---
title: "The modern AI systems roadmap"
chapter: "00"
---

# The modern AI systems roadmap

An AI-powered system is ordinary software around a probabilistic model. The
model predicts useful output; your application owns data, tools, permissions,
state, validation, cost, latency, evidence, and recovery.

## Current baseline, August 2026

| Layer | Current production baseline | Important note |
|---|---|---|
| Spring AI | 2.0.0 GA | Spring Boot 4.0/4.1 and Spring Framework 7 |
| Java | 21+ | Use the version supported by your Boot line |
| OpenAI | Responses API; GPT-5.6 family | Route Sol/Terra/Luna by workload role |
| Gemini | Gemini 3.6 Flash; 3.5 Flash-Lite | Stable model IDs can still deprecate later |
| Ollama | 0.32.5 | Local runtime; capabilities depend on the chosen model |
| Google embeddings | `gemini-embedding-2` | GA multimodal embeddings, 128–3072 dimensions |
| OpenAI embeddings | `text-embedding-3-small/large` | 1536/3072 default dimensions |
| Local embeddings | `embeddinggemma`, `qwen3-embedding` | Keep index and query model identical |
| Vector search | pgvector HNSW or managed equivalent | Measure recall, latency, filters, and operations |
| Agent integration | Tool calling and MCP | Tools need authorization, schemas, budgets, and audit |

“Latest” means the newest compatible, stable set that fits quality, latency,
cost, privacy, and lifecycle requirements. A flagship model is not the default
for every classification or extraction request.

## The seven layers

`experience → orchestration → model gateway → retrieval/tools → enterprise
systems → safety/evaluation → operations`

Spring AI sits mainly in orchestration and provider integration. Ollama,
OpenAI, and Gemini are inference providers. A vector database is retrieval
infrastructure. None of them alone creates a trustworthy product.

## Build sequence

1. Define the user decision or job.
2. Create an evaluation dataset before choosing architecture.
3. Establish a simple prompt baseline.
4. Add structured output when software consumes the result.
5. Add RAG only when external knowledge is needed.
6. Add tools only when the system must act or obtain live state.
7. Add an agent loop only when a fixed workflow cannot express the task.
8. Fine-tune only after measured prompt/RAG/tool limitations.

## Feynman check

Explain the system as a librarian, a writer, and a careful operator. Retrieval
finds evidence; the model writes; application code checks and acts.