Getting Started with Sovereign AI

Intelligence is not the model. Intelligence is the accumulated decisions that shaped the model.

By Daniel Kliewer
Published: July 5, 2026
Reading Time: 15 minutes
Prerequisites: None (beginner to advanced)
Related Posts: Sovereign AI Architecture, The Sovereign Intelligence Stack, The Model Is Not the Product

---

Executive Summary

This post is your on-ramp to sovereign AI. It defines key terms, shows a simple example of recipe compilation, and points you to more advanced resources.

What you'll learn:

• What sovereign AI is (and isn't)
• What recipe compilation means
• What signal routing means
• What autonomous evaluation means
• How to get started with the Sovereign Intelligence Stack
• Where to find more advanced resources

---

What is Sovereign AI?

Sovereign AI is the idea that intelligence is not the model. Intelligence is the accumulated decisions that shaped the model.

This means:

• The model is just a snapshot of past decisions
• The loop is what keeps accumulating
• Systems that don't capture decisions are building castles on sand
• Compounding intelligence requires capture, evaluation, and storage

What Sovereign AI Is NOT

• Not just local LLMs — Local LLMs are a component, not the whole system
• Not just agent frameworks — Agent frameworks are tools, not architecture
• Not just RAG — RAG is retrieval, not intelligence
• Not just prompts — Prompts are inputs, not decisions

What Sovereign AI IS

• A compounding system — Gets smarter over time
• A recipe-based system — Captures decisions as immutable records
• A sovereign system — No cloud APIs required, data stays local
• An observable system — Every decision produces a timeline event

---

Key Concepts

Recipe Compilation

Definition: Capturing AI decisions as immutable records.

Why it matters: Without recipes, you have no history. You have no way to know why a model made a decision, what memory it used, what the outcome was.

What a recipe captures:

• Objective — What was the task?
• Model — Which model was used?
• Memory — What memory was injected?
• Prompt — What was the prompt (with versioning)?
• Reasoning Patterns — What reasoning patterns were used?
• Evaluation — How was it evaluated?
• Result — What was the result?
• Timestamp — When was it captured?

Example:

pythonCopy
1@dataclass
2class Recipe:
3    objective: str
4    model: str
5    memory_snapshot: Optional[str] = None
6    prompt: Optional[str] = None
7    reasoning_patterns: List[str] = field(default_factory=list)
8    evaluation_score: Optional[float] = None
9    outcome: str = "unknown"
10    timestamp: datetime = field(default_factory=datetime.now)
11    tags: List[str] = field(default_factory=list)

Signal Routing

Definition: Classifying incoming tasks and routing them through optimal evaluation paths.

Why it matters: Not all tasks are created equal. Simple tasks should be routed to fast, lightweight models. Complex tasks should be routed to capable models with full context.

Signal Types:

• Cheap — Simple tasks routed to fast, lightweight models
• Expert — Complex tasks routed to capable models with full context
• Hybrid — Tasks that benefit from multi-stage evaluation

Autonomous Evaluation

Definition: Self-improving loops that generate tests, evaluate performance, and detect drift.

Why it matters: Without evaluation, you have no way to know if your system is improving or degrading. Drift detection catches performance regressions before they compound.

Components:

• Signal Registry — Define what to evaluate
• Test Generator — Generate synthetic test cases
• Drift Detector — Detect performance drift (KS and PSI statistics)
• Loop Controller — Autonomous evaluation scheduling

---

How to Get Started

Step 1: Install the Sovereign Intelligence Stack

bashCopy
1# Clone the repository
2git clone https://github.com/kliewerdaniel/sovereign-intelligence-stack.git
3cd sovereign-intelligence-stack
4
5# Create virtual environment
6python -m venv .venv
7source .venv/bin/activate
8
9# Install dependencies
10pip install -e .

Step 2: Capture Your First Recipe

pythonCopy
1from src.recipe_compiler.models import Recipe
2from src.recipe_compiler.storage import RecipeStorage
3
4storage = RecipeStorage("my_stack.db")
5
6recipe = Recipe(
7    objective="Generate error handler for API calls",
8    model="gpt-4",
9    outcome="accepted",
10    evaluation_score=0.92,
11    tags=["error_handling", "api", "reliability"]
12)
13
14storage.create_recipe(recipe)
15print(f"Recipe captured: {recipe.id}")

Step 3: Run the Full Pipeline

pythonCopy
1from src.integration.pipe import SovereignPipeline, PipelineConfig
2
3config = PipelineConfig(db_path="intelligence.db")
4pipeline = SovereignPipeline(config)
5pipeline.initialize()
6
7# Capture a recipe
8recipe = Recipe(
9    objective="Optimize database query",
10    model="claude-2",
11    outcome="accepted",
12    evaluation_score=0.87,
13    tags=["optimization", "database"]
14)
15result = pipeline.capture_recipe(recipe)
16
17# Get intelligence summary
18summary = pipeline.get_intelligence_summary()
19print(summary)

Step 4: Run Autonomous Evaluation

pythonCopy
1from src.evaluation.loop import EvaluationLoop, LoopConfig
2
3config = LoopConfig(
4    signal_names=["code_correctness", "performance", "reliability"],
5    test_count=50,
6    interval_seconds=60
7)
8loop = EvaluationLoop(recipe_storage, config)
9loop.start()

Step 5: Explore the Intelligence Observatory

pythonCopy
1from src.observatory.timeline import IntelligenceTimeline
2
3timeline = IntelligenceTimeline(recipe_storage)
4timeline.record_event(IntelligenceEvent(
5    type="recipe_captured",
6    recipe_id=recipe.id,
7    timestamp=datetime.now()
8))
9
10# Get timeline
11events = timeline.get_timeline(days=30)
12for event in events:
13    print(f"{event.timestamp}: {event.type} - {event.recipe_id}")

---

What's Next?

For Beginners

1. Read the Sovereign AI Architecture post — Comprehensive synthesis of the entire system
2. Read the Sovereign Intelligence Stack post — Deep dive into the 5-layer architecture
3. Read the Model Is Not the Product post — Research validation and convergence

For Intermediate Readers

1. Read the Sovereign Memory Bank post — 7-layer memory system
2. Read the Dynamic Persona MoE RAG post — Persona-driven retrieval
3. Read the SovereignSpec post — Spec-driven development

For Advanced Readers

1. Read the Loop Is the Product post — Intelligence Observatory deep dive
2. Read the Autonomous Sovereign AI post — Autoresearch loops and expert fine-tuning
3. Contribute to the sovereign-intelligence-stack repository

---

FAQ

Is this just local LLMs?

No. Local LLMs are a component. Sovereign AI is the entire architecture: capture, route, evaluate, store, observe.

Do I need to use Ollama?

No. The stack works with any model provider (OpenAI, Anthropic, local LLMs, etc.). Ollama is just one option.

Is this production-ready?

Yes. The stack has 70 Python files, 7,757 lines of code, and 26 modules verified. It's used in production for autonomous research and expert fine-tuning.

Can I use this for my own projects?

Yes. The stack is open-source (MIT license). You can use it for any project, commercial or non-commercial.

What's the difference between this and CrewAI?

CrewAI is a multi-agent framework. The Sovereign Intelligence Stack is a compounding intelligence system that captures decisions, routes tasks, evaluates autonomously, stores knowledge, and observes patterns. It's the operating system that makes all of these pieces work together.

---

References

Related Posts

• Sovereign AI Architecture — Comprehensive synthesis of four years of work
• The Sovereign Intelligence Stack — Architecture deep dive
• The Model Is Not the Product — Research validation
• The Loop Is the Product — Companion post
• Building Autonomous Sovereign AI — Autonomous evaluation
• Local AI Architecture — Local AI guide
• Retrieval Architecture — Retrieval guide

Related Repositories

• sovereign-intelligence-stack — Working code
• Sovereign Memory Bank — Memory system
• Dynamic Persona MoE RAG — Retrieval system
• Objective05 — Persistent infrastructure
• SovereignSpec — Spec-driven development

Research Papers

• Residual Context Diffusion Language Models (Hu et al., 2026) — Apple research
• SGLang (LMSYS, UC Berkeley) — Agentic execution graphs
• Context Engineering (13.5K stars) — Systematic replacement for vibe coding
• Agent Harnesses (ECC 225K + Superpowers 244K stars) — Operating system layer for agents
• Persistent Memory (Claude Mem, 85K stars) — Stateful agent collaboration
• Multi-Agent Orchestration (CrewAI, 55K stars) — Collaborative intelligence
• Spec-Driven Development — Structured specifications (117K stars ecosystem)
• GraphRAG (Microsoft, 70K+ stars) — Knowledge graph retrieval
• The Sovereign Intelligence Stack
• The Model Is Not the Product
• The Loop Is the Product
• Building Autonomous Sovereign AI
• Sovereign Memory Bank
• Dynamic Persona MoE RAG
• SovereignSpec

Related Repositories

• sovereign-intelligence-stack
• Sovereign Memory Bank
• Dynamic Persona MoE RAG
• Objective05
• SovereignSpec

---

Published July 5, 2026 by Daniel Kliewer
License: MIT