The Agentic AI Stack — Every Layer, Mapped

Embeddings, vector stores, orchestration, memory, guardrails, observability. A full map of the agentic AI landscape and where each piece fits.


Every few weeks I catch myself re-explaining the agentic AI landscape to someone — a recruiter, a fellow engineer, or honestly, myself at 2am trying to remember if I need a vector store for this or not.

So I built the map once, properly, and I’m keeping it here.

This isn’t a “best tool” ranking. It’s a layer-by-layer breakdown of what each category of tool does, why it exists, and what trade-off you’re accepting when you pick one over another.


Why a Map, Not a List

Most “agentic AI tools” posts mix categories — they’ll put Pinecone and LangGraph in the same bullet list even though one stores vectors and the other orchestrates agent logic. That’s like comparing a database to a web framework.

The stack actually breaks into distinct layers. Here they are.


1. Embeddings

Turns text into vectors so meaning can be compared mathematically.

ToolBest ForTrade-off
Voyage AIRAG paired with ClaudeSmaller ecosystem than OpenAI’s
OpenAI EmbeddingsFast prototyping, huge communityNot domain-tuned
Cohere EmbedMultilingual + built-in rerankingSmaller community
Jina AISelf-hosted, cost-sensitive setupsMore ops work if self-hosted

I use Voyage AI in the Site Search Agent project — it’s Anthropic’s recommended pairing, and the accuracy on product-catalog text has been solid.


2. Retrieval Techniques

The actual strategy for finding relevant context, independent of which vector store you use.

For the Site Search Agent, plain RAG was enough — the vocabulary mismatch problem (“footwear for jogging” → running shoes) is solved by the embedding step itself, not by a fancier retrieval strategy.


3. Vector Stores

Where the vectors actually live.

ToolBest ForTrade-off
PineconeZero-ops production appsCost scales with usage, lock-in
WeaviateHybrid keyword + vector searchMore config than Pinecone
QdrantCost-conscious, on-premSmaller ecosystem
MilvusBillion-scale vector countsHeavy ops overhead
ChromaLocal dev, prototypingNot built for production scale
pgvectorTeams already on PostgresLess optimized at huge scale

This is the one that actually matters most for my stack. I’m on Neon Postgres for everything already — adding pgvector means no new infrastructure, no new vendor, no new bill. For a portfolio-scale RAG project, that’s the right trade every time.


4. Agent Memory

Persisting context across sessions, not just within one conversation.

Neither of my projects need this yet — everything so far is single-session. But the Family Assistant platform will eventually need to remember a child’s preferences across visits, and that’s exactly this layer’s job.


5. Orchestration Frameworks

The layer that actually runs the agent loop.

ToolBest ForTrade-off
Claude Agent SDKNative Claude agents, no extra abstractionSmaller community than LangChain
LangGraphComplex, conditional multi-step flowsSteeper learning curve
CrewAIRole-based multi-agent collaborationLess low-level control
AutoGenResearch, agent-to-agent dialogueHarder to productionize
LlamaIndex AgentsRetrieval-heavy agentsLess general-purpose outside RAG

I’ve deliberately avoided LangChain across all four projects — every agentic loop I’ve built (while(stop_reason === "tool_use")) is hand-rolled against the raw Anthropic API. It’s more code up front, but I understand every line of it, and there’s nothing to debug through an abstraction layer when something breaks.


6. Tool-Use Protocols

How the model actually calls your code.

Project 4 (Restaurant Agent) was my first real MCP build — restaurant-mcp-server exposes the tools, restaurant-agent consumes them. The appeal is portability: those same tools could be wired into Claude Desktop, Claude Code, or any other MCP client without touching the server code.


7. Reasoning & Planning

Not a tool category — a set of prompting/looping patterns.


8. Evaluation & Observability

How you know the agent is actually working, and keeps working.

ToolBest ForTrade-off
LangSmithLangGraph/LangChain appsBest value locked to that ecosystem
LangfuseFramework-agnostic, self-hostableLess polished UI than LangSmith
BraintrustRigorous eval/regression pipelinesEval-focused, less general tracing
HeliconeQuick cost/latency monitoringLess deep tracing

Since none of my projects use LangChain, Langfuse or Helicone are the natural fit here — I just haven’t wired one in yet. It’s on the list.


9. Guardrails & Safety

Relevant the moment an agent handles untrusted input — user uploads, scraped web content, anything you didn’t write yourself. The Autism Worksheet Studio’s content moderation pipeline is a version of this: pre- and post-generation checks before anything reaches a family.


10. Deployment & Low-Code Layers


Where My Stack Actually Sits

Laying all four projects against this map:

Embeddings        → Voyage AI            (Project 3)
Retrieval         → RAG                  (Projects 2, 3)
Vector store       → pgvector on Neon     (Project 3)
Orchestration      → hand-rolled loop     (Projects 1–4)
Tool protocol       → MCP                 (Project 4)
Reasoning pattern   → ReAct               (Projects 1–4)
Deployment          → Cloudflare Workers  (Project 4, this site)

No LangChain, no managed agent platform, no vector DB vendor beyond what Neon already gives me. It’s more typing up front than reaching for a framework — but every piece is something I can explain line-by-line, which matters more to me right now than saving a week of setup time.


Next up: wiring Langfuse into the Restaurant Agent so I can actually see what these agent loops are doing in production, not just trust that they’re working.

← All posts