BrainyBeeBrainyBee
ExploreBlogStart Studying
HomeDeveloping AI Apps and Agents on Azure (AI-103)Quick Note — Choose appropriate memory, tool, and knowledge integration services for agent solutions
LO Quick Note949 words

Quick Note — Choose appropriate memory, tool, and knowledge integration services for agent solutions

AI-103 › Unit 1: Plan and manage an Azure AI solution › Choose the appropriate Foundry services for generative AI and agents › Choose appropriate memory, tool, and knowledge integration services for agent solutions

Quick Note — Choose appropriate memory, tool, and knowledge integration services for agent solutions

An agent is asked to do three things: recall a user's stated preferences months later, answer from a corpus the platform team already indexes, and keep a durable record of every conversation for audit. A team that reaches for one mechanism — usually memory — satisfies none of them properly. These are three different stores with three different jobs, and the exam rewards telling them apart.

Retrieval target

Objective
Choose appropriate memory, tool, and knowledge integration services for agent solutions
Mode
Closed-book recall
Target time
5 minutes
Escalation
Open Microsoft Learn after a miss

Decision anchors

PromptCompact answer
Memory toolDurable recall of facts about the user across sessions. In preview — no SLA, not recommended for production. Not a grounding corpus and not an audit record.
File SearchGrounds an agent in files uploaded to it, using vector search. Right for documents a user hands the agent; wrong for a governed enterprise corpus that already has a pipeline.
Azure AI Search toolGrounds agents "with data from an existing Azure AI Search index" — no re-ingestion, and the owning team's enrichment and relevance tuning keep applying. The answer whenever a stem says an index is already maintained.
Foundry IQ knowledge baseOne or more knowledge sources, an optional LLM for planning and synthesis, and retrieval parameters. Use it when several collections must be planned and merged by the service, and when grounding must be permission-aware.
Conversation stateThe record of what was said. Use bring your own resources — your own Azure Cosmos DB — when retention and control must sit with your organization. store=false is the different requirement: do not persist at all.
ToolboxA curated set of tools defined once and exposed through a single MCP-compatible endpoint, consumable by any MCP-compatible runtime. The recommended way to give agents tools. Versioned: create a version, test it, promote it to default.
Which tool typeBuilt-in — the service executes (web search, code interpreter, file search, Azure AI Search). OpenAPI tool — an external HTTP API with a specification. Function calling — your application executes and returns the result. MCP — tools shared across agents or owned by another team.

Read the answers once, then cover the right-hand column and reconstruct each one from the prompt. A useful answer names the requirement, the capability that satisfies it, and the nearest alternative it rejects. If you can only recognize the answer after seeing it, retrieval is not yet secure.

Ask who runs it and where the knowledge lives

The service runs it → built-in tool. A described external API → OpenAPI tool. Your code runs it → function calling. Another team owns it → MCP. And for knowledge: files handed to the agent → File Search; an index you already run → the Azure AI Search tool; several governed collections → a knowledge base.

Ninety-second explanation

Without notes, explain:

  1. Distinguish memory from conversation state in one sentence each.
  2. A corpus is already indexed and tuned by another team — what do you attach, and why not File Search?
  3. What preview status must a readiness review record, and what follows from it?
  4. What does toolbox versioning let you do that editing a tool in place does not?
  5. Which knowledge-source kind supports per-user permission inheritance?

Then check yourself against current Microsoft Learn. Record the missing decision rule, not merely the missed product name, in your error log.

Loading flashcards…

When to go deeper

Go deeper when the design depends on agent identity and authentication for a tool — key-based, Microsoft Entra via managed identity, or OAuth On-Behalf-Of passthrough, which is what makes retrieval respect the calling user's own permissions.

Source and freshness

Written against current Microsoft Learn documentation for the AI-103 skills measured (16 April 2026). Reviewed 2026-08-20. Microsoft Learn controls changing product contracts — availability, limits, preview status, naming, and retirement dates move, and this note is deliberately compact.

All Developing AI Apps and Agents on Azure (AI-103) Study Resources

Related Notes

  • Choose appropriate memory, tool, and knowledge integration services for agent solutions2,815 words
  • Choose an appropriate method for retrieval and indexing2,778 words
  • Quick Note — Choose an appropriate method for retrieval and indexing888 words
  • Choose an appropriate model for each task, including LLMs, small language models, multimodal models, and Foundry Tools3,097 words
  • Quick Note — Choose an appropriate model for each task, including LLMs, small language models, multimodal models, and Foundry Tools1,041 words
  • Choose the appropriate Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing2,733 words
  • Quick Note — Choose the appropriate Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing901 words
  • Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling2,891 words
  • Configure safety filters, guardrails, risk detection, and content moderation2,795 words
  • Govern agent behavior with oversight modes, constraints, and tool-access controls2,863 words
  • Implement auditing through trace logging, provenance metadata, and approval workflows2,624 words
  • Configure security including managed identity, private networking, keyless credentials, and role policies2,695 words

Ready to study Developing AI Apps and Agents on Azure (AI-103)?

Practice tests, flashcards, and all study notes — free, no sign-up.

Start Studying

Ready to study Developing AI Apps and Agents on Azure (AI-103)?

Practice tests, flashcards, and all study notes — free, no sign-up needed.

Start Studying — Free
Developing AI Apps and Agents on Azure (AI-103) ResourcesExplore All HivesBlogHome

© 2026 BrainyBee. Free AI-powered exam prep.

Choose appropriate memory, tool, and knowledge integration services for agent solutions — quick retrieval

Card 1 of 5

Front of flashcard 1 of 5

Memory vs conversation state

easy

Memory (preview) = durable recall of facts about the user across sessions. Conversation state = the record of what was said, which you can hold in your own Cosmos DB for retention and control. Retention is not recall.

memorystate

Choose appropriate memory, tool, and knowledge integration services for agent solutions — quick retrieval

Card 1

Front

Memory vs conversation state

Back

Memory (preview) = durable recall of facts about the user across sessions. Conversation state = the record of what was said, which you can hold in your own Cosmos DB for retention and control. Retention is not recall.

Card 2

Front

File Search vs Azure AI Search tool

Back

File Search — documents uploaded to the agent, vector search, no pipeline. Azure AI Search tool — grounds on an existing index you already maintain and tune. Never re-upload a corpus that is already indexed.

Card 3

Front

Toolbox

Back

A curated tool set exposed on one MCP-compatible endpoint, consumable by any MCP-compatible runtime — the recommended way to give agents tools. Versioned: create, test, promote to default.

Card 4

Front

Tool type by executor

Back

Built-in = service executes. OpenAPI = external HTTP API with a spec. Function calling = your app executes. MCP = shared or third-party tools. The stem names the executor.

Card 5

Front

Preview tools

Back

Memory and web search are in preview — no SLA, not recommended for production. Preview status is per tool, not per catalogue: the built-in list mixes GA and preview entries.

Choose appropriate memory, tool, and knowledge integration services for agent solutions — quick retrieval

Card 1

Front

Memory vs conversation state

Back

Memory (preview) = durable recall of facts about the user across sessions. Conversation state = the record of what was said, which you can hold in your own Cosmos DB for retention and control. Retention is not recall.

Card 2

Front

File Search vs Azure AI Search tool

Back

File Search — documents uploaded to the agent, vector search, no pipeline. Azure AI Search tool — grounds on an existing index you already maintain and tune. Never re-upload a corpus that is already indexed.

Card 3

Front

Toolbox

Back

A curated tool set exposed on one MCP-compatible endpoint, consumable by any MCP-compatible runtime — the recommended way to give agents tools. Versioned: create, test, promote to default.

Card 4

Front

Tool type by executor

Back

Built-in = service executes. OpenAPI = external HTTP API with a spec. Function calling = your app executes. MCP = shared or third-party tools. The stem names the executor.

Card 5

Front

Preview tools

Back

Memory and web search are in preview — no SLA, not recommended for production. Preview status is per tool, not per catalogue: the built-in list mixes GA and preview entries.