Skip to content

Repository files navigation

Proof-Adjusted Autonomy (PAA)

DOI

English | 中文

Autonomy is not what your agent does. It's what it can prove.

Proof-Adjusted Autonomy (PAA) is a metric for AI agent systems, coined by Michał Piszczek (2026). It measures the share of an organization's completed work that an AI system executes without human intervention and supports with independent, reliable and timely evidence.

Canonical definition & FAQ: https://piszczek.pl/proof-adjusted-autonomy Launch essay: https://piszczek.pl/blog/proof-adjusted-autonomy


The formula

PAA = P(A) × P(C|A) × P(R|A,C) × P(T|A,C,R)

Four conditional gates, multiplied — no independence assumption, no double counting:

Gate Meaning
A — Autonomous execution The work was completed without a human touching it.
C — Complete evidence It arrived with a full evidence package: what was intended, touched, done, and produced.
R — Independent validation The evidence survived a different mechanism than the one that produced it — deterministic tests, a different model family, replay, a human at irreversible boundaries. Never the agent grading its own homework.
T — Timeliness The verified result landed inside the decision window. Proof after the deploy is a post-mortem, not a safeguard.

The 90% agent is a 61.6% agent

A demo agent at 0.90 raw autonomy, 0.80 evidence coverage, 0.95 validation pass rate and 0.90 on-time delivery is a 0.90 × 0.80 × 0.95 × 0.90 = 61.6% agent. Marketing reports the first factor. Operations lives with the product of all four.

Proof Debt

The unresolved remainder accumulates as Proof Debt — the stock of AI-generated work whose verification cost, uncertainty or liability hasn't been resolved yet:

ProofDebt(t+1) = max(0, ProofDebt(t) + GeneratedWork − ProvenWork − RejectedWork)

Deferred liability the P&L doesn't show until an incident, audit or customer claim prices it. Law: sustainable autonomy cannot exceed proof capacity — safe throughput is min(generation rate, proof rate).


Reference calculator

A tiny, dependency-free reference implementation lives in examples/paa_calculator.py:

python examples/paa_calculator.py --a 0.90 --c 0.80 --r 0.95 --t 0.90
# PAA = 0.6156  (61.6%)  — a "90% autonomous" agent is a 61.6% agent.

How to compute PAA from production logs

Over a defined period:

  1. P(A) — share of completed tasks executed without human intervention.
  2. P(C|A) — of those, share carrying the evidence package your policy requires.
  3. P(R|A,C) — of those, share passing independent validation, estimated on a random or complete sample (validate only the easy work and your PAA is a ceiling, not a measurement).
  4. P(T|A,C,R) — of those, share verified inside the decision window.

Multiply the four factors.

What PAA is not

  • Not the AI Proof Gap (Grant Thornton) — that documents the gap exists; PAA is the instrument that measures it from your own logs.
  • Not Verifier's rule (Jason Wei) — that predicts which tasks AI masters fastest (the learning frontier); PAA measures how much of that mastery you can let act (the deployment frontier).
  • Not runtime-verification research — guardrails and formal checks are mechanisms; PAA is the operational metric that tells you whether they actually buy you autonomy.

Related work by the same author

Discussed across the web

Proof-Adjusted Autonomy appears, with canonical attribution to piszczek.pl, on:

Citing

See CITATION.cff. Canonical, quotable with attribution to https://piszczek.pl/proof-adjusted-autonomy.

License

Documentation and specification: CC BY 4.0. Code in examples/: MIT (see file headers).


Concept by Michał Piszczek — CTO of Archdesk; founder of Robotero (acq. HTF Brokers), Rejsomat.pl, Inclify and Lextron.ai. · piszczek.pl · LinkedIn · ORCID: 0009-0000-5182-5756

About

Proof-Adjusted Autonomy (PAA): the metric of independently proven AI agent work. PAA = P(A)×P(C|A)×P(R|A,C)×P(T|A,C,R). Concept by Michał Piszczek.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors