Fin AI podcast

Guardrails, not guard dogs: Shipping reliable AI actions

1 h 8 min · 18 de sep de 2025
Portada del episodio Guardrails, not guard dogs: Shipping reliable AI actions

Descripción

Intercom’s Chief AI Officer Fergal Reid sits down with Principal Machine Learning Engineer Pratik Bothra to explore what it really takes to make AI actions reliable and safe. They dive into the pitfalls of moving from demo to deployment, why deterministic checks trump LLM watchdogs, and why most resolutions still come from strong informational answers. It’s a candid look at the challenges and trade-offs in building agentic workflows that work in production. Watch on YouTube: https://youtu.be/bcghIm-1sAI?si=mm5QA_gafBP29XMXFollow the people https://www.linkedin.com/in/fergalreid/ https://www.linkedin.com/in/pratik-bothra-bba03074/ Insights and blogs from the AI Group building Fin at Intercom: https://fin.ai/research/ https://www.linkedin.com/showcase/fin/ https://x.com/Fin_ai https://www.fin.ai See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

Comentarios

0

Sé la primera persona en comentar

¡Regístrate ahora y únete a la comunidad de Fin AI podcast!

Prueba gratis

Empieza 7 días de prueba

$99 / mes después de la prueba. · Cancela cuando quieras.

  • Podcasts solo en Podimo
  • 20 horas de audiolibros al mes
  • Podcast gratuitos

Todos los episodios

3 episodios

episode Guardrails, not guard dogs: Shipping reliable AI actions artwork

Guardrails, not guard dogs: Shipping reliable AI actions

Intercom’s Chief AI Officer Fergal Reid sits down with Principal Machine Learning Engineer Pratik Bothra to explore what it really takes to make AI actions reliable and safe. They dive into the pitfalls of moving from demo to deployment, why deterministic checks trump LLM watchdogs, and why most resolutions still come from strong informational answers. It’s a candid look at the challenges and trade-offs in building agentic workflows that work in production. Watch on YouTube: https://youtu.be/bcghIm-1sAI?si=mm5QA_gafBP29XMXFollow the people https://www.linkedin.com/in/fergalreid/ https://www.linkedin.com/in/pratik-bothra-bba03074/ Insights and blogs from the AI Group building Fin at Intercom: https://fin.ai/research/ https://www.linkedin.com/showcase/fin/ https://x.com/Fin_ai https://www.fin.ai See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

18 de sep de 20251 h 8 min
episode Closing the loop: From snippet monster to maintainable insights artwork

Closing the loop: From snippet monster to maintainable insights

Intercom’s Chief AI Officer Fergal Reid sits down with Staff ML Scientist Fedor Parfenov to unpack how the Fin team turned failed conversations into better answers - safely. They trace the journey from Copilot to the new Insights product, tackling content gaps, the “snippet monster,” accumulation and consolidation, and why causal inference beat classic A/B tests for measuring real impact. Watch this episode on YouTube: https://youtu.be/Qagm7Pb2aRk?si=2bIhZ0uAd0XEBw8v Follow the people https://www.linkedin.com/in/fergalreid/ https://www.linkedin.com/in/fedor-parfenov/ https://fin.ai/research/ Insights and blogs from the AI Group building Fin at Intercom See Privacy Policy at https://art19.com/privacy [https://art19.com/privacy] and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info [https://art19.com/privacy#do-not-sell-my-info].

9 de sep de 202548 min