James Plaschke
Builds/Build 03

Self-Coaching Loop

My AI watches my calls and tells me what I keep doing wrong, by name, every time I do it again.

times flagged
  • Answering objections with jargon, not the screen49
  • Answering a different question than asked42
  • Moving on right after they name the pain27
  • Pitching fixes that ignore their stated limits18
  • Hedging on my own product's features16
  • Going along with framing I'm unsure of7
  • Asking it three ways, then offering an out3
  • Fumbling the punchline the demo builds to1
The 8 habits it has caught, May 18 - Oct 13, 62 calls.
The problem

Feedback on how I communicate used to come once a quarter, from memory. I wanted a few real moments from each call that show me how I actually did.

How it works
  1. The same plumbing as the clip pipeline picks up every external call. Only moments where I am speaking count.
  2. Claude picks 0-5 strong or needs-work moments, each with one skill tag and a blunt note: what happened, the quote, what to do instead.
  3. A second pass matches each moment to a named habit in a running registry, either still doing it or caught it, and merges near-duplicates.
  4. Known habits go into the next call's prompt, so repeats get called out by name.
  5. Clips go to a private folder and a private Slack digest.
  6. A habit ledger dashboard rebuilds after each run, with no model involved: flags per call against the prior window.
The numbers
62calls reviewed, May to Oct
8named habits in the registry
27times I caught myself instead
The value
  • I can see how I actually work on calls, whether I'm improving, and what to focus on next.
  • I get feedback on every call, not once a quarter.
  • Habits are named and counted across 62 calls, so I can tell whether they are going away.