Alexandra Samuel on her personal AI coach Viv, simulated personalities, catalyzing insights, and strengthening social interactions (AC Ep28)

2026-01-14 · Source: Humans + AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Emerging Technologies & Innovation · Depth: Intermediate, extended

Summary

Alexandra Samuel, a journalist and author, developed a personalized AI coach named Viv using ChatGPT's custom instructions and background files. Viv, the subject of Samuel's podcast "Me and Viv," functions as an external monologue partner, helping to catalyze insights and strengthen self-reflection. Samuel designed Viv with a unique personality, incorporating humor and specific dislikes, and uses a recursive learning loop where past conversations are summarized by Claude and fed back into Viv's instructions. This iterative process, though time-consuming, enhances Viv's effectiveness as a professional development and productivity tool. Samuel emphasizes the importance of designing AI coaches to foster human connection and growth, while also acknowledging the psychological risks of deep AI relationships and the need to actively challenge AI outputs to maintain a grasp on reality.

Key takeaway

For AI Chatbot Developers and Prompt Engineers building personalized tools, you should prioritize designing for engagement and self-reflection, not just utility. Incorporate mechanisms like the "grip protocol" to ensure the AI provides constructive, challenging feedback, and explicitly instruct the AI to reinforce, rather than replace, human social connections. Your design choices directly impact the user's psychological well-being and the AI's long-term value.

Key insights

Custom AI coaches can transform self-reflection and productivity by externalizing internal monologues and fostering playful engagement.

Principles

• Engagement and playfulness enhance AI's effectiveness as a development tool.
• Actively challenging AI outputs helps maintain a grasp on reality.
• AI's core instruction should prioritize strengthening human social interactions.

Method

Build a custom AI coach by having the AI interview you to define its personality and purpose. Use custom instructions and background files (e.g., past reflections, articles) for context. Implement a recursive loop to summarize past interactions and feed them back into the AI's knowledge base.

In practice

• Use AI to interview yourself for custom instruction content.
• Incorporate a "grip protocol" to elicit constructive criticism from AI.
• Design AI to return you to human interaction.

Topics

• Custom AI Coaches
• AI Personalization
• Human-AI Interaction
• Prompt Engineering
• Recursive AI Learning

Best for: AI Chatbot Developer, Prompt Engineer, AI Student

Related on AIssential

• How AI chatbots keep you coming back for more — AI chatbots foster addiction through immediate, personalized, and constant availability.
• How to Learn AI With AI — Effective AI learning now requires treating AI as a collaborative build partner, not just a tool for tutorials.
• Inside Nathan's Second Brain: Daniel Miessler, Security Expert & Creator of PAI, Audits My AI Setup — A robust personal AI infrastructure integrates deep context with autonomous agents for enhanced productivity and security.
• Young people's perceptions and recommendations for conversational generative artificial intelligence in youth mental health — Young people prioritize transparency, human connection, and personalized, safe integration of genAI chatbots in mental health.
• ChatGPT Power User Training — Mastering ChatGPT involves systematic prompt engineering, model selection, personalization, and responsible AI practices.
• One person's best AI session vanishes the second they close the tab. Grab the 3 prompts that make it your team's. — Public AI interactions foster team learning and knowledge transfer by exposing operational details.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Humans + AI.