Agentic AI Interview Glossary

The DBA's Guide to Oracle Agentic AI Foundations · Glossary

Every acronym, key idea and likely interview question from the series, explained in plain words with an Oracle DBA comparison. Bookmark it for revision before your exam or interview.

• Full forms
• Key concepts
• Interview Q&A
• How to answer

Full forms

The highlighted letters show where each acronym comes from. Learn the full form first; the meaning usually follows from it.

AI and model basics

AI

Artificial Intelligence

Machines doing tasks that need human-like thinking

ML

Machine Learning

Systems that learn patterns from data instead of fixed rules

GenAI

Generative AI

AI that creates new text, images or code

LLM

Large Language Model

The "brain" of an agent, trained on huge amounts of text

NLP

Natural Language Processing

Making computers understand human language

HITL

Human-in-the-Loop

A person approves each important step

Reasoning and retrieval

RAG

Retrieval-Augmented Generation

Fetch relevant documents first, then let the LLM answer from them

CoT

Chain-of-Thought

Reason step by step before answering

ReAct

Reason + Act

Thought → Action → Observation, in a loop

ToT

Tree-of-Thought

Explore several reasoning paths, keep the best

NL2SQL

Natural Language to SQL

Turn an English question into a SQL query

KB

Knowledge Base

The document library a RAG tool searches

Frameworks and protocols

MCP

Model Context Protocol

Open standard to plug any AI app into any tool ("USB-C of AI")

A2A

Agent2Agent protocol

Open standard for agents talking to other agents

SDK

Software Development Kit

Ready-made libraries for building apps, e.g. OpenAI Agents SDK

LCEL

LangChain Expression Language

Joins steps with a pipe: prompt | model | parser

API

Application Programming Interface

A defined way for software to talk to software

REST

Representational State Transfer

The common style for web APIs over HTTP

JSON

JavaScript Object Notation

The text format tools and LLMs exchange data in

JSON-RPC

JSON Remote Procedure Call

The message format MCP uses (version 2.0)

HTTP

Hypertext Transfer Protocol

Web transport; MCP's remote option is Streamable HTTP

SSE

Server-Sent Events

Older MCP remote transport, replaced by Streamable HTTP

stdio

Standard input/output

MCP transport for a local server on the same machine

OAuth

Open Authorization

Standard for secure delegated access to remote servers

Oracle and database

OCI

Oracle Cloud Infrastructure

Oracle's cloud

IAM

Identity and Access Management

Who can do what in OCI (policies, compartments)

ADB

Autonomous Database

Oracle's self-managing cloud database

HNSW

Hierarchical Navigable Small World

In-memory graph vector index: fastest, very accurate

IVF

Inverted File (Flat) index

Partition-based vector index: scales to huge data

ANN

Approximate Nearest Neighbor

Fast vector search using an index, slightly less than 100% accurate

KNN

k-Nearest Neighbors

Find the k closest vectors; exact search compares them all

ONNX

Open Neural Network Exchange

Model format you load into the database to create embeddings

VPD

Virtual Private Database

Row-level security that also applies to agent queries

PII

Personally Identifiable Information

Names, phone numbers, IDs: guardrails mask or block it

Key concepts

What each term means, and how to explain it using things a DBA already knows.

AI agent

An LLM that plans, uses tools and remembers, looping until a goal is met

The DBA wayThe on-call DBA who fixes the alert, not the one who only explains the error

Workflow (vs agent)

Fixed steps decided by code, with LLM calls inside

The DBA wayA scheduled RMAN script: same steps every time

Token

The small piece of text a model reads and writes (about ¾ of a word)

The DBA wayLike a block: the unit everything is counted and billed in

Context window

How many tokens the model can see at once; also its short-term memory

The DBA wayThe SGA: fast, limited, cleared when the session ends

System prompt

Fixed rules that set the agent's role and limits

The DBA wayThe runbook and change policy

Embedding

A list of numbers that captures the meaning of text

The DBA wayA fingerprint of meaning, not of spelling

Vector

The stored embedding; similar meanings sit close together

The DBA wayA row you search by closeness instead of equality

Semantic search

Finding results by meaning, not exact words

The DBA way"Tablespace full" also finds "no space in datafile"

Cosine similarity

Measures the angle between two vectors; the usual text metric

The DBA wayUsed inside VECTOR_DISTANCE(..., COSINE)

Chunking

Splitting documents into small pieces before embedding

The DBA wayLike splitting a large export into manageable files

Grounding

Tying answers to real data (tools, RAG)

The DBA wayAnswering from AWR, not from memory

Hallucination

A confident but made-up answer

The DBA wayA guess written into an RCA without proof

Function / tool calling

The LLM outputs a structured request; the app runs it

The DBA wayThe LLM writes the ticket; the operator executes it

Guardrails

Checks on input and output (injection, PII, toxicity)

The DBA wayChange control and audit for the agent

Prompt injection

Hidden instructions in input or tool results that try to hijack the agent

The DBA waySQL injection, but in plain language

Least privilege

Give tools only the access they need

The DBA wayA read-only DB user for a reporting agent

Handoff

One agent passes control to another

The DBA wayL1 hands the ticket to L2

Supervisor pattern

A manager agent delegates to specialists

The DBA wayThe incident manager in a P1 war room

Reflection

The agent critiques and improves its own output

The DBA wayReviewing your own RCA before sending it

Fine-tuning

Retraining a model on your data to change its behaviour or style

The DBA wayChanging the engine, not the fuel

RAG vs fine-tuning

RAG adds fresh facts at question time; fine-tuning changes how the model behaves

The DBA wayUse RAG for changing data like runbooks; it needs no retraining

Zero-shot / few-shot

Asking with no examples / with a few examples in the prompt

The DBA wayFew-shot = showing a junior two sample tickets first

Temperature

Controls randomness; low = consistent, high = creative

The DBA wayKeep it low for SQL and factual answers

Observability / tracing

A log of every step, tool call and result

The DBA wayThe audit trail and AWR for agents

Interview Q&A

The 15 questions you are most likely to hear. Each answer takes under 30 seconds to say.

Try answering out loud first, then tap a question to check yourself.

1What is an AI agent?

An AI agent is an LLM that can plan, use tools, remember and act in a loop until it reaches a goal. A chatbot answers once; an agent does the work, like an on-call DBA who checks, fixes and verifies.

2What are the components of an agent?

Five: the model, instructions, tools, memory and planning. I remember them as "My Instructions Tell Me Plans".

3Agent vs workflow: what's the difference?

In a workflow, code fixes the steps. In an agent, the LLM decides the next step based on what it finds. If the steps never change, a workflow is cheaper and more reliable.

4Does the LLM execute the tools itself?

No. The LLM returns a structured request with the tool name and arguments. The application runs it and sends the result back. That is function calling.

5Explain ReAct.

Reason + Act. The agent alternates Thought, Action and Observation until it can answer. It's how a DBA tunes a query: think, run the plan, read it, think again.

6What is RAG and why use it?

Retrieval-Augmented Generation. You retrieve relevant chunks from your documents and give them to the LLM with the question. It grounds answers in your data, reduces hallucination and needs no retraining.

7RAG or fine-tuning?

RAG for facts that change, like runbooks and policies. Fine-tuning to change the model's style or behaviour on a narrow task. Most enterprise use cases start with RAG.

8What is MCP?

Model Context Protocol, an open standard that connects AI apps to tools and data in one way. The host runs clients; each client connects to one server; servers expose tools, resources and prompts over JSON-RPC 2.0. Think of it as the Oracle listener for AI.

9Tools vs resources vs prompts in MCP?

Tools are actions the model decides to call. Resources are read-only context the application supplies. Prompts are templates the user picks.

10How do you build agents on OCI?

Create an agent with instructions, attach tools (RAG for documents, SQL for tables, custom functions for APIs), connect a knowledge base, and expose it through an endpoint with sessions and guardrails.

11What does Oracle AI Database add for agents?

It stores vectors next to relational and JSON data, so one query can combine semantic search and SQL. Existing security like privileges, VPD and auditing still applies, and there is no separate vector store to keep in sync.

12HNSW or IVF?

HNSW is an in-memory graph: fastest and very accurate, but needs the vector memory pool. IVF partitions vectors on disk and scales to very large data with less memory.

13What is Select AI?

Natural language to SQL inside the database, using DBMS_CLOUD_AI and an AI profile. Actions like showsql show the generated SQL, runsql runs it, and narrate answers in plain English.

14How do you make agents safe in production?

Input and output guardrails, least-privilege tools, human approval for irreversible actions, iteration and token limits, and full tracing. The same discipline as change control on a production database.

15Single agent or multi-agent?

Start with one agent. Move to multi-agent (supervisor, handoffs) only when tasks need clear specialisation, because each extra agent adds latency, cost and debugging effort.

How to answer any question

Use the same three steps every time. They show both knowledge and real experience.

Step 1

Define it with the full form

"RAG stands for Retrieval-Augmented Generation. It retrieves relevant documents and gives them to the LLM before it answers."

Step 2

Give the DBA analogy

"It's like answering a performance question from the AWR report instead of from memory."

Step 3

Connect it to Oracle

"In Oracle AI Database, the chunks sit in a VECTOR column, and I find them with VECTOR_DISTANCE using an HNSW index."

Don't know an answer? Say what you do know and how you would find out: "I haven't used that in production, but it works like X, and I'd check the OCI documentation for Y."

Part of The DBA's Guide to Oracle Agentic AI Foundations. For the full picture in one diagram, see the Agentic AI Cram Board. Independent study notes, not official Oracle material.

DBA AGENTIC AI FOUNDATIONS

The DBA's Guide to Oracle Agentic AI Foundations · 1Z0-1157-26

Agentic AI Cram Board

One picture that connects all six exam modules, a 60-second way to explain it, and a sticky note per module. Colours match: each box in the diagram is the same colour as its note.

40 questions60 minutes65% = 26 correct$0 on MyLearn

The whole picture

Follow a request from left to right. Every exam module sits somewhere on this path.

M1Agent basics M2Reasoning & memory M3LangChain & Agents SDK M4MCP M5OCI agents M6Oracle AI Database

Explain it in 60 seconds

If someone asks "what is agentic AI?", walk the diagram in this order.

1. A user's request reaches the agent endpoint. Sessions keep the conversation, and guardrails check what goes in and comes out.M5
2. Behind it sits the agent: an LLM with instructions, memory and a plan. It doesn't just answer; it works toward a goal.M1
3. It thinks in a loop: Thought → Action → Observation. That pattern is ReAct. Big jobs can be split across a supervisor and specialist agents.M2
4. To act, it calls tools. The LLM only asks; the application runs them. RAG for documents, SQL for tables, custom functions for APIs.M5
5. Outside tools plug in through MCP, a standard plug like an Oracle listener: client to server over JSON-RPC, exposing tools, resources and prompts.M4
6. The knowledge lives in Oracle AI Database as vectors, found by meaning with VECTOR_DISTANCE and HNSW or IVF indexes. Select AI turns English into SQL.M6
7. Developers build all of this with LangChain, LangGraph or the OpenAI Agents SDK.M3

Sticky notes

One per module. Read the "Say it" line out loud; if you can explain that sentence, you know the module.

Module 1

What is an agent?

• Agent = LLM + Instructions + Tools + Memory + Planning
• Trick: "My Instructions Tell Me Plans"
• Loop: Perceive → Reason → Act → Observe → repeat
• LLM requests a tool; the app executes it (function calling)
• Fixed steps = workflow · LLM picks steps = agent
• Human-in-the-loop → on-the-loop → autonomous
• Grounding (tools, RAG) cuts hallucination

Say itAn agent is an LLM that plans and uses tools in a loop until the goal is met.

Module 2

How agents think

• CoT: step-by-step reasoning, no tools
• ReAct: Thought → Action → Observation
• Plan-and-Execute: full plan first
• Reflection: critiques its own output
• Supervisor delegates · Handoff gives control away · Agent-as-tool keeps control
• Memory: short = context window · long = vector store
• Guardrails on input + output, least privilege, human approval, max iterations, tracing

Say itReAct is the DBA way: think, run a query, read the result, think again.

Module 3

The toolbox

• Loader → Splitter → Embeddings → Vector store → Retriever
• Prompt template · Chat model · Output parser
• LCEL: prompt | model | parser
• LangGraph: nodes, edges, state, checkpointer → loops and branches
• Agents SDK: Agent, Runner, @function_tool, Handoff, Guardrails (tripwire), Sessions, Tracing

Say itStraight line is a chain; loops and branches need LangGraph.

Module 4

MCP

• Open standard, "USB-C of AI", fixes the M×N problem
• Host holds clients; each client ↔ one server
• T-R-P: Tools = model · Resources = app (read-only) · Prompts = user
• Client offers: Sampling · Roots · Elicitation
• JSON-RPC 2.0 · stdio local · Streamable HTTP remote
• tools/list to discover, tools/call to run
• Consent, least privilege, OAuth

Say itMCP is the Oracle listener for AI: one standard way for any app to reach any tool.

Module 5

Agents on OCI

• Agent → Tools → Knowledge base → Endpoint
• Documents → RAG tool (with citations)
• Tables → SQL tool (give schema description)
• Actions → custom function tool
• KB stores: Object Storage · OpenSearch · Oracle AI DB
• New files? Rerun the ingestion job
• Endpoint: sessions, guardrails (moderation, injection, PII), citations, trace
• Access via IAM policies + compartments

Say itDocuments go to RAG, tables go to SQL, actions go to a custom tool.

Module 6

Oracle AI Database

• VECTOR(768, FLOAT32) column
• VECTOR_EMBEDDING + ONNX model in DB
• DBMS_VECTOR_CHAIN: text → chunks → embeddings
• ORDER BY VECTOR_DISTANCE(..., COSINE) FETCH FIRST 5
• HNSW = in-memory graph · IVF = partitions, scale
• Exact = 100% · APPROX ... TARGET ACCURACY = index
• RAG: load → chunk → embed → store → embed question → search → LLM → answer
• Select AI: DBMS_CLOUD_AI + AI profile; showsql shows, doesn't run

Say itThe database is the agent's memory: vectors next to tables, under the security we already manage.

Exam day

Before you click Start

• 40 questions · 60 minutes · ~90 seconds each
• Need 26 correct (65%)
• Answer easy ones first, mark hard ones, come back
• Cut two wrong options, then choose
• Match keywords: "plan first", "critic", "read-only", "in-memory"
• Never leave a question blank
• Quiet room, ID ready, other apps closed

Say itI know the picture, so I can work out any question from it.

Independent study notes for Oracle Agentic AI Foundations Associate (1Z0-1157-26). Check current exam details and service names on Oracle MyLearn.

The DBA’s Guide to Oracle Agentic AI Foundations (Oracle AI Database)

Agentic AI Foundations Series · Part 6 of 6

Part 6: Oracle AI Database – The Agent's Memory

1Z0-1157-26 exam prep for Oracle DBAs

Oracle AI Database stores vectors right next to your tables, JSON, and graphs. An agent can search by meaning and run SQL in one place, under the security you already manage. For a DBA, this is home ground.

What is a vector, really?

An embedding is a list of numbers that captures meaning. "Tablespace full" and "no space left in datafile" use different words but land close together. "Listener down" lands far away. Searching by closeness = semantic search.

The new SQL pieces

• VECTOR data type – a column for embeddings, e.g. VECTOR(768, FLOAT32).
• VECTOR_EMBEDDING() – creates embeddings inside the database using an ONNX model you load with DBMS_VECTOR.LOAD_ONNX_MODEL. You can also call external models such as OCI Generative AI.
• DBMS_VECTOR_CHAIN – the pipeline helpers: UTL_TO_TEXT (extract), UTL_TO_CHUNKS (split), UTL_TO_EMBEDDINGS (embed).
• VECTOR_DISTANCE() – measures closeness. Order by it and fetch the top rows:

SELECT doc_id, chunk_text
FROM   runbook_chunks
ORDER  BY VECTOR_DISTANCE(embedding, :q_vec, COSINE)
FETCH  FIRST 5 ROWS ONLY;

Distance metrics: COSINE (most common for text), EUCLIDEAN, DOT, MANHATTAN, and HAMMING/JACCARD for binary vectors.

Vector indexes: think B-tree vs bitmap

Just as you choose index types for workloads, you choose vector indexes:

• HNSW – an in-memory graph of neighbors. Fastest and very accurate. Needs the vector memory pool (VECTOR_MEMORY_SIZE).
• IVF – groups vectors into partitions on disk. Scales to huge data with less memory.

Exact search compares every vector: 100% accurate, slower. Approximate search uses the index: FETCH APPROX FIRST 5 ROWS ONLY WITH TARGET ACCURACY 90.

Exam hook: HNSW = memory + speed. IVF = partitions + scale.

RAG in eight steps

Be ready to put these in order:

1. Load documents
2. Chunk them
3. Embed the chunks
4. Store in a VECTOR column and index it
5. Embed the user's question
6. Similarity search for the top-k chunks
7. Send question + chunks to the LLM
8. Return a grounded answer with sources

Select AI: talk to your data in English

• Package DBMS_CLOUD_AI; you create an AI profile (provider, credential, model, allowed tables).
• Actions: runsql (default, runs it), showsql (shows SQL only), explainsql, narrate (answer in plain language), chat.
• Select AI with RAG adds vector search over your documents; Select AI Agent builds agents with tools inside the database.

Why keep the agent's memory in the database?

One source of truth, transactional consistency, and your existing privileges, VPD, and auditing apply to every agent query. No separate vector store to sync.

Remember for the exam

• VECTOR type, VECTOR_EMBEDDING, VECTOR_DISTANCE; COSINE is the usual metric.
• HNSW in memory, IVF partitioned; approximate = index, exact = full compare.
• Select AI = DBMS_CLOUD_AI + AI profile; showsql shows without running.

Self-check

1. Which vector index lives in memory? (HNSW)
2. Which Select AI action shows the generated SQL without running it? (showsql)
3. In RAG, what happens right after chunking? (Embedding the chunks)

That's the series. Take the free practice exam on Oracle MyLearn next.

The DBA’s Guide to Oracle Agentic AI Foundations (OCI agent service)

Agentic AI Foundations Series · Part 5 of 6

Part 5: Building Agents on OCI – Tools, Knowledge Bases, and Endpoints

1Z0-1157-26 exam prep for Oracle DBAs

OCI gives you a managed agent service: you describe the agent, attach tools and data, and publish it through an endpoint. No servers to patch. (Oracle renames services often, so match the names to what you see in the course videos.)

The help-desk analogy

Picture building an "Ask the DBA team" assistant for your company.

• The agent is the assistant, with instructions like "Answer database questions politely; never share passwords."
• Its tools are what it can do.
• Its knowledge base is the library of runbooks and SOPs it reads from.
• The endpoint is the front door your users' apps knock on.

The tools (know which one fits which question)

Need	Tool to choose
Answer from PDFs, runbooks, SOPs, with citations	RAG tool + knowledge base
Answer "How many open SRs this week?" from tables	SQL tool (natural language to SQL; give it a schema description)
Create a ticket, call a REST API, run your function	Custom / function-calling tool
Use another service or agent	API endpoint / agent tool

Exam hook: Documents → RAG. Tables → SQL. Actions → custom function.

Knowledge bases: where the agent reads

A knowledge base points to a data store:

• Object Storage – drop files in a bucket; OCI chunks, embeds, and indexes them for you (service-managed).
• OCI Search with OpenSearch – bring an existing search index.
• Oracle AI Database vector store – bring your own vectors, with your own database security.

Files get in through a data source and an ingestion job. If you add new runbooks, rerun ingestion.

The endpoint: front door settings

• Sessions – keep conversation context across turns (with an idle timeout).
• Guardrails – content moderation, prompt-injection protection, PII protection.
• Citations and trace – show sources and the agent's steps.

The OCI pieces around it

• OCI Generative AI – the hosted chat and embedding models the agent uses; dedicated AI clusters for fine-tuning or private hosting.
• IAM policies and compartments – who can create agents and read the data. Same idea as granting privileges.
• Object Storage – usually where source documents live.

Remember for the exam

• RAG tool for documents, SQL tool for tables, custom tool for APIs.
• Knowledge base stores: Object Storage, OpenSearch, Oracle AI Database.
• Turn on sessions to remember context; guardrails live on the endpoint.

Self-check

1. Users ask questions about HR policy PDFs. Which tool? (RAG tool with a knowledge base)
2. How does the agent keep context between messages? (Sessions on the endpoint)
3. Name one guardrail available on the endpoint. (Content moderation, prompt-injection, or PII protection)

Next in the series: Part 6

The DBA’s Guide to Oracle Agentic AI Foundations (MCP)

Agentic AI Foundations Series · Part 4 of 6

Part 4: MCP – The USB-C of AI, in Plain Words

1Z0-1157-26 exam prep for Oracle DBAs

Model Context Protocol (MCP) is an open standard, started by Anthropic, that lets any AI app plug into any tool or data source the same way. Build a connector once; every MCP-aware app can use it.

The listener analogy

As a DBA you know this already. Before Oracle Net, every app needed its own way to reach the database. With a listener and a standard protocol, any client that speaks Oracle Net can connect.

MCP does that for AI. Without it, 5 AI apps × 10 tools = 50 custom integrations (the M×N problem). With MCP, each side implements the protocol once.

The three roles

• Host – the AI app the user works in (Claude Desktop, an IDE, your agent app). Like SQL Developer.
• Client – sits inside the host and holds one connection to one server. Like a single session.
• Server – exposes capabilities: a database server, a GitHub server, a file server. Like the database behind the listener.

Exam hook: Host holds clients; each client talks to exactly one server (1:1).

What a server offers: three primitives

This is the most tested part. Learn who controls each:

Primitive	Who controls it	DBA example
Tools	The model decides to call	run_sql, restart_listener
Resources	The application supplies	A schema file, alert log contents (read-only)
Prompts	The user picks	A saved "AWR analysis" template

Exam hook: T-R-P = Model, App, User. Tools act; resources are read-only context.

What a client offers back

• Sampling – the server asks the host's LLM to write something.
• Roots – the client tells the server which folders/files it may touch.
• Elicitation – the server asks the user for missing input.

Under the hood

• Messages are JSON-RPC 2.0.
• Two transports: stdio for a local server on the same machine, Streamable HTTP for remote servers (it replaced the older HTTP+SSE).
• Lifecycle: initialize → negotiate capabilities → work → shut down.
• Typical calls: tools/list to discover, tools/call to run.
• Security: user consent, least privilege, OAuth for remote servers, and watch for prompt injection hidden in tool results.

MCP vs function calling

Function calling is how one model asks for one tool. MCP is the standard plug that makes tools discoverable and reusable across apps. They work together.

Remember for the exam

• Host, client, server; client-to-server is 1:1.
• Tools = model, resources = app, prompts = user.
• JSON-RPC 2.0; stdio local, Streamable HTTP remote.

Self-check

1. Which primitive gives read-only context such as file contents? (Resources)
2. Which transport fits a server running on the same laptop? (stdio)
3. What message format does MCP use? (JSON-RPC 2.0)

Next in the series: Part 5

The DBA’s Guide to Oracle Agentic AI Foundations (LangChain and the OpenAI Agents SDK)

Agentic AI Foundations Series · Part 3 of 6

Part 3: LangChain and the OpenAI Agents SDK – Your Agent Toolbox

1Z0-1157-26 exam prep for Oracle DBAs

You don't need to write code for this exam. You need to know which building block does which job.

LangChain: the Lego set

LangChain is a framework of reusable pieces you snap together. Think of building a RAG app over your EBS runbooks:

1. Document loader reads the runbook PDFs.
2. Text splitter cuts them into small chunks.
3. Embeddings turn each chunk into a vector.
4. Vector store saves the vectors (Oracle AI Vector Search works here).
5. Retriever finds the chunks that match a question.
6. Prompt template builds the prompt with variables like {question} and {context}.
7. Chat model calls the LLM.
8. Output parser turns the reply into clean JSON or a list.

The glue is LCEL, LangChain Expression Language. It joins steps with a pipe, just like Unix: prompt | model | parser.

For agents, add tools (any function, often marked with @tool) and memory (chat history).

LangGraph: when you need loops and branches

LangGraph models an agent as a flowchart:

• Nodes = steps (call LLM, run tool).
• Edges = arrows between steps; conditional edges choose the next step.
• State = shared data passed around.
• Checkpointer = saves progress so you can pause for human approval and resume, much like a restartable patch session.

Exam hook: Straight line = chain (LCEL). Loops, branches, multi-agent = LangGraph.

OpenAI Agents SDK: small and simple

This SDK has only a handful of primitives:

• Agent – name + instructions + tools + model.
• Runner – runs the loop (run, run_sync, run_streamed).
• Function tool – a Python function turned into a tool with @function_tool.
• Handoff – pass control to another agent (triage → billing).
• Guardrails – input/output checks; a tripwire stops the run when triggered.
• Sessions – automatic conversation memory.
• Tracing – built-in log of every LLM call, tool call, and handoff.

It can also use MCP servers as tool sources and call agents as tools.

Remember for the exam

• Text splitter = chunking; retriever = fetching relevant chunks.
• LCEL pipe: prompt | model | parser.
• LangGraph = nodes, edges, state, checkpointer.
• Agents SDK: Agent, Runner, tools, handoffs, guardrails (tripwire), sessions, tracing.

Self-check

1. Which LangChain component breaks documents into chunks? (Text splitter)
2. Which OpenAI Agents SDK primitive executes the agent loop? (Runner)
3. What saves LangGraph state so a run can pause and resume? (Checkpointer)

Next in the series: Part 4

The DBA’s Guide to Oracle Agentic AI Foundations (Reasoning patterns, memory and guardrails)

Agentic AI Foundations Series · Part 2 of 6

Part 2: How Agents Think – Reasoning Patterns, Memory, and Guardrails

1Z0-1157-26 exam prep for Oracle DBAs

Agents follow a few well-known thinking styles. Learn the name, the one-line idea, and the keyword that gives it away in a question.

Five thinking styles, one DBA story

The problem: "Users say the month-end report is slow."

• Chain-of-Thought (CoT) – You think aloud before answering: "Slow report → maybe bad plan → maybe stale stats." No tools, just reasoning step by step.
• ReAct (Reason + Act) – You think, run something, look, think again. Thought: check the plan. Action: run DBMS_XPLAN. Observation: full table scan. Thought: check stats… This is the most tested pattern.
• Plan-and-Execute – You write the full plan first (1. AWR, 2. SQL plan, 3. stats, 4. fix), then work through it. Good for long tasks.
• Reflection – After writing your RCA, you review it yourself: "Did I prove the root cause or just guess?" The agent critiques and improves its own output.
• Routing – A triage step sends the issue to the right specialist: performance, storage, or EBS.

Exam hook: Thought-Action-Observation = ReAct. "Plan first" = Plan-and-Execute. "Critic" = Reflection.

When one agent isn't enough

Think of a war room during a P1 outage.

• Supervisor pattern – the incident manager assigns work to the DBA, network, and app teams, then combines their findings.
• Handoff – L1 support passes the ticket (with full history) to L2. L1 is now out of it.
• Agent as a tool – the incident manager asks the network team one question, gets the answer, and stays in charge.

Multi-agent gives specialization and parallel work, but costs more tokens, time, and debugging effort.

Memory: what the agent remembers

• Short-term – tonight's conversation, held in the context window. Gone when the session ends.
• Long-term – saved in a database or vector store and recalled by meaning.
• Sub-types you may see: episodic (past events), semantic (facts), procedural (how to do things).

Guardrails: change control for agents

You would never let a junior DBA run anything in production without controls. Same for agents:

• Input guardrails – block prompt injection, jailbreaks, off-topic requests.
• Output guardrails – catch PII leaks, toxic text, wrong formats, hallucinations.
• Least privilege – a read-only DB user for a reporting agent.
• Human approval for anything irreversible: delete, pay, send.
• Limits – max loop iterations, timeouts, token budgets.
• Tracing – log every step, like an audit trail.

Remember for the exam

• ReAct = Thought → Action → Observation.
• Handoff gives control away; agent-as-tool keeps control.
• Short-term = context window; long-term = vector store/DB.
• Guardrails sit on both input and output.

Self-check

1. An agent that drafts an answer, then critiques and rewrites it, uses…? (Reflection)
2. A manager agent delegating to specialist agents is the…? (Supervisor pattern)
3. Where does short-term memory live? (The context window)

Next in the series: Part 3

The DBA’s Guide to Oracle Agentic AI Foundations (AI agent basics)

← The DBA's Guide to Oracle Agentic AI Foundations

The DBA's Guide to Oracle Agentic AI Foundations · Part 1 of 6

What Is an AI Agent? Explained Like a DBA on Night Shift

Oracle Agentic AI Foundations Associate (1Z0-1157-26) exam prep · ~6 min read

An AI agent is an LLM that doesn't just answer, it works: it plans, uses tools, checks results, and keeps going until the job is done.

The night-shift analogy

Imagine two people on your on-call rota.

The first only answers questions. You ask "What does ORA-01555 mean?" and they explain snapshot too old. Useful, but they never touch the database. That's a plain LLM.

The second gets an alert: "Tablespace USERS is 95% full." They check free space, look at what's growing, add a datafile, verify, and update the ticket. Nobody told them each step. They decided. That's an AI agent.

The five parts of every agent

Think of the second DBA again:

1. Model (LLM) – their brain. It reasons and decides.
2. Instructions – the runbook and rules: "Never drop objects in production."
3. Tools – SQL*Plus, OEM, the ticketing system. Without tools, the brain can't act.
4. Memory – what happened earlier tonight (short-term) and lessons from past incidents (long-term).
5. Planning – breaking "fix the tablespace" into small steps.

Exam hook: M-I-T-M-P – "My Instructions Tell Me Plans." Model, Instructions, Tools, Memory, Planning.

The agent loop

Every agent runs the same loop: Perceive → Reason → Act → Observe → Repeat. It stops when the goal is met or a limit is reached.

One point people miss: the LLM never runs the tool itself. It says "call check_tablespace with name=USERS" as structured JSON. Your application runs it and hands back the result. This is function calling.

Agent or workflow?

If the steps are always the same (export, compress, copy), that's a workflow: code decides the order. If the path depends on what it finds, that's an agent: the LLM decides. Exam questions love this difference.

Autonomy is a dial: human-in-the-loop (approves each step), human-on-the-loop (watches, can stop it), or fully autonomous.

Remember for the exam

• Agent = LLM + instructions + tools + memory + planning, in a loop.
• The app executes tools; the LLM only requests them.
• Fixed steps = workflow. LLM chooses steps = agent.
• Grounding with real data (tools, RAG) reduces hallucination.

Self-check

1. Who executes a tool call: the LLM or the application? (Application)
2. A process that always runs the same 4 steps in order is a…? (Workflow)
3. Name the five agent components. (Model, instructions, tools, memory, planning)

Back toSeries overviewNext · Part 2How AI Agents Think: ReAct, Planning and Reflection for DBAs

The DBA’s Guide to Oracle Agentic AI Foundations

← The DBA's Guide to Oracle Agentic AI Foundations

The DBA's Guide to Oracle Agentic AI Foundations · Part 6 of 6

Oracle AI Database: Where Your AI Agent Keeps Its Memory

Oracle Agentic AI Foundations Associate (1Z0-1157-26) exam prep · ~6 min read

Oracle AI Database stores vectors right next to your tables, JSON, and graphs. An agent can search by meaning and run SQL in one place, under the security you already manage. For a DBA, this is home ground.

What is a vector, really?

An embedding is a list of numbers that captures meaning. "Tablespace full" and "no space left in datafile" use different words but land close together. "Listener down" lands far away. Searching by closeness = semantic search.

The new SQL pieces

• VECTOR data type – a column for embeddings, e.g. VECTOR(768, FLOAT32).
• VECTOR_EMBEDDING() – creates embeddings inside the database using an ONNX model you load with DBMS_VECTOR.LOAD_ONNX_MODEL. You can also call external models such as OCI Generative AI.
• DBMS_VECTOR_CHAIN – the pipeline helpers: UTL_TO_TEXT (extract), UTL_TO_CHUNKS (split), UTL_TO_EMBEDDINGS (embed).
• VECTOR_DISTANCE() – measures closeness. Order by it and fetch the top rows:

SELECT doc_id, chunk_text
FROM   runbook_chunks
ORDER  BY VECTOR_DISTANCE(embedding, :q_vec, COSINE)
FETCH  FIRST 5 ROWS ONLY;

Distance metrics: COSINE (most common for text), EUCLIDEAN, DOT, MANHATTAN, and HAMMING/JACCARD for binary vectors.

Vector indexes: think B-tree vs bitmap

Just as you choose index types for workloads, you choose vector indexes:

• HNSW – an in-memory graph of neighbors. Fastest and very accurate. Needs the vector memory pool (VECTOR_MEMORY_SIZE).
• IVF – groups vectors into partitions on disk. Scales to huge data with less memory.

Exact search compares every vector: 100% accurate, slower. Approximate search uses the index: FETCH APPROX FIRST 5 ROWS ONLY WITH TARGET ACCURACY 90.

Exam hook: HNSW = memory + speed. IVF = partitions + scale.

RAG in eight steps

Be ready to put these in order:

1. Load documents
2. Chunk them
3. Embed the chunks
4. Store in a VECTOR column and index it
5. Embed the user's question
6. Similarity search for the top-k chunks
7. Send question + chunks to the LLM
8. Return a grounded answer with sources

Select AI: talk to your data in English

• Package DBMS_CLOUD_AI; you create an AI profile (provider, credential, model, allowed tables).
• Actions: runsql (default, runs it), showsql (shows SQL only), explainsql, narrate (answer in plain language), chat.
• Select AI with RAG adds vector search over your documents; Select AI Agent builds agents with tools inside the database.

Why keep the agent's memory in the database?

One source of truth, transactional consistency, and your existing privileges, VPD, and auditing apply to every agent query. No separate vector store to sync.

Remember for the exam

• VECTOR type, VECTOR_EMBEDDING, VECTOR_DISTANCE; COSINE is the usual metric.
• HNSW in memory, IVF partitioned; approximate = index, exact = full compare.
• Select AI = DBMS_CLOUD_AI + AI profile; showsql shows without running.

Self-check

1. Which vector index lives in memory? (HNSW)
2. Which Select AI action shows the generated SQL without running it? (showsql)
3. In RAG, what happens right after chunking? (Embedding the chunks)

Previous · Part 5Building AI Agents on OCI: Tools, Knowledge Bases and EndpointsFinished the series?Take the free practice exam on Oracle MyLearn

How to Add an Email Address for Alerts in Oracle OEM 13c

How to Add an Email Address for Alerts in Oracle Enterprise Manager 13c

By Punit Kumar | Oracle DBA & Monitoring

Reliable monitoring includes making sure the right person receives the alert. When a new DBA joins the team or an on-call contact changes, email delivery should be part of the operational handover.

This guide covers recipient setup, notification schedules, incident rules, and delivery checks. Menu labels may vary slightly by release; the instructions follow Oracle OEM 13c Release 5 documentation.

Check all three: the email address, notification schedule, and incident rule. Adding an address alone does not complete alert routing.

1. Add the Email Address

1. Open your username menu and select Enterprise Manager Password & Email.
2. Click Add Another Row and enter the address.
3. Choose Email (Long) for detailed notifications.
4. Click Apply.

For another administrator, a Super Administrator can update the email under Setup → Security → Administrators.

2. Check the Notification Schedule

Go to Setup → Notifications → My Notification Schedule. Include the new address in the required time periods and save.

Match the coverage to the support arrangement. Choose 24×7 delivery when continuous coverage is required, or agree on the appropriate periods with the on-call team.

3. Update the Incident Rule

Navigate to Setup → Incidents → Incident Rules.

1. Edit the relevant rule set and verify its target scope.
2. Select the appropriate rule and edit its notification action.
3. Add the OEM administrator account to the email recipients, using the appropriate Email To or Email Cc field.
4. Review the event type, severity, and action conditions.
5. Complete the wizard and save the rule set.

Recipients need appropriate privileges for the underlying targets or events. The person editing the rule also needs the required rule-set permissions.

4. Verify the Mail Server

Open Setup → Notifications → Mail Servers and use Test Mail Servers. SMTP configuration requires Super Administrator privileges. Its sender address is separate from the alert recipient.

A successful mail-server test is only one part of validation. Confirm that the intended alert also reaches the expected inbox.

5. Troubleshoot Missing Emails

Symptom	Suggested Check
Mail-server test fails	Ask the mail team to check relay access, authentication, connectivity, and the test timestamp.
Only the new recipient misses alerts	Recheck the address, schedule, recipient selection, and spam or quarantine folders.
Test mail arrives, but alerts do not	Review target scope, event criteria, severity, action conditions, and recipient privileges.
Warning emails are missing	The default all-targets incident rule set does not email warnings. Review the relevant conditions.

6. Validate and Document the Change

OEM supports rule-set simulation using existing events to inspect rule behavior. Follow this with a controlled delivery check appropriate to your environment.

• Record the test target, event, severity, and time.
• Confirm receipt in the intended inbox.
• Compare the message with the expected alert.
• Restore any temporary test settings.
• Record the outcome in the change ticket or team runbook.

Avoid disrupting production simply to generate an alert. Use an approved test environment or an appropriate naturally occurring event.

Oracle References

• Oracle Enterprise Manager 13c Release 5 — Using Notifications
• Oracle Enterprise Manager 13c Release 5 — Using Incident Management