Mersive Q1 2023🐣- Q2 2024 🪦
The Mersive Story
For more than a decade I had the belief that most of us need a personal coach for the rest of our lives just like we need personal trainers for our physical fitness.
With the rise of reliable LLMs and specifically the launch of Chatgpt at the end of 2022 I became convinced that the moment arrived to create it.
December 2022. The hypothesis was:
Some people are 120% self-motivated, they do not need a personal trainer, support or anything of that nature, but there’s the rest of us we need the PTs to make us sweat on a regular basis.
A Personal trainer is there for accountability and sharing some best practices (exercising with correct form, targeting different muscle groups, warming up etc) BUT you decide what type of trainer you want the goals objectives and focus (mobility, strength, lifting X weight etc) and choose the PT with the methodology that works best for you.
Similarly, for coaching we should pick our methodology and objectives and the style that works for you. For that, we have a pseudo-infinite bank of material to work with. All the books that you read and the ideas you like and want to implement. Choose your own favorite book or any body of content -BOC- (could be 10 podcasts or 30 essays, etc etc)
LLMs are good for I/O BUT we should help model the world for them so our plan was to build an game engine similar to what a game AI would be to record and model different element of the real world and then use that in conjunction with the BOC of your choice.
The Product v0.1: Creating a personal coach
This is a whiteboard from early 2023 showing the components of the product at a high level:
Body of content [BOC]: this is the book or other content that the user picks to adopt and then the coach uses as a map.
From the BOC we extract what a general MOP is:
Mission the overall north star that the BOC is pointing you towards.
Objectives: the specific goals you want to achieve
The path: the sub-milestones to hit on your way towards achieving those objectives
This becomes similar to a real world or game map of the landscape of the BOC, you can navigate it in any dimensions. Sometimes there are constraints like sequencing, a milestone has to be achieved before proceeding to a next stage. So there’s a balance between freedom of “movement” and BOC derived constraints (dependencies/gating items etc)
BOC is queried through semantic search to answer use chats/questions or “I don’t know”
User model: This is the collection of data points (Qual and Quant) that we have about the user and use to help them.
There’s a minimum viable amount of info we can go with and we keep enriching it as we go, no intense long onboarding as it creates a bad first impression and makes the convo mechanistic.Assumed: start with some assumptions then check them
volunteered: things the user mentions during onboarding or
Answered: specific essential information/context: we just ask the user for them.
The User model is ALWAYS updated, every interaction updates it:
New info from user
User response time/speed
Tone
And Deltas between all these things in different contexts.
EQ engine: This is a fancy name for a set of logic and heuristics that takes as the input the next milestone the user needs to achieve, the user state, the general context and creates the custom prompts that feed to the llm to handle the conversation to approach the next milestone. I believe In the gaming world it is called a quest system or mission planner.
Coaching Styles and frameworks
Coaching Frameworks
Did a bit of research about the methodologies the coaching world uses, learned a bit more about the GROW, OSCAR. CLAIRE frameworks.
They all basically boil down to:
Know current reality, understand the delta between reality and Goal and Work on closing that delta.
Coach Values
Integrity: I keep my commitments, and take responsibility for my actions.
Honesty, make intentions clear
Commitment to client’s success
Empathetic/Understanding
Adaptability
