AI analyzes online meetings and creates structured notes in the CRM

Automated Conversation Analysis Using AI

For a company conducting a large number of business calls , we created a system that combines meeting transcripts, artificial intelligence, document storage, and HubSpot CRM into a single, cohesive process.

The solution automatically logs analyzed calls in the CRM, allows the user to select the correct meeting, and then uses AI to organize the data and pre-fill the form.

Instead of manually reviewing transcripts and rewriting information, the team receives ready-to-use material for quick verification.

The Challenge

After each call, the team had to perform several repetitive tasks:

• locate the recording or transcript,
• assign the conversation to the correct contact,
• analyze its content using a different prompt depending on the type of meeting,
• extract the most important information,
• transfer the data to the appropriate form,
• save the results in the CRM.

The process was time-consuming and required constantly switching between different tools. As the number of meetings increased, so did the risk of overlooking a conversation, creating a duplicate, or assigning information to the wrong record.

SOLUTION

Solution

We designed an automated data flow connecting Fireflies.ai, Google Drive, HubSpot, and an AI model.

The system periodically detects new conversations and checks whether they have already been recorded. It then identifies the correct contact and record owner, saves the meeting information in the CRM, and creates a link to the source transcript.

Directly from within HubSpot, the user can view conversations assigned to a specific contact and select the one they want to analyze.

Once the analysis is launched, the system:

1. verifies whether the selected conversation belongs to the correct contact,
2. retrieves the transcript document from Google Drive,
3. reads and organizes its content,
4. sends the data to the AI model,
5. converts the conversation into structured data,
6. opens a form with automatically populated content.

AI

AI that works based on facts

The model has been configured to use only the information found in the transcript.

If the conversation does not contain sufficient data, the system does not fill in the gaps with its own assumptions. As a result, the analysis remains based on the actual content of the meeting, and the user can easily identify elements that require further verification.

Responses are generated in a consistent, business-oriented format, regardless of the conversation’s length or how the meeting was conducted.

INTEGRATION

Why didn’t we use a ready-made integration available directly in HubSpot?

In the HubSpot Marketplace, you’ll find many pre-built integrations with tools for recording and analyzing meetings, such as Fireflies.

Many of these pre-built integrations support basic business processes, but they are insufficient for complex scenarios.

01

1. The key goal was to integrate the entire process into the tool the team uses every day—“without leaving HubSpot.”

That’s why a dedicated dashboard was created in HubSpot that allows you to:

• retrieve conversations associated with a contact,
• select the correct meeting version,
• run an AI analysis,
• go to a pre-filled form,
• maintain the link between the contact, the conversation, and the analysis result.

02

2. Security and Quality Control

We have implemented additional control mechanisms in the process:

Automation speeds up work but does not take away the team’s control over the information entering the CRM.

03

3. What Sets This Solution Apart from Standard Integration—Summary

Fireflies’ native integration with HubSpot works well for standard transfers of notes, summaries, tasks, and meeting data to the CRM.

In this implementation, however, Fireflies is just one component of a much broader process. The system identifies the conversation category based on meeting tags stored in HubSpot and then automatically selects the appropriate analysis scenario and a dedicated AI prompt.

As a result, each meeting is evaluated according to rules, context, and expected outcomes specific to its purpose, rather than being analyzed using a single, one-size-fits-all summary.

The solution also identifies the correct record and its owner, checks for duplicates and relationships, supports custom objects, and allows the user to select a specific conversation directly in HubSpot.

It then retrieves the source document from Google Drive and prepares a dedicated form for verification. Thus, it is not a ready-made data synchronization connector, but a complete process application that connects multiple systems and maps the organization’s unique workflow.

RESULTS

Impact of the Implementation

A consistent process was created, leading from the conclusion of a conversation to ready-to-use, organized data.

The solution:

• reduces the need to manually review transcripts,
• eliminates the need to retype the same information multiple times,
• standardizes the way conversations are documented,
• reduces the risk of errors and omissions,
• allows for faster updates to CRM data,
• ensures a consistent standard for analysis,
• enables handling a growing number of meetings without a proportional increase in operational workload.

The team can devote more time to working with clients and making decisions, rather than performing repetitive administrative tasks.

TECHNOLOGIES

Technologies Used

Automation tailored to the existing process

We didn’t replace the tools the team was already familiar with. We integrated them into a single process and added an AI layer where it could deliver the most value.

Standardizing notes and summaries is a crucial part of the process in large organizations. By using HubSpot forms with precisely structured meeting outcomes, the team knows exactly where to find key information.

The solution has become a natural part of daily work—accessible directly within the CRM and tailored to the organization’s way of working.

VELMANTA

Want to automatically turn conversations into organized data?

At Velmanta, we design AI automations that integrate conversations, documents, forms, and CRM systems. We build solutions tailored to existing processes, allowing teams to work faster without having to implement yet another standalone tool.