Making Slack Less Overwhelming


This project got it’s start when browsing product review site’s Slack page. Lot’s of people were frustrated with the fact that over the past few years Slack has gotten really overwhelming.

Distracted and overstimulated employees can't do their work effectively. Failing to address this issue could cause businesses to sour on the platform altogether, leading to lost subscribers and revenue.

Product Designer
Spring 2023
12 weeks
Product Designer (Me)
Slack Sr. Engineer (Consulted)
ML Engineer (Consulted)
Adobe Suite
Google Workspace
Industry Trends
Competitive Analysis
SWOT Analysis
Heuristic Evaluation
Problem Statement
User Interviews (x5 Users)
Affinity Map
Story Maps
Competitive Solution Analysis
Flow Map
Usability Tests (x5 Users)
Final UI Screens
High Fidelity Prototype
I led the full design of this project and produced all deliverables.

Get caught up to speed on your channels up to 100x faster. Goodbye information overwhelm!

Slack hero animation

The medium is the message: Looking for a big challenge to tackle

One of the things I’ve always been fascinated by is how changing communication technologies shape culture. One of my favorite thinkers Marshall McLuhan has this famous quote, "The medium is the message." This essentially means that the content of any piece of communication is always secondary to the actual tools with which its being delivered to shape culture, people and ideas.

Back in the day, the invention of the printing press radically changed the world as did the radio and television in later centuries. What drew me to this problem was the potential magnitude of it as well as the opportunity to address the issue of healthy and productive use of technology in our everyday lives.

illustration of man overlooking mountain
From a personal standpoint, this problem seemed pretty massive to tackle.

Slack has become a distraction machine

20% of the work week searching for info

Average amount of time knowledge workers spend looking for internal info or tracking down people to help with specific tasks.

200 messages a week at large companies

Average amount of messages sent by
Slack users at large companies. Power users are sending out more than x1000 per day.

Getting the lay of the business landscape & figuring out where my knowledge blind spots were

Again and again the theme that kept popping up in user comments was that they found Slack to be both really overwhelming as well as distracting them from their actual work with all of the messages, channels and threads there are to keep track of.

There was a business opportunity here. Distracted and overwhelmed employees aren’t productive workers. There was a real threat that users could abandon the platform altogether, leading to lost revenue.

Next steps would be conducting a SWOT analysis, competitor analysis, industry trends, and heuristic evaluation. I specifically chose these methods of discovery because they were a quick way to get needed context on the business side of the problem as well as potential areas for improvement.

Discovery methods

Where are some areas that weaknesses / threats could combine with opportunities?
SWOT analysis
There is a lot of conversation online around "always on" work culture online. Slack's instant messaging style communication creates a lot of pressure for people to respond to things immediately.
AI tech is working its way into all sorts of products. Direct competitors like MS Teams is making it a priority.
What are some potential avenues of innovation in relationship to the competition?
Competitor analysis
Competitor products are leaning into AI hard. There's a risk of being left out of the game.
Slack uses a lot more 3rd party plugins than its strongest competitor MS Teams.
What are some patterns in business and society that could help frame this problem?
Industry trends
A majority of office workers want some sort of communication tool that's not instant messaging based.
Hybrid work continues to grow, meaning teams can be spread out all over the place.
Where specifically is there room for improvement when looking at the software?
Hueristic evaluation
Cognitive Overload: There is a lot of text populating the screen at any one time and it moves very quickly.
Simplicity and Efficiency: It takes a lot of trial and error to really learn the ins and outs of the software to use it effectively.

“It quickly gets overwhelming within a busy workplace. Setting up channels for specific projects/topics or direct messages (DM's) for specific conversations helps organize concerns, but that can get unwieldy. They added favoriting channels and people, in essence you see those new messages first, but I find that no matter what I do, it becomes a chore to keep up with everything.”

- Jesse K. / comment

ChatGPT is announced for Slack. But what does that mean?

Great! I felt like I was on to a solid lead. Then the mixed emotions hit. An article pops up in one of my feeds mentioning that Chat GPT is being planned for integration with Slack and might be looking to address this very problem.

What would this look like though? My thinking moving forward was this. AI is worth taking a look at, but I shouldn't assume its a solution to a problem I haven’t fully explored yet.

I wrapped up discovery with this guiding statement.

How might we help users of Slack feel more empowered and less overwhelmed when trying to retain important or actionable information?

Activities & outputs

SWOT Analysis
Industry Trends
Competitive Analysis
Heuristic Evaluation
Framing the Problem

Lost in the woods: Is this problem too systemic?

illustration of lone man walking in forest
I felt pretty lost. How would I be able to find a path forward?

To get a better handle on the problem, I interviewed x5 Slack users. The overall goal was to get specific and expand on what I'd learned in discovery and also uncover any other work habits, processes or coping mechanisms people were using.

In choosing my interviewees I wanted to get a broad range of people with different job title types. This would ensure that whatever solution came down the pipe later on it was catered to the collective needs of an entire organization.

Here's what users had to say.

“From like a senior leadership level, I would have just liked kind of daily reports on each channel. I guess more like issues reporting or, anything in the channel that like directly related to the project, I wish there was a better way for Slack to kind of report back to me at the end of the day... things that I needed to know because of everything that was happening within Slack. I don't know if there's a great way to do it which is probably why they haven't come up with it yet."

- Erin T. / Interviewee

"l usually can't use Slack at the same time I’m actually doing my work. So I'll just have to just silence it. Or don't even silence it. I just, check in on Slack and I do my work, and I check in on Slack.

- Ben E. / Interviewee

Looking for patterns in the interview data

Affinity map example 1
I had assumed that users were saving information within Slack. This turned out not to be true.
Affinity map example 2
60% of interviewees specifically mentioned that they generally take stock of what they need to do and get caught up to speed in the morning and at the beginning of each week.
Affinity map example 3
All said and done interviewees problems largely boiled down into one of these five categories.

Well I learned a lot of specifics, but I still don't know which direction to go.

There was still no obvious direction from here: I knew I needed some outside expert help to break the stalemate and gain some much needed perspective.

AI is something users are experimenting with: This ties into a huge business opportunity to keep up with the competition (like MS Teams).

I needed to tweak my guiding statement: I had a couple of faulty assumptions built in that turned out not to be true.

Old: HMW
How might we help users of Slack feel more empowered and less overwhelmed when trying to retain important or actionable information?
New: HMW
How might we help Slack users feel more empowered and less overwhelmed in their ability to interact with important information as part of a team?

Focus on the team aspect: This problem needs to be approached both from an individual AND from a team standpoint. There are many people involved that contribute to the issue, not just a single isolated individual.

Its not really about “saving” information: The previous statement had a wrong assumption that this problem was about “saving” information. Interviews didn’t support this.

Activities & outputs

Interviews x5 Users
Affinity Maps
Reframing the Problem

The tricky part: Trying to narrow project scope (but not too much)

Sketching and going wide with lots of ideas is one of my superpowers. Feeling energized now!

This next part was tricky, because I was trying to do seemingly opposing things at once.
Narrowing the project focus based on what I’d learned so far with story maps and jobs to be done was objective one. Exploring ideas widely with sketching and a competitor solution analysis was objective two.

To strike a balance, I ended up doing two different story maps (instead of the usual one) based on insights I’d learned from user interviews. This would set the stage and allow me to explore more territory while sketching through ideas to ensure I was taking the right approach.

Story maps: Leaving the scope open wide for exploration

I mapped out what I learned from users to explore how that might translate to features.
Story Map 1
This exercise served its purpose of exploring how user insights could turn into actual features while also leaving the scope open enough for exploration later on.
I wanted to cover all of my bases, so a secondary "back burner idea" map was created.  
Story Map 1
I wanted to make sure I had an alternate direction to go in if I needed to switch gears later on.

Sketching like mad: Exploring all the angles

All said and done I looked at 7 different design directions.

1. Channels Smart Sorting

2. Channels AI Summary Inbox

3. Focus Mode AI Summary

4. AI Channel Summary with Action Items

5. Grouped Channel Dashboard

6. Interactive Channel Summary Timeline

7. Huddles Meetings Transcriptions

Channels Smart Sorting
Sketch 1
Slack already does this but maybe we can give users even more control over how channels are sorted.
Channels AI Summary Inbox
Sketch 2
Maybe we can show users cards in a scrolling feed that use AI to surface relevant info from their most important channels.
Focus Mode AI Summary
Sketch 3
100% of interviewees use some sort of time blocking or focus mode when they work. Maybe we can use AI to show them a summary of what they missed while they were away.
AI Channel Summary with Action Items
Sketch 4
40% of users mentioned that having some sort of recap list of action items is really important to them. It helps distill lots of info down into what they can do right now to move forward on a project.  
Grouped Channel Dashboard
Sketch 5
Maybe users can group channels together into a dashboard that gives insight into what's going on in those channels in more easy to handle bite sized chunks.
Interactive Channel Summary Timeline
Sketch 6
Instead of reading through an entire channel, can we use AI to summarize threads into a way more easily digestible feed?
Huddles Meetings Transcriptions
Sketch 7
The problem with huddles (Slack's version of video meetings) is that there is no record of what was discussed which might have important info. Maybe we include transcriptions of video conversations.

Closing in on a path & talking with a Sr. engineer friend at Slack

After doing my due diligence and exploring lots of different options, the decision was made to pursue an AI based solution. The reasoning was simple. It had the highest upside from both a potential business AND user impact perspective.

I knew I needed more input though so I got in touch with an old college friend who was an engineer at Slack and showed him two quick ideas I’d wireframed up. I was trying to learn two things.

Q. How feasible are these ideas to actually build?
A. No major red flags raised

Q. Did he have any additional insight into how to make these concepts better?
A. Yes, maybe think about summarizing unreads and huddles transcripts. (Slack’s version of Zoom)

Activities & outputs

Story Maps
Competitive Solution Analysis
Flow Map

Catching the AI wave with a little more help from my techie friends

illustration of 3 people on a mountain
Sometimes asking for help along the way is the best way to move forward!

I then ran x5 user tests. I was trying to find out three main things.

1. Could users understand what the feature set was and what it was supposed to do?

2. How useful would users find this feature set to their everyday workflows?

3. Did users have any additional insights into how this feature set might fit their needs better?

User test insights

Action items:
A must have

60% of participants were choosing to include action items as what they wanted to see returned in a channel summary.

Shareable content:
It's a team sport

The lone exec. tester felt strongly that whatever info these summaries returned, it needed to be easily shareable with others on a team.

Orienting the user:
Clear explainer screens

60% of interviewees had trouble understanding what the feature orientation pop up screens were trying to show.

Renaming the summary: Custom tools

40% of interviewees were not satisfied with where in the process you could rename summaries. It was also not obvious you even could rename summaries.

Easily scannable inbox: Surfacing info

One user mentioned that when looking at the summary titles there wasn’t much info there to help him. He wanted easily scannable info to help.

Summary complete:
A nice touch

60% of users mentioned that they appreciated the fact that the system alerted them to the fact that their channel summary was complete.

A technical deep dive with a machine learning engineer

I still had one burning question I had yet to answer that could make or break this feature set.
Could AI summarize an entire channel or would a better approach be only trying to summarize Slack threads within a channel?

I needed to find out more, so I spent a few minutes talking through some of the specifics of how these AI models work with one of my test users who happened to be a freelance machine learning engineer.

As a result of that conversation, the decision was made to only summarize threads within a channel. This would be much easier and would require less time, effort and money to implement.


The home stretch: Sticking to threads

illustration of 3 people on a mountain
I could see the final designs starting to take shape!

AI summarization of channel threads

Summarize up to x5 channels at a time (only the threads of each within a set time period) with the click of a button.

Slack hero animation

Action items

Actionable items from the summary are extremely important to users, so they are pre-selected by default.

AI summary example animation

Summary complete alert

While you are waiting for your summary to finish, the left side panel lets you know its working. When it’s done you get a standard Slack pop up alert.

AI notification example animation

AI summary explainer pop-ups

Since this is a new feature, users need to quickly understand what it does and how to use it. A simple pop up does the trick.

AI modal example animation

Shareable insights

Slack is about teamwork. Being able to share information from summaries with others helps everyone do their work more efficiently.

AI share summary example animation

Summary inbox keywords

Keywords let you quickly scan your inbox for a past summary you may have created. You need to be able to have some context for what you are looking for.

AI summary example animation

Activities & outputs

High Fidelity Desktop UI
High Fidelity Prototype

Giving people their sanity back: Calming the information storm

Get caught up on a channel up to 100x faster

Rather than having to manually browse through threads to get caught up to speed, you can now summarize those threads with the click of a button and save that info for later. This has the potential to drastically improve worker productivity.

Slack stays relevant in the AI arms race

This is especially important as Microsoft Teams is implementing lots of AI time savers into their products. Its important for the success of the business to wisely incorporate this emerging technology.

Encourages the use of threads in channel

If users know that putting their comments into the proper threads makes it easier to summarize them later they may be more inclined to keep things tidy in threads, in channel.
(More testing would be needed.)

Users are less likely to abandon the platform

If Slack makes employees more productive, management will have little reason to look elsewhere for their internal communication needs.
A user win is a win for business goals.

“I immediately see how this would impact me, I might be gone for two or three days.
I've got 14 channels that have 50 messages, each all with threads in those in those channels. So having a tool that can capture the action items, summarize and then capture the action items that are specific to me, like, Dude... I could see raising VC capital for this 100%. Like you could raise money for this.”

- Andrew T.


Well would you look at that. Slack is actually building this thing!

Fast forward a few months. To my complete surprise I stumbled across this article on my Google feed one day.  Slack would be building a feature very similar to the one I had just built!

Slack AI summary article

Lessons learned & areas for improvement

Do just enough research to move on: This is a difficult thing to master but is key to balancing speed and accuracy. I tried to do this throughout.

Leave enough margin time for interviews: When scheduling interviews or user tests with people make sure I leave extra time in case someone is a no show or needs to reschedule. This happened a few times on this project but didn’t significantly mess up my timeline.

Future roadmap

These are some things I’d look to continue to iterate on in the future with this feature.

Inclusion of "Huddles" in summaries

Huddles are kind of Slack’s version of Zoom calls. Including text transcription summaries of these calls was something I had talked about with my engineer friend but didn’t make it into this first version of the feature.

This could be an interesting avenue to continue down. Often times clarifying conversations to work conflicts happen on video calls.

Look to users to help improve the AI algorithm

One of the things my machine learning engineer friend mentioned was an avenue I might explore would be UI that would let users help improve the algorithms by letting them give feedback on how accurate or not accurate summary results were.

This is something I could test with to improve effectiveness and accuracy of the feature.

I'd love to chat about how I might align with your team's goals!
Feel free to email or connect on Linkedin.

Check out my other work!

Enhancing Miro's File Management
View Project >