… 4 unchanged lines …
  - You point each agent instance at a product line and an opportunity segment — for example Hot opportunities with estimated revenue over a threshold. Only opportunities matching the selection criteria get researched, and only high and medium importance ones appear in the seller view.
  - Up to **10 active agent instances** per organisation, each with its own profile, selection criteria and knowledge-source filters. They all draw from the same capacity pool and share one Copilot Studio knowledge base.
  - Research refreshes **every three days by default**; the admin can set High (daily) or Low (every seven days). Edits to Account, Contact, Est. close date, Actual close date or Est. revenue trigger an immediate re-research.
- - Eleven built-in **risk criteria** — no recent engagement, unresponsive champion, not multithreaded, missing stakeholder roles, close date deviation, stalled in stage, objections raised, missing BANT info, aging opportunity, competitor mention, negative news. Thresholds, roles and per-stage values are all editable, and each can be switched out of the assessment.
+ - Eleven built-in **risk criteria** — no recent engagement, unresponsive stakeholder, not multithreaded, missing stakeholder roles, close date deviation, stalled in stage, objections raised, missing BANT info, aging opportunity, competitor mention, negative company news. Thresholds, roles and per-stage values are all editable, and each can be switched out of the assessment.
+ - **Updated 23 October 2026:** the old unresponsive-champion criterion is now **Unresponsive stakeholder**, where Champion is the default but you can select Influencer, Decision Maker or several roles at once.
+ - Stage-based thresholds are driven by a **business process flow** chosen in the Opportunity assessment settings: the standard Sales Process (Qualified, Develop, Propose, Close) by default, **None** to switch stage-based filtering off, or any custom flow the organisation has built. No recent engagement, close date deviation and stalled in stage take a different threshold per stage; not multithreaded and the stage-dependent checks key off the same stages.
  - Six built-in **importance criteria** — existing customer, high account win history, Top 500 account, strategic references, large deal size, executive visibility. Same deal: editable thresholds, toggle per criterion.
  - Custom criteria on both sides are defined by name, description and mapped opportunity (or related-table) fields, tuned with natural-language instructions.
  - It depends on **predictive opportunity scoring**. If the model isn't configured in the environment, starting the agent configures it for you.
    … 18 unchanged lines …
  - Whether to run one agent or several — enterprise versus mid-market, different product lines — remembering selection criteria must be distinct per instance.
  - Microsoft 365 Services consent versus server-side synchronisation. This is a data-protection decision as much as a technical one, and the consent route is one-way.
  - Refresh frequency against capacity: daily on a large segment is a very different bill from every seven days.
- - Which risk criteria stay on, and what the thresholds and stage-specific values are. Stalled-in-stage and close-date deviation need the client's real cycle times, not the defaults.
+ - Which business process flow drives stage-based risk (standard Sales Process, a custom flow, or none), and which risk criteria stay on with what thresholds and stage-specific values. Stalled-in-stage and close-date deviation need the client's real cycle times, not the defaults.
  - Which stakeholder roles map to your organisation's actual role names, rather than leaving the built-in Champion and executive assumptions in place.
  - Objection keywords and competitor names, which are only as good as the list someone maintains.
  - Which importance criteria reflect how the business genuinely prioritises, and whether custom criteria are needed for strategic accounts or key product lines.
    … 7 unchanged lines …
  - Connected skills is still marked preview, and the Recommended Actions section needs the separate Recommended Actions Agent enabled — so a demo can show no recommended actions at all and look broken.
  - The prerequisites page still labels this agent as preview in its related links while the agent's own articles no longer carry a preview banner. Treat the specific capability you're promising as the thing to verify, not the agent as a whole.
  - Predictive opportunity scoring gets configured silently when you start the agent. If the client has opinions about scoring models, they'll want to know that happened.
+ - A client with a heavily customised business process flow should pick it deliberately: the flow chosen for assessment decides which stages you can set thresholds against, so changing it later means revisiting the numbers.
  - Ten instances sharing one capacity pool means one badly scoped instance on a daily refresh can starve the others.
  - Email insights depend on sender-address-to-contact mapping. Sellers who email from a shared mailbox, or contacts stored without their real address, produce nothing and no error.
  - Changing Est. revenue or close date triggers an immediate re-research, so a seller doing routine housekeeping on a hundred records can generate a burst of consumption.
    … 10 unchanged lines …
  
  ---
  
- *Worth revisiting once connected skills leaves preview and the criteria set settles. Last refreshed 2026-09-23: source repointed after Microsoft renamed Opportunity Research Agent to Sales Opportunity Agent, plus new guidance on the initial-run capacity spike.*
+ *Worth revisiting once connected skills leaves preview and the criteria set settles. Last refreshed 2026-10-28: unresponsive stakeholder roles and business-process-flow-based stage thresholds added.*
  

    … 11 unchanged lines …
  - Email insight gathering runs one of two ways: Microsoft 365 Services consent, where the agent reads the opportunity owner's mailbox directly every six hours without storing it — **and that consent can't be revoked** — or server-side synchronisation, where it only sees mail already synced into Dataverse.
  - Email insights need a real external email on the opportunity whose sender address maps to an associated contact. No mapped contact, no insight.
  - Insights are generated in the **agent's** configured language; section headings render in the user's language. A German-language agent with English users produces exactly that mix.
+ - On activation the agent performs an **initial run across every open opportunity matching the selection criteria**, to build baseline insights. After that, consumption tracks segment size and refresh frequency. The first bill is therefore not representative of the steady-state one.
+ - **Sales Close Agent is a different product.** Microsoft renamed the Opportunity Research Agent to Sales Opportunity Agent in September 2026, and several article paths still carry the old `opportunity-research` or `sales-close-agent` names. When following links or reading older material, check which agent you're actually looking at.
  - Runs on Copilot Studio capacity under consumption-based billing, and needs the tenant-level Power Platform prerequisites done once: Copilot Studio capacity, cross-region data movement accepted, AI prompts on, AI insight cards on, AI Agents on.
  - Data policies must allow the Copilot Studio, Direct Line and knowledge-source connectors, plus SharePoint/OneDrive or document connectors if internal documents are in scope.
  - Sellers need read on Connector at user level to give the Microsoft 365 consent. Salesperson and Sales Manager already have it; custom roles won't.
    … 27 unchanged lines …
  - Ten instances sharing one capacity pool means one badly scoped instance on a daily refresh can starve the others.
  - Email insights depend on sender-address-to-contact mapping. Sellers who email from a shared mailbox, or contacts stored without their real address, produce nothing and no error.
  - Changing Est. revenue or close date triggers an immediate re-research, so a seller doing routine housekeeping on a hundred records can generate a burst of consumption.
+ - The initial run is a one-off spike nobody budgets for. Activate against a large segment and the agent works through the whole backlog before it settles into the refresh schedule — which looks like runaway consumption if you haven't warned anyone it's coming.
+ - The documentation set was renamed mid-September 2026 and cross-references between Sales Opportunity Agent and Sales Close Agent are still being untangled upstream. Confirm the agent name on the page you're reading before quoting a prerequisite from it.
  
  ## Consultant notes
  
  - Scope the criteria configuration as a workshop, not a setting. The defaults produce plausible-looking risk flags that don't match the client's sales process, and the first thing a sales director says in UAT is "that deal isn't at risk". Bring their real cycle times and stage definitions and set the thresholds in the room with them.
  - Raise the irrevocable email consent early and in writing. It's the one decision on this feature that can't be walked back, and it tends to reach the data-protection lead late, after sellers have already been told to click the banner.
- - Pilot on a segment small enough that the Copilot Studio bill is boring. Consumption is driven by segment size times refresh frequency, and the temptation to turn it on for all opportunities at daily refresh is exactly how clients get a surprise invoice in month two.
+ - Pilot on a segment small enough that the Copilot Studio bill is boring. Consumption is driven by segment size times refresh frequency, plus a one-off initial run over the whole matching backlog, and the temptation to turn it on for all opportunities at daily refresh is exactly how clients get a surprise invoice in month two. Tell the client about the initial run before you switch it on — it's the single most common "why is this so expensive" conversation on this feature.
  - The agent is a mirror on CRM data quality, and that surfaces awkwardly post-go-live. Where stage values are inconsistent or stakeholder connections aren't maintained, the agent's output is visibly wrong and sellers blame the tool. Audit the data before enabling, and use the first month's risk flags as a data-quality report rather than a seller performance one.
  - Sequencing matters: the tenant-level Power Platform prerequisites, capacity purchase and data-policy connector allowances all sit outside the Sales project and involve people who aren't in your standups. Start them the week you agree the feature, not the week you configure it.
  
  ---
  
- *Worth revisiting once connected skills leaves preview and the criteria set settles — both sides of the model are new and Microsoft is still adding to them.*
+ *Worth revisiting once connected skills leaves preview and the criteria set settles. Last refreshed 2026-09-23: source repointed after Microsoft renamed Opportunity Research Agent to Sales Opportunity Agent, plus new guidance on the initial-run capacity spike.*