---
title: "Designing AI coaching around the manager’s day."
description: "A management coaching company wanted an AI companion to support its management coaching. We worked on the product experience and architecture for a Slack-based assistant, focusing on how to make it relevant enough for people to keep using."
url: https://coyotiv.com/work/ai-coaching-companion/
---

1. [Work](https://coyotiv.com/work/)
2. [AI coaching companion](https://coyotiv.com/work/ai-coaching-companion/)

# Designing AI coaching around the manager’s day.

A management coaching company wanted an AI companion to support its management coaching. We worked on the product experience and architecture for a Slack-based assistant, focusing on how to make it relevant enough for people to keep using.

[Book a call](https://coyotiv.com/work/ai-coaching-companion/#book) [See all work](https://coyotiv.com/work/)

Client

AI coaching companion

Sector

Management coaching and learning

Our role

Product discovery, AI architecture, and interaction design

Today

A proposed product approach, from about three months of discovery and architecture

The story

1. [A coaching chatbot people weren’t returning to.](https://coyotiv.com/work/ai-coaching-companion/#a-coaching-chatbot-people-werent-returning-to)
2. [A clearer design for a coaching companion.](https://coyotiv.com/work/ai-coaching-companion/#a-clearer-design-for-a-coaching-companion)

## A coaching chatbot people weren’t returning to.

The company coached middle managers through human coaching sessions and its own learning platform. An AI component could extend that support into the manager’s everyday work.

The central problem was engagement. Participants were not returning to the chatbot often enough. Responses that felt unhelpful, repetitive, or disconnected from the person’s situation could end the conversation.

The assistant needed to understand the coaching context and offer a useful next step without making the participant do too much work.

## A clearer design for a coaching companion.

The work produced product concepts and an architecture for a more contextual Slack companion: one that could connect learning and coaching activity, offer concise prompts, and accept different forms of feedback.

The engagement centered on discovery and architecture. The weekly prompt and several interaction mechanisms were explored as design concepts; the outcome described here is the proposed product approach.

How it went

## Design for the moment someone needs support.

1. Context  
### Bring the coaching context into the conversation  
We explored how the assistant could draw on coaching sessions, challenges recorded on Miro boards, and learning activity such as lectures and quizzes. The aim was to connect a manager’s question to what they had already learned and were trying to apply.
2. Interaction  
### Make the interaction easier  
We designed alternatives to open-ended typing: simple choices, buttons, yes-or-no responses, and voice messages in Slack. These formats gave participants different ways to share progress or ask for help.
3. Return  
### Create useful reasons to return  
We developed a concept for a short weekly message that would prompt action or reflection. Follow-ups could relate to a real situation, such as a difficult conversation with a team member or a coaching method the manager was practicing.
4. Feedback  
### Define how the assistant would use feedback  
The architecture explored maintaining a participant profile over time, interpreting new feedback, and connecting it to their challenges and recommended actions. New concerns could also become material for the human coach.
5. Measures  
### Choose measures tied to participation  
We identified engagement measures around whether people responded, which kinds of interaction prompted a response, and how often the assistant had to remind them. These would help evaluate the proposed experience.

The result

## A clearer design for a coaching companion.

Product concepts for a more contextual Slack companion: concise prompts and different forms of feedback.

Concepts

A proposed architecture connecting learning and coaching activity to the Slack experience.

Architecture

More work

## More work.

[See all work](https://coyotiv.com/work/)

Personalized products and fulfillment

### [A critical application, ready to run the business.](https://coyotiv.com/work/thefreshener/)

Months of continued development added features and integrations, allowing the company to expand its operations to new product types.

TheFreshener

HR technology and hiring

### [A hiring workflow that had outgrown a single agent.](https://coyotiv.com/work/klareda/)

Klareda could take on larger hiring use cases, with the work divided across agents and their steps available for review.

Contact

## Book a call.

Free, 30 minutes, with an engineer. Tell us what you are working on.

- Startups Free architecture review
- Enterprises AI review
- School Apply for the next cohort
[hello@coyotiv.com](mailto:hello@coyotiv.com)