# Simone Systems Research
> Independent, founder-led research on how to evaluate AI agents, verify their results, keep humans in control of their actions, and make their compute earn its cost.

Simone Systems Research is an independent research organization led by Jonathan Simone. It is founder-led and has no institutional affiliation.

## Research Questions
- **Systems & Control**: How should heterogeneous models, tools, and agents divide work and coordinate reliably?
- **Reliability & Measurement**: How do we distinguish genuine improvement from false progress, benchmark noise, and brittle behavior?
- **Inference & Budgeting**: When does additional inference improve verified outcomes enough to justify its cost?
- **Dynamic Learning**: How can systems learn from measured failures and improve their own workflows without losing control or reproducibility?

## Research Principles
1. **Evidence before promotion**: Improvements should survive measurement, not merely look plausible.
2. **Independent verification**: Positive results should be reproduced outside the context that generated them.
3. **Compute must earn its cost**: Expensive inference should be reserved for decisions where it materially improves verified outcomes.
4. **Negative results are retained**: Failed hypotheses are useful evidence and should not disappear from the record.
5. **Artifacts matter**: Claims should refer to the exact code, model, configuration, and environment actually evaluated.

## Projects
Status tokens are a closed vocabulary: HYPOTHESIS, SUPPORTED, REFUTED, NULL, INSTRUMENT VALIDATED, AUTHOR-RUN, INDEPENDENTLY REPRODUCED, WORKING MVP, RETIRED, NEGATIVE RESULT, PUBLIC.

- SEED (https://github.com/thisisntjon/seed-protocol): HYPOTHESIS (C-004) · INSTRUMENT VALIDATED · case study AUTHOR-RUN. A measurement and epistemic-control protocol for distinguishing implementation activity from verified progress in agent-driven software work. Fleet orchestration is deferred until a single-agent baseline is measured. Research note: https://simoneresearch.com/blog/throughput-is-not-progress/
- The Council (https://github.com/thisisntjon/thecouncil): PUBLIC working system. A heterogeneous multi-model verification system separating answer generation, peer critique, cross-vendor claim verification, and synthesis. Fixture runs are simulated evidence; live runs are captured evidence, not a benchmark.
- BigBoss (https://github.com/thisisntjon/bigboss-approval-plane): WORKING MVP. A local human-authority and observability plane for AI coding agents. Harness proposes, BigBoss evaluates and routes, human approval is authoritative for gated actions, decisions are bound to action hashes, state and audit persist.
- The Bus (https://github.com/thisisntjon/thebus): NEGATIVE RESULT · RETIRED. A preserved negative result; prior-art sweep invalidated 17 assumptions in the initial sweep; retraction ledger kept; do not build on it.
- Godot AI Methodology (https://github.com/thisisntjon/godot-ai-methodology): PUBLIC. Second-domain application: deterministic, observable, testable, modular, data-driven, documented codebases are easier for AI coding systems to modify safely and verify. No decompilation, no extracted assets, no copied source.

## What has been measured
Every figure keeps its caveat. None is a causal claim.
- 1,979 PR-linked first-parent commits analyzed (author-run, n = 1 repository). https://github.com/thisisntjon/seed-protocol/blob/main/workflow/research/2026-08-24-pr-case-study/PAPER.md
- 43.2% docs-only share of those commits, 855/1,979 (composition, not merge rate). Same source, artifacts/summary.json
- 2/80 sampled PRs changed the playing agent (80-PR stratified inspection, single inspector). Same source, artifacts/sample80_summary.json
- 17 assumptions invalidated in the initial prior-art sweep (grew to 21 after a later step). https://github.com/thisisntjon/thebus
- 4 model vendors in The Council: Claude, GPT, Gemini, Grok (fast-tier models: Claude Haiku 4.5, GPT-5.4 mini, Gemini 3.5 Flash, Grok 4.3). https://github.com/thisisntjon/thecouncil

## How the projects relate
SEED measures whether agent-driven work constitutes verified progress. BigBoss controls which autonomous actions can occur and preserves human decision authority. The Council tests independent verification through heterogeneous model families. The Bus shows adversarial review terminating a bad architecture before further implementation. Godot Methodology tests whether the same verification principles generalize into software architecture.

## Researcher Identity
- **Founder & Principal**: Jonathan Simone
- **Email**: jon@simoneresearch.com
- **GitHub**: https://github.com/thisisntjon
- **Website**: https://simoneresearch.com

## Detailed Documentation
- Full research context: https://simoneresearch.com/llms-full.txt