Not prompt engineering. Systems architecture.
Five principles that define how I design autonomous systems. Each one is a result of real failures and iterations.
Consensus over trust
No single LLM makes decisions alone. Every critical decision goes through a panel of 4 independent providers with quorum ≥3/4. Different reasoning architectures (reasoning tokens, thinking blocks) compensate for each other's weaknesses.
Evaluation is built-in, not bolted on
Every pipeline stage passes through an evaluator. A judge system with 26 checkpoints and a 100-point scale. A critic with 5 criteria. A reviewer with retry cycles. Evaluation is not the final step — it's a component of every step.
Rejection is cheaper than rework
Kill gates stand before every expensive stage. If an idea doesn't pass the critic (< min_score), it won't reach code generation. Every rejection is recorded with kill_stage and kill_reason for funnel analytics.
Agents as components
Each agent is a service with a defined contract: inputs, outputs, prompt, model, max_tokens. Agents don't know about each other — the orchestrator manages the flow. This allows replacing, scaling, and testing each one independently.
Meta-level: agents for agents
Agent Manager monitors all parallel sessions. Buddy System automatically restores context when switching tasks. Thinking Amplifier forces a pause to analyze alternatives before making a decision.
Technologies
Tools are chosen for the task, not the other way around.
Orchestration
LLM Providers
Agent CLI
Data
Frontend
Infrastructure
Why NOT LangGraph, CrewAI, Fine-tuning
Every 'gap' is a conscious architectural decision, not ignorance.
LangGraph doesn't support 2-stage deliberation and kill gates at arbitrary points. A custom orchestrator gives full control over flow, retry logic, and observability.
Frameworks abstract away what needs to be controlled: prompts, call order, error handling. Custom code is transparent, testable, and has no magic.
Models are a commodity that updates every 3 months. Orchestration architecture is a sustainable moat. Investment in systems engineering yields greater returns.
Automatic prompt optimization works well for simple tasks. Complex multi-agent pipelines need control over every step.
Universal observability, not tied to LLM-specific tooling. The same metrics, traces, and dashboards work for all system components — not just LLMs.
“If an agent can make a mistake — it will. That's why every result goes through independent evaluation, not hope.”
Ready to discuss?
If you need an architect who builds autonomous AI systems — reach out.
Serbia-based · CET/CEST timezone · EU-aligned working hours · International contracts experience