How we built an AI ecosystem to power our event content | MarTech

How we built an AI ecosystem to power our event content | MarTech

3 minutes, 42 seconds Read

By some estimates, more than half of the content is now on the Internet generated by AI. When you think about how long it took people to generate the other half, you probably think, “That escalated quickly,” and it did.

A divide is emerging among content creators, content marketers, and almost anyone who values ​​quality content and the craftsmanship it requires. Content is either “AI slop” or human-generated art.

In reality, that has never been the case. People were creating long before generative AI became widely available, and AI can be used to create great, valuable content. This is an example of the latter.

We’ve built an AI-powered content ecosystem at MarTech to help us amplify the content of the MarTech conference in September. People were involved every step of the way. Nothing was published without a human reviewing and editing the content.

But the work – and believe me, atomizing and amplifying the content of a conference can be a lot of of the work – was accelerated and simplified, allowing the content to reach the audience faster.

Here’s how we did it.

September’s MarTech conference

The September edition of the MarTech Conference took place on September 17, 2025. It was a free, online conference consisting of six live panel discussions on data and AI, streamed to registered audience members.

Each conference session had four to five participants, including a moderator.

Transcriptions and video clips

The first step in atomizing six panel discussions is to put the content in a form that is easily digestible by other tools. To do that, our team turned to Descript, an AI-powered video editing tool.

Using Descript, our team was able to easily create dozens of short video clips of the conference sessions. More importantly, it generated fast and accurate transcripts of each session, identifying which speaker spoke along the way.

During the day of the conference, our team created a Google Doc, adding the full transcript of each conference session shortly afterwards. By the end of the day, the document was almost 100 pages.

Those transcripts made everything that happened next possible.

Key insights and quotes from the conference

The full transcripts were exported as PDFs from Google Docs and uploaded to ChatGPT, which was tasked with reviewing the sessions and identifying interesting insights and quotes from the panelists.

A human editor reviewed the ChatGPT output and chose the best quotes and insights that would become content pieces on the MarTech site within days of the conference’s conclusion. We’ve also used the best quotes in a carousel format for social media.

ChatGPT also prepared summary articles of the sessions, which were reviewed by human editors and published in the days following the conference.

An audio overview of the conference sessions

We also used Google’s NotebookLM to create an AI-generated audio overview of the event. That overview, which lasted twelve minutes, was embedded in the summary articles that appeared after the conference.

AI-powered session evaluations

Live conferences are stressful. The MarTech Conference sessions were unscripted (although each panel had a scheduling call beforehand), meaning you’re never 100% sure what you’re going to get.

For our events team, we created a Gemini GEM to quickly evaluate the sessions. Once again, the transcripts of the sessions formed the basis.

Gemini took the title and description of each session as it appeared on the conference agenda and compared it to the transcript to see how well our content delivered on its promise. It also told us the share of voice for each speaker. Gemini calculated how long each panelist spoke in each session, in both minutes and seconds and as a percentage of the session.

What is the future for this ecosystem?

With September’s MarTech conference, we developed a solid playbook for atomizing and amplifying event content. We met our initial expectations, but there are more opportunities to explore.

One area we want to explore is connecting some of the AI-generated output to our back-end event management platform. The platform contains the history of MarTech and SMX events going back years: every session, speaker and topic.

By connecting session transcripts and AI-generated evaluations to the system, more information will be available to team members planning future events.

Energize yourself with free marketing insights.

MarTech is owned by Semrush. We remain committed to providing high-quality reporting on marketing topics. Unless otherwise stated, the content of this page was written by an employee or paid contractor of Semrush Inc.

#built #ecosystem #power #event #content #MarTech

Similar Posts

Leave a Reply

Your email address will not be published. Required fields are marked *