AB-620 open-book strategy
Microsoft role-based exams like AB-620 give you a restricted Microsoft Learn pane during the exam. This page is the plan I used: which pages to open, what to Ctrl+F, and which questions aren't worth searching. Every page and term was checked against live Learn in September 2026. Pages change, so re-verify before you rely on it.
Learn is a verification tool, not a discovery tool. Use it to confirm a documented limit, prerequisite or known limitation you half-remember. Never use it for judgment, "best approach", or ordering questions. That rule comes from my AB-100 attempt, where searches for judgment and ordering questions found nothing useful.
Why AB-620 is more Learn-friendly than AB-100
Many of the facts that are easy to forget are stated word for word on a single Copilot Studio page: 25 websites, 2 × 15 tables, one index, 15 credits, 512 MB, Official source, the Fabric limits. On AB-100 those facts were buried; here they're in "Known limitations" and limit tables. A targeted lookup costs about 60 seconds and turns a coin-flip into a sure point.
Exam-room mechanics
- Learn opens in a restricted pane inside the exam. You can have several Learn tabs; community Q&A is blocked.
- Ctrl+F / Cmd+F searches the Learn page, not the question. Always navigate to the page, then Ctrl+F the term below.
- Case studies can't be reopened once you leave them. Do any case-study lookups before you leave that section.
- Use in-site Copilot Studio search (the search box on the Copilot Studio docs), not global Learn search. In practice, in-site search takes about 60 s; global search is noise.
The core loop: answer first, look up last
- First pass: answer every question from memory at about 45 s each. If a question hinges on a lookup-able fact (table below), pick your best guess, mark it for review, and write the lookup code on the whiteboard/notepad (e.g.
K1). - Review pass: with the remaining time, run only the marked lookups, cheapest first.
- Hard stops: 90 s per lookup; about 12–15 min total. If the first page + Ctrl+F doesn't hit, keep your guess and move on.
Lookups can never cost you an unanswered question, because you already answered everything.
Decision tree
Does the answer hinge on a NUMBER, LIMIT, PREREQUISITE, or "can/can't" fact?
├── YES → Is it in the lookup table below?
│ ├── YES → mark for review; look it up in the review pass (≤ 90 s)
│ └── NO → one in-site Copilot Studio search in the review pass; no hit in top 3 → keep guess
└── NO → Is it ORDERING, "which should you do / best approach", mapping of roles, or a case-study judgment?
└── DO NOT SEARCH. Use the decision rules. Move on.Tabs to open at the start (in this order)
| # | Tab | URL (under learn.microsoft.com/en-us/microsoft-copilot-studio/ unless full) |
|---|---|---|
| 1 | Knowledge sources (highest yield) | knowledge-copilot-studio |
| 2 | Add other agents (child/connected/Fabric limitations) | authoring-add-other-agents |
| 3 | Azure AI Search knowledge | knowledge-azure-ai-search |
| 4 | Computer use | computer-use |
| 5 | REST API tools | agent-extend-action-rest-api |
| 6 | Evaluation methods | analytics-agent-evaluation-overview |
| 7 | Copilot Studio docs home (for in-site search) | /microsoft-copilot-studio/ |
Open the others only on demand: MCP, A2A, Foundry agent, App Insights, pipelines, authentication, flows, HTTP node.
Lookup table (page → Ctrl+F → what you're confirming)
Say the answer column to yourself before the exam. If you're sure, don't look it up.
Tab 1: Knowledge sources (knowledge-copilot-studio)
| Code | Cue in the question | Ctrl+F | Expected answer |
|---|---|---|---|
| K1 | How many websites / SharePoint sources? | 25 | 25 generative; 4 classic |
| K2 | Classic Dataverse knowledge limits | 15 tables | 2 sources × 15 tables |
| K3 | "Official source" option greyed out | Official source | Classic orchestration only |
| K4 | Answers blocked / "can't find" with ungrounded off | ungrounded | Uncited answers withheld → add citation instructions; Fallback |
| K5 | Bing Custom Search / custom data in a generative agent | Bing Custom Search | Generative answers node → Classic data |
| K6 | Large SharePoint files | 512 | 200 MB; 512 MB for PDF/PPTX/DOCX (tenant graph grounding) |
| K7 | Tenant graph grounding requirements | tenant graph | Authenticate with Microsoft; extra cost |
| K8 | More than 25 sources | 25 | Description-based filtering; uploaded files don't count |
Tab 2: Add other agents (authoring-add-other-agents)
| Code | Cue | Ctrl+F | Expected answer |
|---|---|---|---|
| M1 | Anything "Fabric Data agent can/can't" | Known limitations | No Redirect, no / reference, no M365 Copilot main agent |
| M2 | Connected agent inside another connected agent | connected agent (Known limitations) | A main agent with connected agents can't itself be connected |
| M3 | Citations missing after a hop | citation | Might not be maintained |
| M4 | Sub-agent and general knowledge | general knowledge | Inherits the main agent's setting |
| M5 | Too many tools/topics | 30 | ~30–40 choices → split into connected agents |
Evaluation + Fabric: analytics-agent-evaluation-intro → Ctrl+F Fabric → not supported.
Tab 3: Azure AI Search (knowledge-azure-ai-search)
| Code | Cue | Ctrl+F | Expected answer |
|---|---|---|---|
| S1 | How many indexes per connection | only one | One vector index |
| S2 | No citations from AI Search | metadata_storage_path | Needs a full-URL field |
| S3 | Private endpoint / network-isolated search | virtual network | Power Platform VNet support |
| S4 | Keyless / governed auth | service principal | Service principal or Entra ID integrated |
Tab 4: Computer use (computer-use)
| Code | Cue | Ctrl+F | Expected answer |
|---|---|---|---|
| C1 | Credits for N steps | Copilot Credits | 5 per step standard, 15 premium |
| C2 | Restrict what it can act on | allow | Access control allow list |
| C3 | HTTPS-only | Enforce HTTPS | Enforce HTTPS setting |
| C4 | Stored sign-in secret | Key Vault | Stored credentials (Key Vault) |
Tab 5: REST API tools (agent-extend-action-rest-api)
| Code | Cue | Ctrl+F | Expected answer |
|---|---|---|---|
| R1 | Solution field left blank | solution | Solution auto-created (action name + default publisher) |
| R2 | Blank parameter descriptions | description | Must be filled in; names/types fixed by spec |
| R3 | Per-user delegated access | OAuth 2.0 | OAuth 2.0 |
Tab 6: Evaluation (analytics-agent-evaluation-overview)
| Code | Cue | Ctrl+F | Expected answer |
|---|---|---|---|
| E1 | Which grader for X | General quality / Compare meaning / Custom | Grader by what "correct" means; refusals → Custom |
| E2 | Result marked Invalid | Invalid | Missing expected answer |
On-demand pages
| Code | Page | Ctrl+F | Expected answer |
|---|---|---|---|
| P1 | agent-extend-action-mcp | resources | MCP = tools + resources; needs generative orchestration |
| P2 | add-agent-agent-to-agent | chat history / custom connector | A2A sends full history + contextId; works in VNet |
| P3 | add-agent-foundry-agent | Activity | Needs the Activity endpoint; project endpoint + Agent ID |
| P4 | advanced-bot-framework-composer-capture-telemetry | designMode / random | Exclude test chats; anonymous = random user ID |
| P5 | https://learn.microsoft.com/en-us/power-platform/alm/pipelines | Managed Environment / delegated | Targets must be Managed; delegated = SP + approval |
| P6 | configuration-end-user-authentication | Authenticate with Microsoft | Teams/M365 only; publish to apply |
| P7 | flows-overview | When an agent calls the flow / capacity | Required trigger; Copilot Studio capacity |
| P8 | authoring-http-node | 30 / Continue on error | 30 s default timeout; handle errors yourself |
Never search these (answer from rules)
| Question shape | Why not | Use instead |
|---|---|---|
| Ordering / sequence | Learn describes steps, not the exam's numbered order (searching these didn't pay off on AB-100) | App Insights: resource → connection string → enable → publish. Agents SDK: publish → channel → config → SDK → validate → deploy. AI Search: Add knowledge → connection → auth → index → add. REST: spec → auth → operations → connection. RAI: DLP → moderation → prompt mods |
| Connected-agent role mapping | Loosely worded key | Publish → callable; Add → collaboration; Connections → invocation |
| "Best approach" / case-study design | Docs don't prescribe combinations | Integration shape: indexed → Copilot connector; live → connector knowledge; write → tool; no API → computer use; foreign agent → A2A |
| Disclaimers / tone / compliance placement | Judgment | Instructions / prompt modifications + DLP; never per-topic edits |
| Model selection for prompts | Judgment | Prompt model settings (Foundry catalog), not instructions |
Final 60-second checklist
- [ ] Open tabs 1–7 as soon as the exam starts.
- [ ] Pace ≈ 45 s/question; strike unlimited / never / only / nothing options first.
- [ ] Mark lookup questions and write their code (K1, M1, …); answer them anyway.
- [ ] Do case-study lookups before leaving the case study.
- [ ] Review pass: marked lookups only, ≤ 90 s each, ≤ 15 min total.