-
Notifications
You must be signed in to change notification settings - Fork 0
What PIC Does Not Do
kadubon edited this page Jul 1, 2026
·
2 revisions
This page states non-goals in direct language.
PIC-TS does not:
- prove that an AI system is generally intelligent;
- prove real ASI;
- prove a physical or simulator result;
- prove a legal, policy, or medical claim;
- replace human review;
- execute shell commands;
- install packages;
- mutate repositories;
- crawl the web in the background;
- send external messages by itself;
- hide missing obligations;
- turn candidate work into completed work without finite verification;
- treat
accepted=trueassettled=true; - treat
workflow_usable=trueassettled=true; - treat
operation_ready=trueas execution or physical proof; - treat CCR JSONL handoff as runtime settlement;
- run
safe_commandsautomatically.
It creates structured reports.
The reports help an agent or engineer see:
- what was accepted;
- what is still missing;
- what remains candidate-only;
- what blocks settlement;
- what should be routed to a verifier;
- what can be handed to CCR or another scheduler as candidate data;
- what can guide the next workflow step.
This makes incomplete work visible.
- Home
- Quickstart
- Getting Started
- Acceleration Measurement
- Operation Guide
- AFST Satisfaction Flux
- Python TypeScript Compatibility
- Security
- Node Only Agent Loop
- ASI Proxy Loop v0.9
- Token Reports and Agent Loop
- ASI Proxy Acceleration
- CCR Interop
- MCP And A2A Safety
- Operation Gate
- Phase Ecology Lab
- CLI Recipes
- JavaScript SDK
- Diagnostic Commands
- How To Read The JSON
- Agent Guide
- Agent Messages and Packets
- Schemas and Conformance
- Safety and Limits
- Compatibility With Python
- npm Package and Release Checks
- Use Cases
- Core Concepts
- Concepts in Plain Language
- What PIC Does Not Do
- Theory Map
- Glossary
- FAQ
- v1.1 Release Notes
- v0.9.0 Release Notes
- v0.8.0 Release Notes
- v0.7.0 Release Notes
- v0.6.0 Release Notes
- v0.5.0 Release Notes