Skip to content

AB-620 cheat sheet ​

One page for the last review before the exam. The study guide explains the reasoning, and the open-book strategy covers what to look up during the exam.

Pass = 700 · INTEGRATE 40–45% · PLAN 30–35% · MANAGE 20–25% · Default = generative orchestration

1. Exam technique ​

HabitFix
RushingTake ~45 s. Strike unlimited / never / always / only / nothing-optional first
Ordering itemsPrerequisite first. For each step ask: what must already exist?
Multi-select second pickTest it against every stem constraint: no API → no connector; retrieval ≠ model choice; no "convert" step

2. Sequences ​

SetupOrder
App Insightsresource → connection string (Settings › Advanced) → enable logging → publish
AI Searchadd knowledge → Azure AI Search → connection → auth + endpoint → index → add
REST wizardadd tool → spec + solution → auth → operations → connection → test
Agents SDKpublish → enable channel → get config → implement SDK → validate → prod
Responsible AIDLP → content moderation → prompt modifications

3. Easy to get wrong (know instantly) ​

CueAnswer
Connected agent actionspublish → callable · Add → collaboration · Configure connections → invocation. An agent is never a knowledge source
No API, must automate a UIEnable Computer use; watch the test pane's live remote session (5 credits/step, 15 premium)
Governed model for a promptFoundry model catalog setting in the prompt, never an instruction line

4. Choose the integration ​

NeedChoose
Indexed third-party contentCopilot connector
Live LOB data, no indexConnector as real-time knowledge
Write back to a systemConnector tool
Tool server that changesMCP: tools + resources, generative only
OpenAPI specREST tool: blank solution = auto-created; fill every parameter description; per-user → OAuth 2.0
No API at allComputer use: UI-only, autonomous
Agent on another platformA2A: sends full chat history; works in a VNet
Agents SDK agentActivity Protocol
Foundry agentProject endpoint + Agent ID
Fabric data agentNo redirect · no M365 Copilot · no evaluation
Same team builds itChild agent
Other team, own ALM or model, reuseConnected agent: can't nest; inherits general knowledge OFF; citations might not survive; ~30–40 choices before splitting

5. Knowledge ​

FactValue
Websites, generative / classic25 / 4 (SharePoint 25 generative)
Dataverse knowledge2 sources × 15 tables
More than 25 sourcesFiltered by description; uploaded files excluded
Azure AI Search1 index per connection · URL field for citations · private endpoint → Power Platform VNet
SharePoint file size200 MB (512 MB for PDF/PPTX/DOCX)
Ungrounded answers OFFUncited answers are withheld → add citation instructions
Classic-only"Official source" · Bing Custom Search → Classic data node

6. Orchestration and identity ​

  • Descriptions beat trigger phrases. Agent decides → generative orchestration; fixed step → tool node
  • Ignored under generative: Conversational boosting, Multiple Topics Matched · custom entities can't be inputs
  • End all topics = cancel the plan · Reset Conversation ≠ clear history
  • Teams/M365 → Authenticate with Microsoft · need User.AccessToken → manual auth · no auth = anyone with the link
  • Auth changes need a publish · D365 Customer Service handoff ✗ Authenticate with Microsoft

7. Flows and topics ​

  • Trigger When an agent calls the flow + Respond to the agent · failing flow → check run history first
  • Cloud flow → agent flow is one-way · multistage approval = AI + manual + conditions, no ALM
  • Capacity: topic = classic answer · orchestrator = autonomous action · test pane = free
  • HTTP node: headers for auth, 30 s timeout, Continue on error
  • Generative answers: disclaimers go in the prompt modification · clear Send a message for cards · node moderation wins
  • Regex case-insensitive = (?i) · Secrets → env var → Key Vault

8. Monitor and evaluate ​

  • App Insights: customEvents · designMode == "False" · anonymous users = random ID per conversation · block via data policy
  • Graders: General quality (no expected answer) · Compare meaning (50) · Exact · Similarity · Tool use · Keyword · Safety (0 = strict) · Custom for business rules · no expected answer → Invalid

9. ALM ​

  • Custom solution → add agent → export (managed is an export option; "convert first" is fake)
  • Env vars → pipelines → targets must be Managed Environments
  • Delegated deployments = approval + service principal · no cross-tenant · no stage skip · Upgrade import

10. Harness (new) ​

Standard = rule-based (this exam) · GitHub Copilot = goal/files/skills/memory · Copilot chat = extends M365 Copilot Chat

Personal study notes written from official documentation. Not affiliated with Microsoft or GitHub. Contains no exam questions.