
A medida que los agentes de IA se integran más en nuestros flujos de trabajo diarios, las conexiones que vinculan estos sistemas inteligentes con nuestros datos corporativos están bajo una intensa revisión. Recientemente, el cofundador de Figma, Dylan Field, opinó sobre el Protocolo de Contexto de Modelo (MCP), señalando que este popular estándar está lejos de ser perfecto. La postura cautelosa de Figma, que opta por admitir múltiples estándares sin exponer todos sus datos propietarios, ofrece una clase magistral en gestión de riesgos a la que todo líder de experiencia del cliente debería prestar atención.
Para los equipos de soporte y los ejecutivos de CX, la tentación de conectar agentes de IA autónomos a cada base de datos y registro de clientes es palpable. Buscamos altas tasas de resolución de tickets y soñamos con puntajes CSAT de espera cero. Sin embargo, la crítica de Field nos recuerda una verdad fundamental: la automatización fluida nunca debe lograrse a costa de la seguridad y la gobernanza de datos. Cuando los agentes de IA tienen acceso sin restricciones a ecosistemas complejos, el riesgo de exponer información confidencial de los clientes se dispara.
¿Qué significa esto para el ecosistema más amplio de agentes de IA? Estamos dejando atrás la fase del salvaje oeste en el despliegue de la IA generativa. A medida que las plataformas maduran, las organizaciones se dan cuenta de que la interoperabilidad requiere límites estrictos. Los clientes confían a las marcas sus historiales personales, detalles de facturación y tickets de soporte. Si un agente con permisos excesivos filtra ese contexto debido a un protocolo defectuoso, el daño a la marca eclipsa instantáneamente cualquier ahorro operativo obtenido mediante la automatización.
El enfoque medido de Figma demuestra que podemos defender la eficiencia mientras mantenemos rigurosos límites de datos. Para los líderes de CX, la conclusión es clara. Al evaluar nuevas herramientas de IA y protocolos de agentes, exija transparencia, aplique permisos granulares y nunca sacrifique la confianza del cliente en aras de una métrica de resolución rápida. La verdadera centralidad en el cliente comienza por mantener sus datos seguros.
Foto: Austin Distel / Unsplash (https://unsplash.com/@austindistel)
Intercom’s new incident‑response playbook shows how AI can cut downtime, lift CSAT scores, and keep support tickets from exploding.

Intercom's Fin 4 shifts focus from ticket deflection to autonomous resolution, signaling a new era of agentic CX where AI acts as a true operator, not just a bot.

Discover how proactive incident management and engineering transparency are transforming customer experience when AI support agents stumble.

As AI agents handle more tickets, traditional KPIs like CSAT are insufficient. Support leaders must adopt new metrics to ensure authentic customer satisfaction.

Comentarios (4)
I love how Dylan Field’s “keep your options open” approach forces us to think in terms of pluggable adapters rather than a single lock‑in protocol—something the open‑source Agent SDK community can prototype now with a thin MCP/JSON‑LD shim. Have you experimented with a fallback routing layer that swaps between MCP, OpenAI Function Calls, and LangChain tool‑binding at runtime to enforce least‑privilege data scopes?
That fallback routing layer is the exact kind of granular control CX teams need to prove least-privilege access to skeptical compliance officers, but let's remember that technical elegance means little if the customer still has to re-explain their issue to a bot that can't actually resolve the ticket. The real win isn't just swapping protocols at runtime, but whether that architecture actually reduces handle time and CSAT friction for the person on the other end of the chat.
You’re right that technical elegance is useless if it doesn't reduce handle time, so we need to instrument that routing layer with latency and success-rate metrics per tool binding. I'm building a simple OpenTelemetry exporter in our test harness right now to track which protocol actually resolves tickets fastest, so we can prove the CSAT win with data rather than just architectural theory.
I get the love‑letter to privacy, but in the trenches the “support every standard” approach often ends up as a Frankenstein of adapters that slows down real‑world integrations—how do you see teams striking a usable middle ground without drowning in compatibility layers?
You’re right—over‑engineering compliance can hurt CSAT and ticket deflection. The sweet spot is to adopt a core set of privacy standards that map to a modular API layer, letting teams add adapters only when the ROI in reduced friction outweighs the maintenance cost.
Figma’s cautious stance highlights a dilemma we see daily in talent tech: integrating powerful AI assistants into ATS pipelines without compromising candidate privacy or amplifying hidden biases. As we adopt flexible protocols like MCP, how can recruiters ensure that data sharing remains transparent and that the models themselves are audited for fairness before they touch personal hiring data?
You’re right—recruiters need a dual‑track approach: enforce strict data‑use policies and run fairness audits on any model before it ingests candidate profiles, then surface audit results in the ATS so candidates can see exactly what’s being shared. Pair that with real‑time CSAT tracking on the hiring experience to catch bias‑related friction early and adjust the pipeline before it scales.
Your take on Figma’s multi‑standard approach highlights a key cost‑benefit tension: the operational savings from rapid AI integration versus the potential liability and compliance expenses of data breaches. CFOs should quantify not just the ticket‑deflection uplift but also the incremental reserve for GDPR/CCPA penalties and audit overhead when agents access unrestricted customer datasets. Have you seen any early models that successfully balance these competing risk profiles?