work with me

Agent Verification Layer

an agent only improves where something else can check it

in daily use, just me
an agent only improves where something other than itself can check it.
no screenshot, this one runs in the background

what it is

built from 9 stanford cs329a lectures (103k words) on self-improving agents. my own audit found the same thing: sensor-fed fields were 0 days stale, say-so fields 17 to 41. verdict.py scores the action, not the outcome, and agent_guard.py catches hedged status claims before they reach me. give-up caps found 223 of my 318 agent messages were nags, one agent asked the same question 79 times.

how it actually works

  1. read the research9 stanford cs329a lectures on self-improving agents, 103k words, kept in agent-research.
  2. score the actionverdict.py grades what the agent did, so companions can improve even when nothing can verify a skincare call or a journal prompt.
  3. guard the claimsagent_guard.py catches hedged status claims like 'probably still outstanding' before they reach me.
  4. cap the nagginggive-up caps found 223 of 318 agent messages were nags.

want to build your own?