I kept forgetting to grab the AI summary before leaving a Teams call. So I built a fix.
The result is a small Windows program. It watches for a Teams call, records both sides, transcribes on my own machine, and writes a transcript with the Outlook meeting details already in it. The audio is deleted once the transcript lands. A tray icon and a folder of text files are the whole product.
I did not write it line by line. I ran it through four steps:
- Notice and explore. Catch the thing you work around, then make the agent show you what it assumed.
- Plan and premortem. Get the plan on the page, then send adversarial agents to poke holes in it.
- Execute and test. Let the agent type, then run the thing yourself. Reading it won't tell you what running it will.
- Deploy and maintain. Hand it to a machine that has never seen it.
One decision from the plan: I wanted AI summaries of each call. Turning that on meant transcripts leaving my machine, so the feature came out instead.
The same four steps gave me a lint script for my own writing, a wiki an agent maintains, and a task queue I no longer track by hand.
The longer version, with the plan file and the install lessons: https://medium.com/generative-ai/stop-absorbing-the-manual-work-four-steps-to-solving-it-yourself-99ac67f13a01?sk=ffe770bc6740373b16234205f90e6a5d
Top comments (1)
"Run the thing yourself, reading it won't tell you" is the step most people skip with agents, so it's good to see it as its own step. One thing to add to the premortem for this particular tool: recording both sides of a call. In a lot of places that needs the other people's consent, and even where it doesn't, people outside your company may not be happy to find out later. A line in the invite or a spoken "this call is transcribed" at the start costs nothing. Did the adversarial agents raise that one, or did it come up some other way?