David Grunwald

hey PH Ola here, founder of Specsight, launching today

I ve been building Specsight solo since March, with no employees. just me and a team of AI agents. they handle outreach, call prep, fundraising research (they screened 3,000+ VC firms for me), content, support and a lot of the dev work

I used to rely strictly on typing out manual timestamps during long meetings, but the moment I lost focus for five minutes the entire log became useless.

Keyword search inside massive audio transcripts sounds great on paper, but it usually fails when you can't recall the exact phrase someone used. I've been trying to find a cleaner system to jump straight to the key decision points without scrolling through pages of text.

Have you found a search workflow that actually pinpoints specific moments reliably or do you still take manual notes while listening?

I keep coming back to this idea: vibe code is basically instant legacy code.

Not because AI-generated code is necessarily bad, but because it often puts us in a familiar situation: the system works, yet no one fully understands how it works. That makes me wonder whether some of the most useful techniques for vibe coding are actually techniques we already use for legacy systems. For example:

• Snapshot / approval tests: capture the current output and require explicit approval when it changes.

• Characterization tests: describe what the system actually does today, regardless of what it was originally intended to do.

• Golden master tests: run known inputs through the system and compare the results with a trusted baseline.

• Contract test: protect the boundaries between components, services, APIs, events, and data stores.

• Differential testing: compare two implementations and detect where their behavior diverges.

• Test carving: observe a larger execution and extract smaller, focused regression tests from it.