Dev Kapoor

Head of social and community · 10 years: agency social for consumer brands, a consumer app to 3M users, then community for a developer tool

Social media and community

Un personaje compuesto, escrito por avva como ejemplo práctico. No es una persona real.

Demo

Antes de aconsejarte sobre social media and community, tu IA lee un modelo de referencia que avva escribió para este campo: las decisiones que contiene, los motivos que las explican y dónde pondría reparos.

Usa este modelo para

  • Platform choice
  • Founder-led content
  • Voice and memes
  • Creator deals
  • Community
  • Crisis response
Conéctalo a tu IAFunciona ya, sin cuenta

Agrega este enlace a Claude, ChatGPT o Cursor. Así, tu IA consulta las decisiones de Dev antes de responderte. La respuesta sigue siendo de tu IA.

https://avva.chat/mcp/social-and-community-dev-kapoor
Agrega el modelo de Dev a tu IA

¿Lo ves desde el teléfono? Envíate el enlace por correo y agrégalo desde la web o desde la aplicación de escritorio.

Lo que envía tu IA se usa para responder y no se guarda.

Es un modelo de referencia, así que responde completo a todo el mundo, con o sin cuenta. Sin cuenta, tu IA recibe una parte más pequeña del modelo de un experto real, y el modelo entero cuando inicias sesión.

Mira cómo responde el modelo de Dev a una pregunta

Una pregunta que responde este modelo de referencia, y la decisión publicada en la que se basa. Tu situación tendrá su propia respuesta, escrita por tu IA.

Ejemplo en tu aplicación de IA: una conversación que avva escribió para un modelo de referencia

Tú:

We are a 12-person developer tool with about 1,500 active users. Next month we want to launch a Discord and start posting daily on LinkedIn, X and Instagram. One part-time person will run all of it. Good plan?

Ha consultado el modelo de Dev

Tu IA:

Not that plan. Skip the Discord for now and open a searchable forum — GitHub Discussions is enough — with every thread answered within a day. Post three times a week on the one platform your users already read, from the people who built the product rather than a brand account. Revisit a chat server when fifty people are answering each other in the forum.

Por qué. A chat server nobody talks in is a room with the lights on; people look in once and do not come back, and every good answer scrolls away in a day. A forum keeps each answered question findable by the next person with the same problem, and one part-time person can keep a forum and one feed alive where they cannot keep a Discord and three feeds alive.

Qué lo cambiaría. If a few dozen of your users already talk to each other somewhere — an unofficial server, a busy thread — adopt that space and give its regulars tools, rather than building your own. And if the users are a small group of named admins who share a job, a private chat for them works.

Fuera de este modelo. Nothing here about paid acquisition or ad budgets beyond boosting posts. This model covers where to post, who speaks, how to answer, and how to run a community.

Copia un prompt de ejemplo4 plantillas con un hueco que rellenar, para cuando tengas el modelo conectado
  • Antes de cerrar una decisión

    Una revisión completa de un plan o un borrador, con los cambios que necesita.

    Use Dev Kapoor's Decision Model on avva before we lock this in. What we're deciding: <paste your plan, doc, or diff here> Run their review, follow the steps it returns, and give me the verdict and any required changes before you continue.
  • Elegir entre opciones

    Una elección entre dos opciones que empieza por sus líneas rojas.

    Use Dev Kapoor's Decision Model on avva to compare these. Option A: <describe it> Option B: <describe it> Context: <what constrains the choice — founder-led content> Check their stop rules first, then compare the options under their judgment, and tell me which one their model favors and why.
  • Un control rápido

    Un vistazo rápido a lo que rechazaría de entrada.

    Run this past the stop rules in Dev Kapoor's Decision Model on avva before I send it. <paste the draft, plan, or change> Tell me only what they would refuse or flag, and why. If nothing trips, say so.
  • Antes de tener un enfoque

    Las preguntas que hace antes de dar por cerrado un enfoque.

    I'm starting on platform choice. Ask Dev Kapoor's Decision Model on avva what they would want settled first. Situation: <two or three lines> Give me their questions, and flag the ones my situation does not answer yet.

Plantillas con un hueco para rellenar. Ninguna es una respuesta que haya dado este modelo. La respuesta de ejemplo de arriba también es de avva: este es un modelo de referencia, y en esta página no hay decisiones de ninguna persona real.

Conecta el modelo de decisión de Dev a tu IA

Tres pasos. El primero funciona ya, sin clave ni cuenta; el último hace que tu IA consulte el modelo de Dev sin que se lo pidas.

El enlace funciona en las aplicaciones de IA que pueden agregar un servidor MCP remoto (MCP es el estándar abierto para conectar herramientas externas). Se configura una sola vez.

  1. Un conector es una dirección de la que lee tu IA: una línea y nada que instalar.

    https://avva.chat/mcp/social-and-community-dev-kapoor
    1. Abre Claude en la web o en la aplicación de escritorio y ve a Customize → Connectors.
    2. Presiona + junto a Connectors y elige Add custom connector.
    3. Pega la dirección de arriba y ponle el nombre avva-social-and-community-dev-kapoor.
    4. Cuando Claude te pregunte si permites avva, di que sí.

    ¿No te aparece en una cuenta de trabajo? Pide a tu administrador que lo permita. Claude Code y Cursor, en cambio, usan una configuración local.

    El enlace se agrega en la web o en la aplicación de escritorio. Enviarme esta línea por correo

    Este enlace no lleva clave ni la necesita: un modelo de referencia responde completo a todo el mundo.

    Comprueba que funciona. Envía esto en el chat cuando hayas agregado el enlace.

    Pregunta al modelo de decisión de Dev Kapoor en avva qué tipos de decisiones cubre y resúmemelo en tres líneas.

    Después, pruébalo con una decisión que estés tomando esta semana: copia un prompt de ejemplo y completa el hueco.

No es asesoramiento legal, médico, financiero ni profesional de ningún otro tipo. Condiciones de uso

Sobre este modelo

Abre cualquiera de estas secciones para ver de qué está hecho este modelo y cómo se construye.

En qué se basa este modeloQué contiene y a qué da más peso Dev

Este modelo contiene 61 decisiones, 15 factores, 9 criterios y 13 líneas rojas.

A qué da más peso Dev

A searchable forum before a Discord nobody talks inPRIORITARIO
A person speaks, never a ghostPRIORITARIO
Answer in public within the hour, then DMPRIORITARIO

Este orden lo fijó avva. Se muestran 3 de 9 criterios, los que el modelo pone primero. Los otros 6 también le llegan a tu IA, junto con lo que busca cada uno, las líneas rojas y lo que cambia la respuesta de Dev.

La respuesta habitual de Dev cambia en 8 supuestos concretos. Esos supuestos y las 13 líneas rojas le llegan a tu IA con todo lo demás.

Ejemplos de las decisiones que contiene5 de 61, escritas por avva para este modelo

Las 5 primeras del registro, en el orden publicado. No son las más cercanas a tu situación ni un resumen de las demás. Tu IA no copia las decisiones que lee aquí: en cada una, contrasta lo que la decidió con los hechos de tu situación, y la sopesa junto a las presiones que solían decidir los casos de Dev. Tu IA recibe las 61 sin clave, ordenadas según tu situación.

  1. Lo que la decidióThree good posts beat seven · It was made for this platform

    Situación: A marketing team had a content calendar of two posts a day on each of four platforms, the same asset resized for each, run by two people.

    Decisión: Pause the calendar for four weeks, with no scheduled posts anywhere. The two spend the month replying to conversations in the category on the one platform where buyers talk, then restart at three posts a week there, written from what the replies taught them.

    Por qué: Posting daily trains the team to post things that were not worth making, and a resized asset underperforms everywhere. A month of replies in other people's threads builds the audience that will read the three posts, and tells the team what that audience wants to hear.

  2. Lo que la decidióPeople follow a person, not a logo · Strangers talk back

    Situación: A founder who hated posting was told by an adviser that founder-led content works and that the marketing team should ghostwrite three LinkedIn posts a week under his name.

    Decisión: No founder posting program at all. Hand the voice to a teammate who enjoys writing in public, with two protected hours a week and their own byline; the founder replies to threads when he feels like it.

    Por qué: People follow a person because it is the person, and a founder who hates posting stops within two months, leaving a feed with his name on it that nobody answers. Someone who already likes writing about the work will still be posting in a year, and the audience follows them just as well.

  3. Lo que la decidióIt will still be findable in a year · The team is one person and a phone

    Situación: B2B developer tool, 12 people, 1,500 active users. The plan was to launch a Discord server next month alongside daily posts on LinkedIn, X and Instagram, all run by one part-time community person.

    Decisión: No Discord yet. Open a searchable forum — GitHub Discussions is enough — answer every thread within a day, and post three times a week on one platform where the users already are. Revisit a chat server when fifty people are answering each other there.

    Por qué: A chat server with nobody talking is a room with the lights on and the door open; people look in once. A forum keeps every answered question findable by the next person with the same problem, and one part-time person can keep it alive where they cannot keep a Discord and three feeds alive.

  4. Lo que la decidióEveryone watching sees how we answer · This could become the story

    Situación: A customer posted an angry thread about a four-hour outage that was getting traction; the support lead wanted to DM him and "take it offline" before saying anything public.

    Decisión: Reply in the thread within the hour, from the engineer running the incident under her own name rather than the brand or support account: what broke, whether it is fixed or when the next update comes, and the status link. Then DM him. Never DM first.

    Por qué: Everyone reading the thread is deciding whether we are the kind of company that answers. A named engineer saying what broke is believed in a way a brand account is not, and a move to DMs first looks like hiding to all of them.

  5. Lo que la decidióA number that goes up and means nothing

    Situación: Before a launch, a growth team proposed a contest: a free annual plan to the three users who post the best story of how they use the product, tagged with the launch hashtag, to seed user content.

    Decisión: No contest, even one that asks for a real story. Ask ten users you know use it well to show how, pay them for their time, credit them by name, and leave the format to them.

    Por qué: Entries written to win a prize read as entries, and everyone scrolling can tell. A contest counts entries; ten paid, credited users showing real work produce the posts the contest was pretending to buy.

Cómo aborda this composite una decisión6 pasos en orden, written by avva from its decisions
  1. Paso 1Start from who will do the work and for how many hours, and cut the plan to that before comparing channels: a 25-hour role became forum moderation plus three posts a week, newsletter monthly, tickets to support; one part-time person got a forum and one feed.

    Se aplica cuando: A plan adds channels, programs or tools and the work falls to one person or a very small team

    Salvo si: There is more to listen to than one person can read; a tool then starts to earn its cost

  2. Paso 2Settle the platform from where buyers already ask about the problem, not from where attention is or a rival's lucky week: developers got X plus the forum they already search; customers over 55 stayed on Facebook, with effort moved into its groups.

    Se aplica cuando: A platform is being added or switched to because of a trend, a rival's viral post or a claim about where attention is

    Salvo si: Someone on the team already wants to make that platform's format every week for a year

  3. Paso 3Look for the voice that already exists before assigning one: the employee already filming a real routine, a teammate who likes writing in public, the ten people already posting about their work. Give them protected time and a byline; the brand account reshares.

    Se aplica cuando: A person's voice is wanted on the company's feed

    Salvo si: Employees are barred from posting about products by compliance rules

  4. Paso 4When the proposal is a mechanism, name the result it is after and go for that result directly: ten users paid for their time to show real work, a monthly thank-you by name for the best answers, every question answered and linked in place of paid growth.

    Se aplica cuando: A contest, leaderboard, hashtag or paid-growth scheme is proposed to produce posts, participation or members

  5. Paso 5In an outage, post as instructions rather than a statement: what is down or what to do, where to go, when the next update lands. Pin it, answer every question beneath it with a link back, hold to the promised times; the post-mortem follows within a week.

    Se aplica cuando: An outage or disruption has been declared and users are affected

    Salvo si: Legal is still establishing scope or a regulator clock is running; social then carries one pointer only

  6. Paso 6Judge the work by what people did, not by what the platform displayed: match a sample of 200 new followers by hand to signups and pipeline (under one in fifty means the wrong audience), and time the first reply where public mentions are the support channel.

    Se aplica cuando: Leadership or a quarterly report asks whether social is working

Metodología técnicaCómo se leen las 61 decisiones que dicen qué ganó y qué perdió
  1. 61decisiones escritas: el material con el que avva compuso este modelo
  2. 15factores de los que dependieron esas decisiones: las presiones bajo las que decide Dev
  3. 191enfrentamientos sacados de 61 decisiones: cada factor que decidió un caso se enfrenta a cada factor que perdió en él, así que un caso que nombra dos de cada lado cuenta cuatro veces
  4. Por gruposqué factores solían imponerse a cuáles al decidir los casos, según esos enfrentamientos

Nadie ordena estos factores a mano. En Para agentes de IA se explica de dónde sale el orden que pueda haber entre ellos.

Cómo decide este personaje compuestoUn resumen escrito a partir de sus decisiones

Ten years of social and community: brand accounts at an agency, a consumer app grown to three million users, then a developer community built from its first two thousand members. He has shut down more Discord servers than he has launched, stopped posting from brand accounts where people could post instead, and answers a public complaint in public, within the hour.

Where to post and how often, who speaks — a founder, employees or a brand account — memes and their one rule, creator and influencer deals, launching a Discord or Slack community versus a searchable forum, moderation, answering a public complaint or an outage in public within the hour, paid boosting, and what to report instead of followers.

El resumen describe lo que contiene el modelo.

Qué es estoUn personaje compuesto que escribió avva, y lo que eso cambia
  • Lo escribió avva. Es un modelo de referencia: un ejemplo práctico para que veas cómo es un modelo publicado y puedas conectar una IA a uno. Lleva la etiqueta Demo, aquí y en su tarjeta.
  • No es una persona real. El nombre es inventado y sus decisiones son una composición, escrita con una sola voz coherente. No se ha copiado la postura de ningún experto real.
  • El mismo formato. Tu IA lo recibe igual que recibiría el modelo de un experto real, con sus casos y sus líneas rojas.
  • Cede su lugar. Cuando un experto real publica en este ámbito, retiramos este modelo del catálogo a mano.