From voice dump to action list

Voice notes from calls, meeting transcripts, half-formed ideas recorded on the move. They contain commercial signals, decisions, and action items, but the format makes them hard to revisit and almost impossible to act on quickly.

aibl co-founder Terry O’Dwyer was spending 20 to 30 minutes processing each one manually. Often it didn’t get done at all.

So he built a pipeline in Notion, Make.com, and an OpenAI Assistant. He records a voice note, pastes the raw transcript into a Notion database through a custom quick-capture mobile interface, and moves on. Make.com triggers automatically and sends the text to an OpenAI Assistant trained on his specific executive profile.

He loaded his Hogan Assessment data, known ADHD traits, and commercial goals into the assistant. The AI processes what he says through the lens of how he actually thinks, his known behavioural patterns, and what he’s trying to achieve commercially.

What lands in Notion after a voice dump

The system triages each raw transcript into distinct data streams:

• Commercial momentum – identifies and flags revenue opportunities buried in the raw content
• Executive coaching – provides psychological feedback based on Terry’s known personality derailers, noticing when he drifts into hyperfocus or avoidance
• Task extraction – generates an immediate “Actions (Next)” list
• Energy tracking – tags mental state and fatigue levels to prevent burnout
• Daily journal – the raw input archives automatically, leaving a clean multi-view journal for daily review
• Searchable record – every processed transcript becomes part of a structured, searchable database that builds over time

One of Terry’s recent voice dumps was him thinking through a Monday morning out loud: pipeline priorities after the weekly sales meeting, advisory board logistics, training, a couple of calls, home admin. Loose, momentum-dependent thinking out loud, mood and all. What landed in Notion was a checkboxed action list, a clear commercial priority with supporting tasks, and a coaching note flagging scope creep and recommending timeboxed blocks for the day.

Terry still reviews every output, but the triage work is done for him. He decides and acts on what the system surfaces.

How a non-technical founder built it

Terry has no engineering background. He built the entire pipeline using Make.com and Gemini to troubleshoot each step.

“Building my first automation in Make was frustrating at times,” he said. “I had no prior experience, and there’s a real learning curve. But using Gemini to troubleshoot step by step made it possible.”

Budget and technical complexity weren’t the issue – friction was. Once the troubleshooting barrier dropped, the build itself was straightforward.

“Something that used to take me 20 to 30 minutes, and often didn’t get done at all because of the friction, now takes seconds. I record a quick voice note, drop it in, and forget it. It gets done. Adoption follows simplicity.”

Why this isn’t a productivity hack

Terry’s building a structured, searchable database of his own commercial thinking that compounds over time. Every processed voice dump adds to a record of decisions, opportunities, and patterns. That database can eventually inform a leadership team – turning what’s trapped in one founder’s head into something the business can access and act on.

The AI acts as a guardian, flagging when Terry’s known derailer patterns show up in his thinking. That goes beyond task efficiency into how a founder manages themselves.

We see this at aibl across mid-market founders who build automations that stick. Terry automated the triage layer between raw thinking and structured action – and built an asset that gets more valuable the more he uses it.

For the research behind this, see how marketing and ops teams are automating workflow capture.

A non-technical founder did this on off-the-shelf tools with no developer. Most operators dealing with the same backlog of unprocessed voice notes and transcripts could build something similar in a few days.