Can users talk to my app in real-time and get their doubts and queries resolved? How should we guide users to complete key actions without asking for support?

Plotline | 2025

Plotline | 2025

Conversational AI builder for consumer apps

Conversational AI for consumer apps //
Can AI actually help users in-context?

Every customer has a unique set of aspirations, sensibilities and expectations from consumer apps. Capturing the intent and assisting users at the right time is what every app aims for, but as B2C apps grow more complex, users struggle to complete key actions.

Unique conversations

Unique conversations

5M+

5M+

Avg uplift in conversions

Avg uplift in conversions

~20%

~20%

Avg reduction in support tickets

Avg reduction in support tickets

~30%

~30%

Improvement in discovery

Improvement in discovery

~40%

~40%

CONTEXT

CONTEXT

CONTEXT

What does Plotline do?

What does Plotline do?

What does Plotline do?

Plotline helps growth teams at consumer apps with onboarding, activation, adoption and retention use cases by letting them build elements like stories, in-line widgets, floating buttons, spotlights, quizzes, scratch cards and much more - without code. We have built a platform for marketers to enable them to nudge the right user at the right time to perform the intended action

Why is Plotline creating in-app conversational agents?

Why is Plotline creating in-app conversational agents?

Plotline partners with leading consumer apps like Upstox, CoinDCX, Niyo, and BharatPe to push the boundaries of in-app user experience. We found that drop-offs in complex journeys are a major growth blocker. This led us to explore how understanding user context can help people complete tasks, access information, and track requests.

// CONTEXT //

Enabling marketers to capture user intent and take right actions in the moment, at a 1:1 level

Enabling marketers to capture user intent and take right actions in the moment, at a 1:1 level

Having learnt the user behaviour across a multitude of consumer apps from gaming to finance to e-commerce, product and growth teams at these apps presented us with these problems.

App usage has a learning curve - FAQs and delayed support is inadequate

App usage has a learning curve - FAQs and delayed support is inadequate

Current In-app interventions are static - one-dimensional. No 2-way conversations

Current In-app interventions are static - one-dimensional. No 2-way conversations

Missed cross-sell opportunities due to delay in capturing user intent

Missed cross-sell opportunities due to delay in capturing user intent

Let's take an actual user journey - applying for a loan in a fintech app.

1.

1.

User starts the loan application process

User starts the loan application process

2.

2.

Has queries about the loan and doesn't build enough confidence

Has queries about the loan and doesn't build enough confidence

3.

3.

Raises support ticket or sales team reaches out - delay of ~1-2 hours on avg for resolution

Raises support ticket or sales team reaches out - delay of ~1-2 hours on avg for resolution

4.

4.

Users drop-off and only those who feel confident enough apply for loan

Users drop-off and only those who feel confident enough apply for loan

This same journey with a real-time intent recognition and communication system

1.

1.

User starts the loan application process

User starts the loan application process

2.

2.

Has queries about the loan and doesn't build enough confidence

Has queries about the loan and doesn't build enough confidence

3.

3.

Discovers missing information through context-aware two-way conversations

Discovers missing information through context-aware two-way conversations

4.

4.

User feels confident enough and applies for loan without delay

User feels confident enough and applies for loan without delay

// PROBLEM DISCOVERY //
// PROBLEM DISCOVERY //

What would these conversational agents do inside the app? What should we design for?

What would these conversational agents do inside the app? What should we design for?

We asked product and growth teams at these apps to know where drop-offs were happening in their apps and which of these avenues could be best solved by conversational agents.

Thus we have to design an agent that enables all of these use cases in a totally brand-safe and empathetic way

// PRIMARY RESEARCH //
// PRIMARY RESEARCH //
Understanding existing workflows, uncovering any latent aspirations and concerns for a conversational AI agent inside their app
Understanding existing workflows, uncovering any latent aspirations and concerns for a conversational AI agent inside their app

User interviews

User interviews

To understand their challenges better, we started 1:1 semi-structured interviews which gave us insights into user needs and pain points, expected experiences from end users and what is the current experience provided to them

To understand their challenges better, we started 1:1 semi-structured interviews which gave us insights into user needs and pain points, expected experiences from end users and what is the current experience provided to them

  • What are the main customer interactions within your app that could benefit from AI-powered conversations (e.g., customer support, product recommendations, order tracking)?

  • How do you currently gather customer feedback, troubleshoot issues, and upsell products? Would a conversational agent be suitable for any of these?

  • What features would define an ideal conversational AI for your app (e.g., multilingual support, personalization, deep product knowledge)?

    • How do you estimate the agent's impact in your app?


  • How important is AI-human handover in complex cases? What is your expectation of bot vs. human interactions?

  • What are your top concerns about integrating conversational AI agents? (Options: technical complexity, security and privacy, customer trust, handling edge cases, impact on brand, regulatory compliance)

“Over the past 2 years, we have seen that the time taken to resolve support tickets is inversely proportional to lifetime value of our customers"

“Over the past 2 years, we have seen that the time taken to resolve support tickets is inversely proportional to lifetime value of our customers"

ALETHIA TAN

ALETHIA TAN

SVP, Growth, Kredivo Indonesia

SVP, Growth, Kredivo Indonesia

“An agentic experience inside my app should aid the overall discoverabilty and usage. It should intelligently understand when it is needed and what it should help with”

“An agentic experience inside my app should aid the overall discoverabilty and usage. It should intelligently understand when it is needed and what it should help with”

Rishabh

Rishabh

Growth team, Dream11

Growth team, Dream11

Key findings from interviews

Key findings from interviews

From the outset, we were aware that this is quite a big paradigm shift in consumer apps as this transforms the app from one-way communication to a two-way context aware communication with end users. There were a lot of concerns from marketing/product leaders we talked to and thus I categorised all the concerns emerging from the primary and secondary research under 3 major themes

  • How will my agents learn?

  • How will my agents interact with my end users

  • How will I orchestrate handovers between my agents and to human support when needed?

How will my agents learn?

How will my agents learn?

  • Need to adapt to all the latest policies, terms and conditions in real-time to not answer any query with stale info

  • Should learn from feedback loops and every customer query to refine itself.

  • Must balance personalization (recommendations, offers) without overwhelming the user.

  • Must handle multilingual support for diverse user base.

How will I test my agent?

How will I test my agent?

  • Key use cases: onboarding, order placement, product discovery, issue resolution, refunds, and upsells.

  • Tone and empathy crucial to earning trust.

  • Nudges must be contextual—embedding upsells into dialogue rather than push notifications.

  • Smooth AI-to-human handover required for complex or sensitive issues.

How will I orchestrate my agents' behaviour?

How will I orchestrate my agents' behaviour?

  • Integrations with order tracking, payment systems, CRM, and backend APIs are critical.

  • AI must log interactions so humans can pick up without repeated context.

  • Need workflows for feedback capture (CSAT via natural conversation instead of surveys).

  • Escalation rules: when to switch from bot to human, how to route correctly.

Ensuring a structure that scales

Ensuring a structure that scales

Since our users treat different use cases separately, I thought of emulating this and to allow them to create an agent for each use case. To solve every use case in a modular way, every agent inside the app would have 4 configurations - Knowledge, Tools & actions, brand and communication along with optimising for product goals

Since our users treat different use cases separately, I thought of emulating this and to allow them to create an agent for each use case. To solve every use case in a modular way, every agent inside the app would have 4 configurations - Knowledge, Tools & actions, brand and communication along with optimising for product goals

Since our users treat different use cases separately, I thought of emulating this and to allow them to create an agent for each use case. To solve every use case in a modular way, every agent inside the app would have 4 configurations - Knowledge, Tools & actions, brand and communication along with optimising for product goals

Configuring an agent - snapshot of the core UX journey

Configuring an agent - snapshot of the core UX journey

Setting up your agents

Setting up your agents

Since the whole concept of having an AI agent take care of your users' needs, aspirations and frustrations was new, I built a few pre-configured templates to help the marketers get started and explore in a low friction way.

Since the whole concept of having an AI agent take care of your users' needs, aspirations and frustrations was new, I built a few pre-configured templates to help the marketers get started and explore in a low friction way.

Since the whole concept of having an AI agent take care of your users' needs, aspirations and frustrations was new, I built a few pre-configured templates to help the marketers get started and explore in a low friction way.

Measuring success for this flow

Measuring success for this flow

It is very important to track the usability of a completely new product added to our core dashboard. Thus, we are closely tracking the performance.

It is very important to track the usability of a completely new product added to our core dashboard. Thus, we are closely tracking the performance.

It is very important to track the usability of a completely new product added to our core dashboard. Thus, we are closely tracking the performance.

Task success rate - Creation

Task success rate - Creation

Currently ~ 57%

Usability support ticket ratio

Usability support ticket ratio

Currently ~ 45%

Time to first value

Time to first value

Currently ~ 8 minutes

How will my agents learn?
Balance automation with a human-like and a dynamic source of truth - Konwledge base for your agents and iterative learning from its own conversations

How will my agents learn?
Balance automation with a human-like and a dynamic source of truth - Konwledge base for your agents and iterative learning from its own conversations

  1. Knowledge base

Collection of data points that the agent can retrieve as required

Collection of data points that the agent can retrieve as required

  1. Feedback from marketers

Marketers rate responses and give addition feedback in blind testing

Marketers rate responses and give addition feedback in blind testing

Missed cross-sell opportunities due to delay in capturing user intent

Missed cross-sell opportunities due to delay in capturing user intent

A dynamic, highly relevant knowledge base is essential for any agentic system to train and learn.

A dynamic, highly relevant knowledge base is essential for any agentic system to train and learn.

A dynamic, highly relevant knowledge base is essential for any agentic system to train and learn.

How will my agents interact with real users?
Let marketers simulate real conversations and build trust on the agent

How will my agents interact with real users?
Let marketers simulate real conversations and build trust on the agent

Testing each agent

Testing each agent

Here’s a snapshot of how we can simulate the entire conversation experience, rate previous conversations and help the agent learn exactly how it is supposed to communicate with your users.

Here’s a snapshot of how we can simulate the entire conversation experience, rate previous conversations and help the agent learn exactly how it is supposed to communicate with your users.

Here’s a snapshot of how we can simulate the entire conversation experience, rate previous conversations and help the agent learn exactly how it is supposed to communicate with your users.

Here’s a snapshot of how we can simulate the entire conversation experience, rate previous conversations and help the agent learn exactly how it is supposed to communicate with your users.

Here’s a snapshot of how we can simulate the entire conversation experience, rate previous conversations and help the agent learn exactly how it is supposed to communicate with your users.

Here’s a snapshot of how we can simulate the entire conversation experience, rate previous conversations and help the agent learn exactly how it is supposed to communicate with your users.

How will I orchestrate my agent's behaviour?
Giving enough context and situation handling directions to the agent

How will I orchestrate my agent's behaviour?
Giving enough context and situation handling directions to the agent

Context broken down into communication styles, conversation guidance & escalation and hand-overs

Context broken down into communication styles, conversation guidance & escalation and hand-overs

Breaking down the context into three parts that form the overall guidance mechanism for the agent in any situation helped reduce the cognitive overload for the users and build better context prompts for the system

Breaking down the context into three parts that form the overall guidance mechanism for the agent in any situation helped reduce the cognitive overload for the users and build better context prompts for the system

Breaking down the context into three parts that form the overall guidance mechanism for the agent in any situation helped reduce the cognitive overload for the users and build better context prompts for the system

Making sense of it all
Setting up iteration and improvement for agents

Making sense of it all
Setting up iteration and improvement for agents

Agent performance broken down into actionable intelligence

Agent performance broken down into actionable intelligence

Started by focusing on core metrics such as conversation volume, goal completion rate, and human handoff rate (when users are escalated to live agents). Real-time conversation logs, knowledge and tools performance also help in targeting the agent better.

Started by focusing on core metrics such as conversation volume, goal completion rate, and human handoff rate (when users are escalated to live agents). Real-time conversation logs, knowledge and tools performance also help in targeting the agent better.

Started by focusing on core metrics such as conversation volume, goal completion rate, and human handoff rate (when users are escalated to live agents). Real-time conversation logs, knowledge and tools performance also help in targeting the agent better.

Key learnings & next steps

Key learnings & next steps

Key UX decisions and learnings

Key UX decisions and learnings

Conceptualising how to build modular agentic experiences for platforms like Plotline, for marketers from leading consumer apps and visualising experience for their end users was a great opportunity to understand and design for

Conceptualising how to build modular agentic experiences for platforms like Plotline, for marketers from leading consumer apps and visualising experience for their end users was a great opportunity to understand and design for

Conceptualising how to build modular agentic experiences for platforms like Plotline, for marketers from leading consumer apps and visualising experience for their end users was a great opportunity to understand and design for

Building conversational agents in a modular way

Building conversational agents in a modular way

  • Breaking the whole process into functions such as context, knowledge, tools & actions ensured a very gradual learning curve

Segregating what building blocks are global and what are at agent-specific

Segregating what building blocks are global and what are at agent-specific

  • Centralising appearance, communication and brand guidelines reduces the potential for inconsistent experiences

Building trust and traceability into every AI decision

Building trust and traceability into every AI decision

  • Breaking down every decision in every interaction solves for trust at a scale of millions

  • Building unbiased testing and learning flows for agent's training

Improvements & next steps

Improvements & next steps

Working on agentic experiences opens a whole world of possibilities. For the next versions, ideations and concepts have already started!

Working on agentic experiences opens a whole world of possibilities. For the next versions, ideations and concepts have already started!

Working on agentic experiences opens a whole world of possibilities. For the next versions, ideations and concepts have already started!

Building 1:1 testing simulator

Building 1:1 testing simulator

Will help simulate conversation with real time performance tracking for different users and use cases

Improving handover flow to manual agents

Improving handover flow to manual agents

Giving more visibility into agent handovers and escalations.

Introducing new access points and interactions

Introducing new access points and interactions

Access points like floating buttons, pinned banners, gestures like long hold, bottom swipe can be introduced

Creativity is the catalyst for progress. Let's craft the future together

always available at aditya.12kansal@gmail.com

Book a short call

Back to top

Creativity is the catalyst for progress. Let's craft the future together

always available at aditya.12kansal@gmail.com

Book a short call

Back to top