CASE STUDY

SaaS

WebApp

Turning engineering heavy agent building process into a

Product led Agent building experience

STAKEHOLDERS

2x Software Engineers

AI Engineer

Product Manager

MY ROLE

Product Designer

PROJECT DURATION

1 month (yes we are fast)

LAST UPDATED

20th February, 2026

CONTEXT

Nolana builds AI support agents for Insurance and Banking
that do more than just answering questions.

Can you change my credit card payment date to 28th of every month going forward?

Fetched customer info from CRM

Read knowledgebase SOP

Read knowledgebase SLA

Executed Procedure Change billing date

Sure! Just so you know that you can change the billing cycle only once every 90 days. Happy to proceed?

PROBLEM

How we built these agents currently was extremely engineering dependent and was never built to scale as a product experience

USER RESEARCH

I reached out to users and they said

1

I simply forget to login and submit updates

2

Signing in every time I have to submit updates is too much work

3

I just don’t see myself paying just for this usecase

HOW MIGHT WE


Ask for follow-ups (for everything, not just standups) that live where work already happens so teams can set it and forget it?

COMPETITOR BENCHMARKING

I started with borrowing patterns from products that already worked

EXPLORATION

I used AI to prototype the interaction design first to speed up my backend developer. Used Gemini, Magicpath and Figma make. This helped me disambiguate the problem and invited ton of collaboration

USED SEVERAL TOOLS TO EXPLORE DIFFERENT APPROACHES

This will help the AI craft a slack message with deadline

DESIGN

Some tradeoffs that we had to make to arrive at the final design

DESIGN

Final flow. To arrive at this, I asked a lot of questions

  1. Does the order of the flow and information architecture make sense?

  2. Is the UI copy unambiguous and clear?

  3. Can I cut any steps that are absolutely not necessary?

  4. Are the defaults good enough?

OUTCOMES

Happy users and better stickiness

LEARNING

  1. The only way to influence your team is to do the “work” around the work

  1. Stop waiting for clarity and start creating it

  1. A picture is worth a 1000 words, a prototype is worth 1000 meetings

  1. Iterate with intent

Say hello 👋

designedbyhari@gmail.com

© 2025 by Hariharan Ramesh

Never stop iterating

Say hello 👋

designedbyhari@gmail.com

© 2025 by Hariharan Ramesh

Never stop iterating

CASE STUDY

SaaS

WebApp

Turning engineering heavy agent building process into a

Product led Agent building experience

STAKEHOLDERS

2x Software Engineers

AI Engineer

Product Manager

MY ROLE

Product Designer

PROJECT DURATION

1 month (yes we are fast)

LAST UPDATED

20th February, 2026

CONTEXT

Nolana builds AI support agents for Insurance and Banking
that do more than just answering questions.

Can you change my credit card payment date to 28th of every month going forward?

Fetched customer info from CRM

Read knowledgebase SOP

Read knowledgebase SLA

Executed Procedure Change billing date

Sure! Just so you know that you can change the billing cycle only once every 90 days. Happy to proceed?

PROBLEM

How we built these agents currently was extremely engineering dependent and was never built to scale as a product experience

USER RESEARCH

I reached out to users and they said

1

I simply forget to login and submit updates

2

Signing in every time I have to submit updates is too much work

3

I just don’t see myself paying just for this usecase

HOW MIGHT WE


Ask for follow-ups (for everything, not just standups) that live where work already happens so teams can set it and forget it?

COMPETITOR BENCHMARKING

I started with borrowing patterns from products that already worked

EXPLORATION

I used AI to prototype the interaction design first to speed up my backend developer. Used Gemini, Magicpath and Figma make. This helped me disambiguate the problem and invited ton of collaboration

USED SEVERAL TOOLS TO EXPLORE DIFFERENT APPROACHES

This will help the AI craft a slack message with deadline

DESIGN

Some tradeoffs that we had to make to arrive at the final design

DESIGN

Final flow. To arrive at this, I asked a lot of questions

  1. Does the order of the flow and information architecture make sense?

  2. Is the UI copy unambiguous and clear?

  3. Can I cut any steps that are absolutely not necessary?

  4. Are the defaults good enough?

OUTCOMES

Happy users and better stickiness

LEARNING

  1. The only way to influence your team is to do the “work” around the work

  1. Stop waiting for clarity and start creating it

  1. A picture is worth a 1000 words, a prototype is worth 1000 meetings

  1. Iterate with intent

Say hello 👋

designedbyhari@gmail.com

© 2025 by Hariharan Ramesh

Never stop iterating