The report goes back to the model
Runs todayA model's loop on GrailAOS: it describes the solution, compiles it, tests it, publishes it, operates it, and fixes it with what the compiler returns.
LLM-first
The model writes, reads and operates the solution
In GrailAOS™, the Agent Operating System by Omniatix™, “LLM-first” means something specific: the model writes the solution, reads what the system returns to it and operates it.
The origin
GrailAOS was born to make life easy for models
GrailAOS started with a question: what a model needs in order to understand a business solution, write it, test it and operate it without guessing.
GrailAOS was born to make life easy for models: so that a model can understand, write, test, and operate a business solution without having to guess.
Limit It is the founder's account of how the project began: it describes an intention, not a measured result.
What already runs in GrailAOS from that idea
- Runs todayA question behind every design decision
- Runs todayDiagnostics written for a model
- Runs todayTests next to each piece
This site does the same
This site does the same for whoever reads it: every page in , an index for models, a read-only and the status of every claim.
The thesis
Author, reader and operator
Each of the model's three roles has a part of the system designed for it.
Every design decision in GrailAOS is made with one question: which option makes it easier for a model to understand it, generate it right on the first try and fix it when it fails.
Author
Runs today- The model
- Declares the solution in text documents.
- GrailAOS gives it
- Pieces that name each other, and tools that tell it what is available.
Reader
Runs today- The model
- Reads what the returns and fixes the solution with it.
- GrailAOS gives it
- Every error in one report, each with its fix and its confidence.
Operator
Runs today- The model
- Tests, publishes versions and rolls back.
- GrailAOS gives it
- Versions without rebuilding, and a test report that separates what was validated from what was simulated.
The cycle
The compiler closes the loop
The compiler and the tests answer the model, and the model keeps fixing until the solution compiles and passes its tests.
Runs today
The diagram as text
- Describe. The model declares the solution in text documents.
- Compile. The compiler returns every error in one report written for a model.
- Test. With everything external simulated, and a judge model for what cannot be compared word for word.
- Publish. In preview and in , without rebuilding the image.
- Operate. On the channels, with people when needed.
- Correct. Until the solution compiles and passes its tests.
Until it passes its tests
Runs todayThe same model designs and writes the solution: the compiler returns what is wrong, the model corrects it, exact tests and a judge model tell it what fails, and the loop repeats until it compiles and passes its tests. That is how any solution the can express is programmed.
Limit By default, an agent test case runs in simulated mode and does not test the model; the judge has to be requested in the tests.
Fixes that get checked
PartialSome common errors have an automatic, deterministic fix; for the rest, the model makes corrections from what the compiler returns, and the compiler checks the solution again.
Limit The assisted loop runs only on the command line.
Diagnostics
Diagnostics written for a model
An error message meant for a person can be brief and take the context for granted. One meant for a model has to carry everything needed to fix the problem without guessing. Every diagnostic from the GrailAOS compiler is designed that way.
All in one pass
Runs todayWhat it does
The report lists every error in the solution, not just the first one.
Why it helps a model
The model fixes the whole list in one round.
What, why, where and how
Runs todayWhat it does
Each diagnostic carries the rule, the exact location and the fix, with its confidence.
Why it helps a model
It does not have to guess the rule or search for the location.
No network, no model
Runs todayWhat it does
Compiling spends no , depends on no other service and always produces the same report.
Why it helps a model
It can compile after every change and compare two runs.
Stable codes
PartialWhat it does
Diagnostic codes are added, not reused.
Why it helps a model
What a model automates today still holds tomorrow.
Limit The test that protects them covers only some of the codes.
On the first try
Pieces designed to come out right on the first try
Fixing is part of the cycle, but every round has a cost. That is why the pieces are designed so a model writes them correctly from the start, and so that whatever comes out half done can be fixed.
Text, not a canvas
Runs todayHow it works
The solution is written as text, with no visual editor, and the diagram a dashboard shows comes from the compiler.
Why it helps a model
Text is where a language model is most at home, and a diagram that comes from the compiler cannot contradict the documents.
Non-negotiable principles
Runs todayHow it works
Text first, self-contained, testable by default and with predictable shapes, and no change may make it harder for a model to write a solution correctly.
Why it helps a model
Anything added to the language is judged first by how a model writes it.
Pieces name each other
Runs todayHow it works
An agent names its tools; a workflow, its agents; a scheduled task, its workflow.
Why it helps a model
A broken name fails at compile time, not in a conversation.
The model asks what exists
Runs todayHow it works
The tells the builder model which pieces and capabilities it has.
Why it helps a model
It writes with what exists, not with what it assumes.
The test next to the piece
Runs todayHow it works
Test cases live inside the agents and workflows, with everything external simulated.
Why it helps a model
It writes the piece and its test together.
Limit A workflow that runs on its own is not tested as a whole in one test case: its agents are.
Limit By default, an agent test case runs in simulated mode.
The evidence
Built with coding agents
GrailAOS is not only designed for models: it is built with coding agents, and so are the solutions.
Share of with attribution to Claude, measured in the repositories
- 72.5%Share of commits attributed to Claude
- 88.6%Share of runtime commits attributed to Claude
- 52.6%Share of specification commits attributed to Claude
How it is measured: the percentage of commits on the main branch, excluding merges, whose message carries an attribution to Claude. It measures how much of the work was declared as done with a coding agent, not who made the decisions.
With coding agents
Runs todayGrailAOS is built with coding agents: excluding merges, 72.5% of the commits to the specification and the runtime carry attribution to Claude.
The solutions too
Runs todaySolutions are also built and operated with coding agents, from the requirements to publishing, operation, and version changes.
The difference
How is GrailAOS different?
Visual builders, automation tools, agent and conversational platforms have different design centers, and each one fits its own case.
What changes the design center
- Runs todayThe unit is the whole solution, declared in versioned text documents
- Runs todayA compiler verifies all of it before anything runs
- Runs todayA change after launch ships as a new version, without rebuilding and with
When another tool fits better: if what you need is a large catalog of ready-made integrations, a visual editor or public source code.
Determinism
Deterministic where it has to be
A model does not always answer the same way, and the design accounts for that: what has to be deterministic is, and the tests separate what was validated from what was simulated.
Bounded determinism
Runs todayWhat is deterministic is bounded: the compiler, contact identity, and canary assignment give the same result for the same input; the model's responses do not.
Real mode and simulated mode
Runs todayIn tests, everything external is simulated, and a case runs with the real model or in simulated mode: the report separates what validated the agent from what was only simulated.
Limit By default, an agent test case runs in simulated mode.
Questions
Frequently asked questions
What is deterministic and what is not?
The compiler, the contact's identity and the canary assignment give the same result for the same input. The model's answers do not: agents run with a nonzero temperature, so two answers to the same question can differ.
Markdown Plain text with simple marks for headings, lists and links, which reads well for both people and models.MCP Model Context Protocol: an open protocol that lets a model use the tools and data that another server offers.Compiler In GrailAOS, the piece that checks the whole solution before anything runs and, for each error, says what happened, where and how to fix it.Canary A new version that first reaches only part of the users, so it can be seen working before everyone gets it.Language In GrailAOS, the way a solution is declared in text documents: its agents, workflows, tools, knowledge, tests and the rest of its pieces.Token The unit in which a model reads and writes text, and in which providers charge: a few letters per token.Runtime The engine that runs a program that is already written. In GrailAOS, the one that operates the compiled solution.Commit A change saved in the history of the code, with a unique identifier that tells which version something comes from and lets you go back to it.Framework A set of libraries on which an application is programmed in code.Rollback Going back to the previous version when the new one is not working well. As a verb, roll back.