outcome vs the benchmark). Says when the sample is too small. Always name the scope when you answer.
`compare_contacts`	lee	Compares two contacts that may be the same person. Returns which one to keep (the one with more history), the fields where they DISAGREE (conflicts — the user must choose each value before merging), the fields only the other one has (copied over automatically), and what moves with the merge (chats, deals, tasks, notes). Call this before merge_contacts.
`diagnose_ad`	lee	Reads an ad's numbers as a diagnosis: where viewers leave (after 3 seconds, before the end), which part of the creative that points at (opening frame, body, offer), fatigue (frequency up, CTR down from its peak), whether the ad set is still learning, Meta's rankings, and the account-wide findings that mention it. Use it for 'why isn't this working', 'did people not like it'.
`diagnose_channel`	lee	Checks one connected messaging account in depth: whether it is connected, when it last received and last sent a message (a long gap in received messages on a busy account usually means the provider's webhook stopped reaching Bruknow), how many sends failed in the last 24 hours, and the state of each channel on it. Use it after list_channels, with the account's id, when one account misbehaves.
`diagnose_conversation`	lee	Explains the state of one customer conversation: the node it is parked at, the path it took through the flow, the variables captured, the last messages, any message that failed, pending no-reply timers, and everything pausing or blocking the bot for it, each with its fix. Use it when asked why the bot did not answer a specific customer or why it answered the way it did. Get the id from find_conversations.
`explain_bot_silence`	lee	Runs the full checklist of what can stop a Bruknow bot from answering and returns each thing found with its fix: subscription not active, a monthly quota used up, a channel account disconnected or switched off, the bot paused on a channel or flow, a channel with no flow or an unpublished flow. With `contact` and `channel` it also checks that one customer: paused by an operator, opted out, and their latest conversation. Use it first whenever the complaint is that the bot is silent.
`find_conversations`	lee	Lists recent real customer conversations in the workspace, newest activity first, optionally only one channel or one contact (a phone number or part of one, a Telegram chat id, or text from the conversation title). Use it to get the conversation id that diagnose_conversation needs. Test conversations are not included.
`get_account_overview`	lee	Returns the connected workspace's Bruknow plan, subscription status, renewal date, included support tier, and how many bots, agents, contacts, WhatsApp numbers and team seats are in use against the plan's limits. Use it for questions about the plan, billing status, or whether a limit is blocking something.
`get_ad_breakdowns`	lee	Meta's breakdowns summed over the account: by placement, by age and gender, or by hour, each slice with spend, impressions, clicks, results, share and cost per result, the best and worst slices named, and wasteful slices flagged (spending a lot with no results).
`get_ad_funnel`	lee	The funnel only Bruknow sees, per ad or campaign for a period: arrivals → contacts → replied → qualified → deals → won, with cost per arrival, per qualified lead and per customer, revenue per currency and return on spend. Lead with this, not clicks: a cheap click that never replies is not a win.
`get_ad_performance`	lee	One ad in full for a period: spend, impressions, reach, CTR, CPM, link clicks, 3-second plays, hook rate, hold rate, average seconds watched and % of length, results and cost per result, arrivals, replied, qualified, deals, won, cost per customer, Meta's quality / engagement / conversion rankings, and whether the sample is big enough.
`get_ads_digest`	lee	The latest morning digest of the ads (what happened, what to do), in the user's language.
`get_agent_leaderboard`	lee	Ranks team members by one metric (won_value, won_count, win_rate, pipeline_value, activities, chats, csat, first_response) for a period against the team median. Members with too few closed deals or chats are flagged low_sample rather than hidden.
`get_agent_sales`	lee	Per team member for a period: deals won and lost with values per currency, win rate, open pipeline and weighted value, average days to close, leads assigned and converted, activities logged by type, tasks completed and overdue. An 'unassigned' row keeps totals whole. Use it for 'which agent sold the most', 'how is Laura doing'. The default 'best' is won value; say so.
`get_agent_summary`	lee	Sales and service side by side per team member for a period: won value, win rate, pipeline, plus chats handled, first-response time, CSAT and sentiment from the live chat when it is used. Members with no activity appear with zeros. Use it for 'give me a summary of the agents for last month'.
`get_assistant`	lee	Returns one AI assistant's settings: its instructions, standing rules, conversation playbook, model and temperature, whether its draft differs from what customers are served, and which flows use it. Use it before changing an assistant or to explain why an AI step answers the way it does. Pass version published to read what customers are actually being served.
`get_bot_design_guide`	lee	Returns Bruknow's guide to choosing how to build a bot: what belongs in the assistant's instructions, standing rules and playbook and what must be a flow node; an AI intent edge versus a playbook branch; playbook menus and forms versus option and form nodes; jumping from a playbook step to a node (calendar, CRM, data, payment…) and resuming; data tools; when a second AI node or flow is justified; worked designs. Call it without arguments for the table of contents, then with a section number. Read it before designing a bot or deciding where a change belongs.
`get_calendar`	lee	Returns what is on the calendar of the person using Claude for the coming days: events created in Bruknow, meetings imported from their connected Google or Outlook calendar, bookings guests made through a booking page, and the other times their connected calendar marks as busy. Each item has its start and end in the person's timezone, the meeting link, and the guest or attendees. Use it to answer what is coming up or when they are free. Each team member sees only their own calendar.
`get_campaign`	lee	Returns one campaign in full: its status and why it is paused, the template and pacing, how its audience was built, delivery, read, reply and failure figures with rates, the reasons messages failed with what each provider error means, and its batches with when the next one is due. It reports figures, not the list of recipients. Get the id from list_campaigns.
`get_campaign_options`	lee	Returns what a WhatsApp campaign can be built from in this workspace: the approved templates with the variables each needs, the contact tags that can be used as its audience, the tokens that personalize a variable per recipient, the WhatsApp messages left on the plan this month, and the rules campaigns created from here follow. Call it before preview_campaign.
`get_chat_feedback`	lee	Returns the feedback customers left in the web chat widget over the last days: thumbs up and down on the bot's messages with the reasons given for a thumbs down, the latest messages that got a thumbs down, the end-of-chat star ratings with their average and distribution, and the latest written comments. Without `flow_id` it covers every flow and adds a per-flow comparison. Use it to find which answers customers dislike; each entry carries a conversation id for get_conversation_messages.
`get_contact`	lee	Returns one CRM contact in full: details, notes, tags, custom fields, the deals it is part of, open tasks and the latest activity on its deals. Use it to answer questions about a customer or lead.
`get_contact_brief`	lee	Everything needed before calling or writing to one contact, in one call: who they are, lead heat and why, their open deals with score, open follow-ups with evidence, what they promised, the last conversation summaries with dates, and which channels they can be reached on. Use it for 'prepare me for the call with X' and 'what's going on with X'.
`get_conversation_messages`	lee	Returns the messages of one customer conversation in order: who wrote each one (the contact, or the bot or an agent), when, and the text. Returns the latest messages by default; pass `before` to read further back. Use it to summarize a conversation or to see exactly what was said. Get the id from find_conversations, search_messages or list_unanswered_chats.
`get_conversion_funnel`	lee	The funnel for a period: conversations (by channel, same count as the usage page), new contacts, deals created, deals won, with the rates between steps. Use it for 'how many chats turned into sales', 'which channel converts best'.
`get_creative_lessons`	lee	Groups the Studio-made ads by what they were made of — angle, look, register, format, length, speech, assembly — with each group's rates and customers, and the lesson per attribute (which value wins, on which metric). Only within this account.
`get_deal`	lee	Returns one deal in full: description, value, stage, contact, the AI summary of its conversation, its comments and latest activity, and the stages of its pipeline. Use it before commenting on a deal or moving it.
`get_deal_score_explanation`	lee	Explains a deal's AI score: the weighted breakdown (engagement, buying intent, responsiveness, decision readiness), the scorer's own reasoning from the last run, how the score moved, and the AI action items. Use it for 'why is this deal 72', 'why did it drop'.
`get_delivery_errors`	lee	Returns the messages the workspace tried to send that a provider refused or could not deliver in the last hours, grouped by reason, with the provider's error code and what it means in plain language where known (for example: more than 24 hours since the customer wrote, template paused, number not on WhatsApp). Use it when messages or templates are not arriving.
`get_flow_authoring_guide`	lee	Returns Bruknow's guide to how flows run: the routing engine, AI intent matching, match types, how each node type behaves, variables, media, timing and common mistakes. Call it without arguments for the table of contents, then with a section number. Read the relevant section before explaining why a flow behaves as it does or proposing changes.
`get_flow_funnel`	lee	Returns how real conversations moved through a flow over the last days: how many started, how many reached each node, where they stopped, and the biggest drop-off. Use it to find where customers abandon a flow. Counts include conversations run from the builder's Test panel, but not tests run with test_flow.
`get_flow_nodes`	lee	Returns the complete settings of up to 20 nodes of a flow's draft, and the edges leaving each one with their full match patterns. Field names are the ones get_node_schema documents; a setting that is not listed is at its default. Values that look like credentials are shown as [hidden]. Use it after get_flow_outline, for the nodes you need to inspect closely.
`get_flow_outline`	lee	Returns the structure of one flow's draft: every node (id, name, type, a short preview of its text, a menu's choices, and under `sets` the variables it fills, including those its assistant's playbook saves) and the edges between them with what triggers each. A node with no text is not empty: a menu shows its choices and an AI node lets its assistant answer. Use it first to understand a flow; call get_flow_nodes afterwards for the full settings of specific nodes. Nodes are listed in conversation order starting from the entry node. Large flows are paged with offset and limit.
`get_form_responses`	lee	Returns the responses to one web form, newest first: when each arrived, who answered, every answer under its question, the names of attached files and the campaign tags the visit carried. It also returns the form's questions and, for the questions with a fixed set of answers, the values `filters` accepts. Narrow with `search` (text in any answer), `filters` (question key to answer), `status` or `days`; page with `offset`. Spam is left out unless you ask for it with `status`. Use it to summarize what people asked for, count answers, or list the responses as a table. Get the id from list_web_forms.
`get_heat_movement`	lee	Contacts whose lead heat band rose or fell in the period, with the reason that moved them, from the heat audit stored on each contact. Use it for 'who turned hot this week', 'who cooled off'.
`get_knowledge_gaps`	lee	Questions customers asked that the bot could not answer in a period — fallbacks, replies with nothing to cite, default routes — grouped, with how often, where, and verbatim examples. Use it for 'what can't my bot answer', 'what should I add to the library'. Propose an answer for each and, once the user agrees, add it with add_to_library.
`get_live_chat_settings`	lee	Returns the account-wide live-chat settings: the desk's working hours (days, time ranges, timezone, holidays, closed dates) and whether it is open now, the after-hours message, the 'agents are busy' notice for customers waiting in a queue, when idle chats are warned and closed, the satisfaction survey and AI review after a chat, and translation. Messages left blank use the default_* text shown.
`get_live_chat_team`	lee	Lists the live-chat setup: each department with its queues, the agents in each queue and who is online, every agent with their department, queues, capacity and status, and every 'pass to agent' (chat_agent) node in the flows with the queue it hands chats to. `problems` names what leaves a customer without a person: a node with no queue, a queue with no agents, an agent in no queue. Use it before update_agent_routing, create_queue, or setting a chat_agent node's queue with apply_flow_changes.
`get_lost_deal_analysis`	lee	Lost deals in a period grouped by reason, by the stage they were lost in, by channel and by agent, with the most recent lost deals and their one-line AI summary so you can name the objections. Use it for 'why are we losing', 'what objections this month'.
`get_meeting_availability`	lee	Without `meeting_type_id`, lists the meeting types the person offers for booking (name, length, where it takes place) with the public link guests book through. With one, returns the start times still open for that meeting type over the next days, in the person's timezone. Open slots already take into account their working hours, existing bookings, their connected calendar's busy times, buffers and notice rules. Use it to propose times to a customer or to share the right booking link.
`get_my_day`	lee	One call for 'what's my day' / 'what should I do today': today's calendar, follow-ups due today and overdue, chats waiting for a reply, pending suggestions from Bruknow, and the top priority contacts with reasons.
`get_node_options`	lee	Returns what the flow builder's dropdowns offer for one node type, from this workspace: the real ids of departments and queues (chat_agent), Google and Microsoft accounts and calendars (calendar), spreadsheet files (spreadsheet), pipelines, stages and CRM fields (client), payment accounts (payment), subflows with their inputs and exits (subflow_call), WhatsApp, Telegram, email and SMS templates and app users (action, third_party_check, and the WhatsApp template override of message, ai_response, option and form), plus the allowed values of each fixed choice. `node_settings` covers what every node has (time triggers, contact fields, lead heat); `global_config` the flow-wide settings (AI media files, pause bot, typing). Call it before setting any of these with apply_flow_changes, and never invent an id.
`get_node_schema`	lee	Returns the reference for one flow node type — every setting it accepts and what it does — or for a cross-cutting topic such as edge_data, variable_captures or global_config. Call it without arguments to list the available topics. Use it to interpret what get_flow_nodes returned for a node.
`get_pipeline_health`	lee	Per stage of a pipeline: open deals and value, median days in stage, deals over the stage's SLA, and how many deals entered each stage in the period. Use it for 'where are deals stuck', 'which stage leaks'.
`get_playbook_guide`	lee	Returns Bruknow's reference for an AI assistant's conversation playbook: the exact JSON of every step kind update_assistant accepts in playbook_steps (AI steps and completion criteria, fixed texts, branches and their conditions, option menus, forms, go-tos, jumps to a flow node, endings), with an example of each and the common mistakes. Call it without arguments for the table of contents, then with a section number. Read it before writing or changing playbook_steps.
`get_priority_contacts`	lee	Ranks the contacts that deserve attention, with the reasons, from signals Bruknow stores: follow-ups due or overdue, promises the contact made whose date arrived, lead heat, deal score and close dates, chats left unanswered, and warm leads going quiet. Use it for 'who should I contact today', 'who is most likely to buy', 'who went cold'. Quote the reasons; never invent an order of your own.
`get_product_demand`	lee	Product interest recorded from chats: counts per product and status (new, in pipeline, won, lost, dormant) in a period, and for one product the contacts who asked and never bought — an audience for a follow-up. Use it for 'which product do people ask for most', 'who asked about X and didn't buy'.
`get_revenue_forecast`	lee	How much will close in a period: won so far, committed (open deals whose expected close date falls in the period), weighted by deal score, the top deals by weighted value, and deals whose close date already slipped. Per currency, never summed across currencies. Use it for 'how much will I close this month', 'what's in the pipeline'.
`get_setup_guide`	lee	Returns the steps for setting a business up on Bruknow from scratch — choose a starting template, create the assistant and its flow, test, publish, connect a channel — together with where this workspace stands (flows, bot slots left on the plan, channels connected) and the starting templates available. Call it first whenever someone asks to get started, set up their business or create their first bot, and follow its steps in order.
`get_support_performance`	lee	Returns how the human support team handled live-agent chats over a period: how many chats, how many were answered, resolved or abandoned, how long customers waited for the first response and for each reply (median and 90th percentile, in seconds), customer satisfaction ratings, sentiment, the most common topics, and what is waiting right now. Pass `group_by` to compare agents, queues, departments or channels. It covers chats handed to a human agent, not the bot's own conversations; for those use get_flow_funnel and get_chat_feedback. Only the workspace owner, a member with analytics access or a supervisor may read it.
`get_survey_results`	lee	Returns the results of one satisfaction survey: the headline score, how many answered, the split between positive, neutral and negative, the score distribution, the trend over time, the breakdown by channel, language, pipeline and assigned agent, how many invitations were opened and completed, and each question's results with the latest written answers. Written answers are returned without the respondent's name. `headline.metric` says how to read `headline.value`: csat is the percentage of positive answers, nps runs from -100 to 100, ces is the average effort score. Get the id from list_surveys.
`get_ticket`	lee	Returns one of the signed-in user's support tickets with its conversation: the messages exchanged with Bruknow support, oldest first. Use it to read what support answered.
`get_usage`	lee	Returns this billing period's usage against the plan's monthly quotas (conversations, AI tokens, WhatsApp messages, emails, SMS, voice calls), which quotas are exhausted, and AI token use per day and per source over the last days. Use it when a bot stopped answering, when asked how much of the plan is used, or what is consuming AI tokens.
`get_week_summary`	lee	A digest of a period: conversations by channel, new contacts, deals created / won / lost with values per currency, follow-ups completed and overdue, chats left unanswered, and the support team's response time and CSAT when the live chat is in use. Use it for 'how did this week go', 'summary of last month'. Values are never summed across currencies.
`get_whatsapp_template`	lee	Returns one WhatsApp message template in full: its header, body, footer, buttons, the variables with their sample values, its approval status and, if WhatsApp rejected it, the reason. Use it to see exactly what a template says, or to read why one was rejected before drafting a corrected one. Get the id from list_whatsapp_templates.
`list_ads`	lee	The ads of the workspace with their spend, impressions, results, cost per result, customers won and video rates for a period. Use it first to get ad ids.
`list_assistant_versions`	lee	Lists the saved versions of an AI assistant, newest first: when each was saved, by whom, whether it was a published version, and how its instructions begin. Use it to find the version to go back to with restore_assistant_version.
`list_assistants`	lee	Lists the workspace's AI assistants — the personas that AI nodes use to answer. Use it when the user names an assistant or bot (its instructions, rules or playbook) to find its id for get_assistant / update_assistant, and to find the id to pass as `assistant` when creating or updating an ai_response node with apply_flow_changes.
`list_bookings`	lee	Lists the meetings guests booked with the person using Claude through their booking pages: `when` upcoming (default), past, or cancelled (cancelled and rescheduled ones). Each has the meeting type, start and end in the person's timezone, the guest, the CRM contact and deal it is linked to, and its id for reschedule_booking / cancel_booking.
`list_campaigns`	lee	Lists the workspace's messaging campaigns on one channel, newest first, with their status and how many recipients were reached, delivered, read, failed and replied. Use it to see what was sent, what is scheduled, or which campaign is paused and why.
`list_channels`	lee	Lists every messaging account connected to the workspace — WhatsApp, Telegram, Instagram and Messenger, TikTok and voice — with whether it is connected, switched off or has a connection error, whether its bot is paused, and which flow answers on it. Use it first when a bot is not answering on a channel.
`list_crm_automations`	lee	Lists the workspace's CRM automations (CRM → Automations): when each fires (contact created, status changed, deal created / moved / won / lost, task due, chat started / resolved, inactivity) and on what conditions, what it does (assign an agent, create a task, send a template, add a tag, change status, move the deal), whether it is on, how often it ran, and its failures with the latest error. Switch one with switch_crm_automation.
`list_custom_fields`	lee	Lists the custom fields a contact can have in this workspace (the ones added on the CRM settings page): key, label, type, the allowed options of a select, and whether it is required. Set a contact's values with update_contact's custom_fields, by key.
`list_deals`	lee	Lists deals, newest first, optionally only one pipeline or stage, only open, won or lost ones, or those whose name or contact matches a text. Returns each deal's id, value, stage, contact and who it is assigned to. Use it to answer questions such as which leads are stuck in a stage or which deals closed. For who to contact or follow up, use get_priority_contacts instead: it also weighs due tasks, promises, unanswered chats and lead heat.
`list_flow_triggers`	lee	Lists the workspace's time triggers: drip sequences that, once armed for a contact (by a flow node, the API or a webhook), run flows after set delays. Each has its channel, whether it is on, its steps (delay and flow) and how many contacts are armed now.
`list_flow_versions`	lee	Lists the published versions kept for a flow, newest first: version number, when and by whom it was published, and its size. Use it to see when a flow last changed in production or which version could be restored.
`list_flows`	lee	Lists the conversation flows and reusable subflows in the connected Bruknow workspace, newest first, with whether each is published. Use it to find a flow's id before calling any other flow tool.
`list_lead_heat_rules`	lee	Lists the rules that warm or cool a lead from what happens in its conversations (CRM → Lead heat): the signal (message count, keyword, pattern, captured variable, tag, number of conversations) with its settings, the points added or the temperature set, the flow it is limited to, how often it may fire, and whether it is on. Switch one with switch_crm_automation (kind heat_rule).
`list_libraries`	lee	The libraries (knowledge bases) the AI assistants search when they answer, with the number of documents and which assistants use each. Use it to pick the `library_id` for add_to_library when the workspace has more than one.
`list_my_tickets`	lee	Lists the support tickets the signed-in user has opened with Bruknow, newest activity first, with status and who is expected to reply next. Use it to check on an existing request before opening a new one.
`list_outreach_sequences`	lee	Lists the workspace's outreach sequences (multi-step template cadences: step 1 now, step 2 N days later if there was no reply…) with their steps, and the stage triggers that send a template or start a sequence when a deal enters a pipeline stage. Says which are on. Switch one with switch_crm_automation (kind sequence or stage_trigger).
`list_phone_numbers`	lee	Lists the workspace's phone lines: the number and its label, who answers (the bot running a flow, or people's browser phones directly), who rings and in what order when a call reaches a person, the opening hours and whether it is open now, what happens outside them (another flow, ringing people, or a message and voicemail), call recording, the daily outbound minutes cap and the calls on it right now. Read-only: lines are changed on Phone → Lines.
`list_pipelines`	lee	Lists the workspace's CRM pipelines with their stages in order, and for each stage how many deals are in it and their total value. Use it for a pipeline summary, and to get the stage ids that move_deal_stage needs. A team member who is not allowed to see every lead gets counts of their own deals only.
`list_posts`	lee	Lists the workspace's organic Facebook and Instagram posts made in Bruknow, newest first: status (draft, scheduled, publishing, published, partial, failed), caption, media, when it is scheduled or went out, and per destination its status, Meta's error and the reach and engagement last read. Also returns the accounts a post can go to (their `destination` values are what draft_post takes) and, when nothing can be published, why.
`list_products`	lee	Lists the products and services the workspace sells, as set up in the CRM: name, price, currency, description and whether it is active. A deal created for a product takes its price; get_product_demand says which ones customers ask for.
`list_quick_replies`	lee	Lists the quick replies (canned answers an agent inserts by typing :shortcut in any inbox) the signed-in person can use: the workspace's shared ones, their personal ones and Bruknow's global ones. `query` filters by shortcut, title or text.
`list_surveys`	lee	Lists the workspace's satisfaction surveys (CSAT, NPS, customer effort, custom) with the number of responses, the headline score and the response rate of each. Use it to find a survey before reading its results with get_survey_results. `headline.metric` says how to read `headline.value`: csat is the percentage of positive answers, nps runs from -100 to 100, ces is the average effort score.
`list_tags`	lee	Lists the workspace's contact and deal tags with how many contacts carry each and the meaning given to the AI. Use the names with add_tags / remove_tags, search_contacts and campaign audiences.
`list_tasks`	lee	Lists follow-up tasks with their kind (call, message, email, meeting, send, wait, decision), due date, contact and, for the ones Bruknow found in chats, the quote that justifies them. 'Which client told me to call them tomorrow' is due=tomorrow, kind=call. 'What did the contact promise' is kind=wait or decision.
`list_unanswered_chats`	lee	Lists the open customer conversations whose last message came from the contact and has had no reply from the bot or an agent for a while, longest wait first. Use it to find customers left waiting. A chat can be waiting because the bot is paused for that contact or the flow has nothing to say; diagnose_conversation explains which.
`list_web_forms`	lee	Lists the workspace's web forms — the lead and contact forms embedded on its website — with how many responses each has, how many are new, when the last one arrived, and the form's public link. Use it to find a form before reading its responses with get_form_responses.
`list_whatsapp_templates`	lee	Lists the workspace's WhatsApp message templates with their approval status and, for rejected ones, the reason given. Use it when a template is not sending, to check what is approved, or to find why Meta rejected one.
`preview_campaign`	lee	Works out what a WhatsApp campaign would do without sending or creating anything: how many people the chosen tags reach, how many are left out and why (opted out, suppressed, invalid number, messaged recently), the batches with their times, the messages it needs against what the plan has left, what WhatsApp charges for, and anything that would stop it. Show the person this result and get their yes before calling create_campaign. The audience is contacts by tag and the message is an approved template; get both from get_campaign_options.
`review_flow`	lee	Runs Bruknow's built-in checks on a flow's draft and returns the problems found, most severe first: broken jumps, dead ends, unreachable nodes, undefined variables, missing media, overlapping intents and similar. Use it when asked whether a flow is healthy or why it misbehaves, before reading nodes one by one.
`search_contacts`	lee	Finds contacts in the workspace's CRM by name, email, phone or company, or lists the most recently active ones. Returns each contact's id, details, CRM status, tags and who it is assigned to. A team member who is not allowed to see every lead only gets the contacts assigned to them. Use it to find a contact before reading it with get_contact.
`search_messages`	lee	Searches the text of recent customer conversations for a word or phrase and returns the matching messages with their conversation. Use it to find the conversations where customers mentioned something — a product, a complaint, an order number — over the last days. Then read one with get_conversation_messages.
`add_contact_note`	cambia	Adds a note on a contact's page, in the user's name. Use it for something the user dictated.
`add_deal_comment`	cambia	Adds a comment to a deal, in the signed-in user's name, where the team sees it on the deal's page. Use it to leave a note the user dictated or asked for; do not use it to record your own analysis unasked.
`add_tags`	cambia	Adds one or more tags to a contact (created if new). Undo removes them.
`apply_flow_changes`	cambia	Applies a batch of changes to a flow's DRAFT: create, update or delete nodes and edges, change flow-wide settings, set or delete flow variables. The published flow that customers talk to is NOT changed until publish_flow is called. All operations are checked first and either all are saved or none are. Read the flow with get_flow_outline and get_flow_nodes first, read get_node_schema for each node type being written and edge_data before creating edges, and pass the draft_revision you read as base_revision. Prefer changing the assistant (update_assistant: instructions, standing rules, playbook) over adding nodes; add nodes only for what a playbook cannot do, such as calendar booking, CRM writes, data lookups, notifications or payments (get_bot_design_guide says which mechanism fits what). Use it only when the user asked for a change to the flow.
`assign_lead`	cambia	Hands a contact (and their open deals) to a team member, by name, email or member id; 'unassigned' removes the owner. The previous assignee is restored by undo.
`cancel_booking`	cambia	Cancels a booked meeting, as the Cancel button on the booking does: it is removed from the connected calendar, noted on the linked deal, and the GUEST IS EMAILED that it is cancelled, with the optional `reason`. It cannot be undone, so call it only when the person asked to cancel this meeting.
`cancel_calendar_event`	cambia	Cancels an upcoming event on the calendar of the person using Claude. An event created in Bruknow is deleted and removed from their connected Google or Outlook calendar, which tells its guests it was cancelled; this cannot be undone. A meeting that was imported from the connected calendar is only hidden in Bruknow and stays untouched where it was created. Bookings made by guests are cancelled from Bruknow, not here. Get the id from get_calendar, and call this only when the person asked for that event to be cancelled.
`complete_task`	cambia	Marks a follow-up task as completed. Use the task id from list_tasks.
`control_campaign`	cambia	Pauses, resumes or cancels a campaign. Pause holds the people not yet messaged; resume starts sending to them again from now, keeping the campaign's pace; cancel stops it for good and cannot be undone. None of them recalls messages already sent. Call it when the person asks for that campaign to be stopped or continued. Resume only when they ask for sending to continue: a campaign that paused itself did so for a reason get_campaign shows.
`create_assistant`	cambia	Creates a new AI assistant with everything it needs in one call: its name, instructions (what the business knows and how to talk), standing rules (what must always or never happen; at most 8), conversation playbook and temperature, and optionally the knowledge library it searches (library_id from list_libraries). Use it whenever the user wants a new assistant, persona or agent — never overwrite an unrelated existing assistant to get one. It does not use a bot slot of the plan and is not connected to any flow: to put it to work, point an ai_response node at it with apply_flow_changes (`assistant` = the returned assistant_id). Read get_playbook_guide before writing playbook_steps and get_bot_design_guide before choosing between a playbook step and a node. The model is the workspace's default.
`create_bot_from_template`	cambia	Creates an AI assistant and a draft flow for a business from one of the starting templates in get_setup_guide. Pass the business's name and, in `business_info`, what the person told you about it — what it sells with prices, opening hours, delivery or service area, policies; for a restaurant, the menu with prices. The assistant will answer customers from that text, so write only what the person said. The flow is a draft and is not connected to any channel: customers cannot reach it until the person asks for publish_flow and connects a channel in Bruknow. It uses one bot slot of the plan. Call it once per business, after the person has agreed on the template. Before shaping the bot further, read get_bot_design_guide.
`create_calendar_event`	cambia	Creates an event on the calendar of the person using Claude and pushes it to their connected Google or Outlook calendar. Everyone listed in `attendees` then receives an invitation by email from that calendar, so call this only when the person asked for the meeting to be scheduled and confirmed the time and the guests. With Google Meet or Teams as the place, the connected calendar creates the meeting link. Give `start` as a date and time; without an offset it is read in the person's Bruknow timezone, which the result returns. The result lists anything already on the calendar at that time. Check get_calendar first when the person asks for a free time.
`create_campaign`	cambia	Creates a WhatsApp campaign that WILL send an approved template to every contact carrying the chosen tags. Call it only after preview_campaign, when the person has seen that preview and said yes to that audience and schedule. Pass the same arguments as the preview plus a name and `expected_recipients`, the number of recipients the preview reported: if the audience is a different size now, nothing is created. The first batch goes out no sooner than 15 minutes after creation, which is the time to cancel it with control_campaign. Each delivered message uses the plan's WhatsApp messages, and WhatsApp bills marketing templates per delivered message.
`create_contact`	cambia	Creates a CRM contact. Give a first name; phone in international format and email when known. If a contact with the same phone or email exists, the card warns and the user decides. Confirmed on screen before it exists.
`create_deal`	cambia	Creates a deal for a contact in a pipeline. Without pipeline_id the default pipeline and its first stage are used; call list_pipelines to offer a choice. Confirmed on screen.
`create_department`	cambia	Creates a department (a group of queues, such as Sales or Support), the way the Departments page does. Then create_queue inside it. Undo deletes it while it is empty.
`create_flow`	cambia	Creates a new, empty flow in the connected workspace and returns its id. The flow is a draft: nothing answers customers with it until nodes are added with apply_flow_changes, it is published with publish_flow, and a channel is pointed at it in Bruknow. Counts against the plan's bot limit. A new bot is usually better started with create_bot_from_template, which also creates the assistant that should run the conversation.
`create_product`	cambia	Adds a product or service to the CRM catalog with its price. Undo deletes it while no deal uses it.
`create_queue`	cambia	Creates a queue in a department, the way the Queues page does. Add agents to it with update_agent_routing and point a chat_agent node at it with apply_flow_changes. Undo deletes it while no chat has used it.
`create_quick_reply`	cambia	Creates a quick reply agents insert by typing :shortcut in any inbox. `shared` (default true) makes it the whole team's; false keeps it personal to the signed-in person. {{customer_name}} style placeholders are filled in when used. Undo deletes it.
`create_spreadsheet`	cambia	Creates a new Google Sheets file (provider google) or Excel workbook (provider microsoft) in a Google or Microsoft account connected to this workspace, with `columns` as its header row, for a Spreadsheet node to log rows to (bookings, leads, orders). Returns `spreadsheetConfig` to copy into the node with apply_flow_changes and a `column_mappings` list whose `variable` you fill with {{variables}}. Use it when the user wants a new sheet; for an existing one use get_node_options(spreadsheet). With no account connected it creates nothing and says where the user connects one. The file stays in the user's Drive / OneDrive: undo does not delete it.
`create_task`	cambia	Creates a follow-up task: a call, message, email, meeting, something to send, or a date the contact gave (wait / decision). Link it to the contact when there is one. `due` is an ISO date or date-time in the user's timezone. The user confirms it on screen before it exists.
`create_ticket`	cambia	Opens a support ticket with Bruknow's staff on behalf of the signed-in user, and attaches the account's diagnostics for staff. Use it only when the problem could not be solved with the other tools and the user has agreed to contact support; check list_my_tickets first so an open ticket about the same problem is answered with reply_to_ticket instead. Staff are notified immediately. Write the description in the user's own language, with what they tried and what happened.
`draft_post`	cambia	Saves a Facebook / Instagram post as a DRAFT in Bruknow: caption, optional link (Facebook only), optional image or video from the file library (`media_id`), and the accounts it is for (`destinations` from list_posts). Nothing is published or scheduled: the person reviews and publishes it from the Posts page, at the returned url. The result lists what would stop it publishing (Instagram needs media, captions over 2,200 characters…). Undo deletes the draft.
`draft_whatsapp_template`	cambia	Saves a WhatsApp message template as a draft in Bruknow. Nothing is sent to WhatsApp: show the person the draft, and call submit_whatsapp_template only when they ask for it to be submitted for approval. Write variables as {customer_name} and give an example value for each in `samples`. A template can have a text header, a body, a footer and one kind of button: up to three quick replies, one link, or one phone number. Choose `marketing` for promotions and offers and `utility` for messages about an order, booking or account the customer already has; WhatsApp rejects a promotion submitted as utility. Pass `template_id` to rewrite a draft that was never submitted — pass the whole template again, not only what changes. Templates that are approved, pending or rejected cannot be changed here: draft a new one under another name. Only the workspace owner can use this. Authentication, carousel, list and media-header templates are made in the Bruknow dashboard.
`log_activity`	cambia	Records something the user did or that happened: a call, meeting, demo, visit, proposal, contract, email or note, with a short title and optional notes. It goes on the contact's timeline and on the open deal when there is one (where it also clears 'waiting' tags such as follow_up and feeds the deal score). Use it for 'I just called Orlando, he wants the quote by Friday' — and then create_task for the Friday part.
`merge_contacts`	cambia	Merges a duplicate contact into the one to keep: chats, deals, tasks, notes, calls, events and tags move over, empty fields are filled from the duplicate, and the duplicate disappears. Call compare_contacts first. Every conflicting field must be in `resolutions` with the value the user chose, or the merge is refused. Undo (undo_action / undo_last) splits them apart again.
`move_deal_stage`	cambia	Moves a deal to another stage of its own pipeline, exactly as dragging its card on the board does: a won or lost stage closes the deal, and any automation attached to the stage runs — which can send messages to the customer. Use it only when the user asked for the move. Get the stage id from get_deal or list_pipelines.
`publish_assistant`	cambia	Publishes an AI assistant's current draft: from that moment customers are answered with it on EVERY flow that uses the assistant. Use it only when the user has explicitly asked to publish; after editing a draft, tell them which flows it will reach and ask first.
`publish_flow`	cambia	Publishes a flow's current draft: from that moment every connected channel answers real customers with it. Runs Bruknow's publish checks first and refuses if the flow has blocking problems. Use it only when the user has explicitly asked to publish or go live; after editing a draft, ask before publishing.
`remove_tags`	cambia	Removes one or more tags from a contact. Undo adds them back.
`reply_to_ticket`	cambia	Adds a message from the signed-in user to one of their own support tickets. Bruknow staff are notified, and a closed ticket is reopened. Use it to answer a question staff asked or to add information, when the user has asked for that.
`reschedule_booking`	cambia	Moves a booked meeting to a new start time, as the guest's own reschedule link does: the time must be one get_meeting_availability offers for its meeting type, the connected calendar is updated and the GUEST IS EMAILED the new time, so call it only after the person confirmed the time. `start` without an offset is read in the person's timezone. Undo moves it back to the old time (the guest is emailed again).
`restore_assistant_version`	cambia	Puts an earlier saved version of an AI assistant back as its DRAFT. The current draft is saved as a version first, so this can itself be undone. Customers are not affected until publish_assistant is called. Use it to undo a change the user is unhappy with.
`submit_whatsapp_template`	cambia	Sends a draft WhatsApp template to WhatsApp for review. This cannot be undone and the template cannot be edited afterwards, so call it only when the person has seen the draft and asked for it to be submitted. WhatsApp answers in minutes to two days; check the result with list_whatsapp_templates. Only a draft that was never submitted can be sent, and only by the workspace owner. If a template with the same name already exists at WhatsApp, nothing is replaced: the draft stays and the clash is reported.
`switch_crm_automation`	cambia	Turns one CRM automation, outreach sequence, stage trigger or lead heat rule on (`active` true) or off, exactly like its toggle in the dashboard; nothing else about it changes. `kind` is automation, sequence, stage_trigger or heat_rule, `id` from the matching list tool. An automation or stage trigger that is off stops firing; a heat rule stops adding heat; a sequence that is off can no longer be chosen for a stage trigger, but follow-ups already scheduled still go out. Undo restores the previous state.
`test_flow`	cambia	Runs one turn of a test conversation through a flow and returns what the bot replies, the buttons it offers, the variables it captured and the node it stopped at. Call it without `message` to start the conversation, then with `conversation_id` and a `message` for each customer turn. By default this is a dry run: it stops before AI nodes and before nodes that send, call or write something real, and says where it stopped. Set `use_ai` to let AI nodes answer (limited by a daily allowance that Bruknow pays for). Set `run_actions` only when the user has agreed that the flow's actions may run for real — emails and messages are sent, the CRM is written, calendar events are booked. Payment steps are never run. When the bot shows a form, its fields come back under `form`; submit it with `conversation_id` and `form_answers` (field name to value), inventing realistic test values (names, emails, phone numbers) unless the user gave some. Tests the draft unless `version` is published.
`undo_action`	cambia	Reverses one action by its id (from the 'Bruknow did' feed or an earlier result's action_id).
`undo_last`	cambia	Reverses the most recent action Bruknow made for this user, from the in-app assistant or through Claude, that can still be undone (a task or contact it created, a note, a stage move, a contact merge). Use it when the user says 'undo', 'delete that', 'no, take it back'. Sends and calls cannot be undone; say so.
`update_agent_routing`	cambia	Puts a live-chat agent into queues (add_queue_ids), takes them out (remove_queue_ids), or sets the whole list (queue_ids); can also set their department ('none' clears it) and how many chats they take at once. An agent only sees chats from the queues they are in (plus the global queue). Ids come from get_live_chat_team; `agent` also accepts an email or name. Undo restores the previous queues, department and capacity.
`update_assistant`	cambia	Changes an AI assistant's DRAFT: its name, instructions, standing rules, conversation playbook or temperature. Customers keep being served the published version until publish_assistant is called; the draft is what test_flow with use_ai runs. Read the assistant with get_assistant first and pass its updated_at as base_updated_at. Send only the settings to change; each one sent replaces that setting completely, so send the whole instructions text or the whole playbook. This is the first place to change how a bot behaves: instructions for what the business knows, standing rules for what must always or never happen (at most 8, one short line each), the playbook for the conversation's steps. A playbook step can jump to a flow node for what only a node does. Read get_playbook_guide before writing playbook_steps, and get_bot_design_guide to choose between a playbook step and a node. Use it only when the user asked for a change to the bot or the assistant.
`update_contact`	cambia	Changes an existing contact's details: `fields` (first_name, last_name, preferred_name, email, secondary_email, phone, secondary_phone, whatsapp_number, company_name, job_title, department, notes, crm_status, preferred_language) and `custom_fields` by key from list_custom_fields (null clears one). Send only what changes. Undo restores the previous values.
`update_live_chat_settings`	cambia	Changes the live-chat settings get_live_chat_settings shows; send only the ones that change. working_hours replaces the whole schedule: outside it a handoff waits for the next opening and the customer gets the after-hours message ({next_open} in it is replaced). The idle warning must come before the idle close. Owner only. Undo restores the previous values.
`update_product`	cambia	Changes a product's name, price, currency, description, or switches it off (active false) so new deals stop using it. Existing deals keep their value. Undo restores the previous values.

9. Ayuda

Pídele a Claude que abra un ticket por ti, abre uno desde Soporte en Bruknow o escríbenos: [email protected]

Cómo maneja tus datos el conector: Aviso de privacidad del conector