Overview

Use the Custom CRM screen pop to select a case without typing its ID when the tenant supplies a stable opaque record key. The launch adapter discards other screen-pop fields and opens the protected staff panel.

Your team hosts the staff interface and case-access checks; Voiceflow runs the published read-only assistant. Tasks run only on a staff action. Automatic selection loads a snapshot, not a live transcript or a customer-send action.

Prepare the staff deployment

Collect the assistant, verified identity and platform configuration once.

Download the starter bundle. Keep support-platforms, contact-center-assist and amazon-connect as sibling directories. Shared agent-assist setup owns the host/session contracts; build the staff assistant before installing the platform entry.

Install the staff entry

Generate the platform files, connect authorized data and activate the pilot surface.

1

Build the platform files

From the extracted archive root, use your HTTPS staff origin without a path:

Build the 8x8 Contact Center staff app

Serve the generated panel.html, panel.css and panel.bundle.mjs together at https://staff.example/support-platforms/8x8-contact-center/panel.html. The command also writes SETUP.md and the applicable platform artifacts. Keep credentials on the server. It refuses an existing output directory; append a new directory after the origin when rebuilding. Configure no-store, approved iframe ancestors and embedded SSO.

2

Connect the authorized case reader

Use the existing authenticated host with routes.mjs:

Mount both authorized staff routes

loadCaseForStaff(staff, id, {signal}) verifies the tenant, provider interaction/case mapping and permitted fields, then returns {id, context: approvedText} or null. It must not accept browser-posted context as evidence.

Mount the handler at both same-origin POST paths, /api/agent-assist and /api/agent-assist/context. Apply the host’s CSRF policy to both, a 32 KiB body limit, staff rate/concurrency limits and bounded identity/provider reads. Honor the supplied cancellation signal. The context route starts no Voiceflow session; every later task reauthorizes and reloads the record.

3

Activate the platform surface

From the tenant’s Integration → Screen Pop parameter reference, identify the opaque transaction/CRM record-ID field and its mapping to your case service. Do not substitute ANI, email, external-login or password fields. Parameter names vary by integration; no undocumented default name is assumed.

Mount createScreenPopLauncher from launchers.mjs at an HTTPS POST route. Supply the generated staffAppURL, the verified idField name and verifyLaunch(request) for your approved tenant/proxy launch policy. Accept only the documented form POST with a 32 KiB body limit. The adapter reads one configured ID, discards the rest and returns a 303 to the fixed staff URL with a fragment. It never signs staff in or reads a case.

In Configuration Manager → Integration → Screen Pop, enable the approved Custom target and point its URL to that POST route. Choose the offered/accepted/completed events appropriate for the pilot and assign the agents. Verify a real sandbox form POST reaches the adapter and staff sign-in survives the redirect. If no stable record key is available, use the manual fallback rather than interpreting caller ID as a case.

4

Load context and choose a task

Open the installed entry for an allowed sandbox record; confirm the selected ID without typing. Wait for Case context ready and inspect Approved case context. Denial keeps tasks disabled. Opening a record or loading context does not ask the model.

Choose Find policy, Draft reply, Suggest next step or Summarize. The question box is optional for these four actions; use it to focus the result. Ask assistant requires a question. Configure the assistant to return customer wording only for Draft reply and staff evidence/missing facts for the other tasks. Review model output before using it.

Use the manual companion fallback

Keep task buttons and context checks when this account cannot supply the automatic surface.

Serve the starter’s original panel.html, CSS and module directories on the protected staff origin, with relative paths intact. It uses start.mjs: enter the authorized case ID, choose Load case context, then choose a task. Editing the ID disables tasks again. The manual companion does not inherit SDK events or screen-pop context.

Configure case context

Treat workspace IDs as selection hints and keep approved data on the server.

The screen-pop form can contain credentials and personal data unrelated to the case. Do not log, reflect or forward its complete body. The adapter selects only the configured opaque ID; the staff service authorizes the tenant/record mapping again after sign-in. A separate staff window is pinned to its launch and does not observe later platform changes. Acceptance on a completed event does not supply a transcript automatically.

Use Copy suggestion only after the complete result arrives, then review/edit it in the normal support workspace. This supplied surface has no verified draft-composer insertion action. A provider endpoint that sends a message or saves a note is not used as a substitute.

The host must reset/unload on logout and account changes. Browser abort stops consumption; it does not prove remote execution stopped or transcripts were deleted. Set expiry and retention with the owning teams. A snapshot above the starter’s 16,000-code-unit limit is rejected; narrow the approved fields instead of silently dropping conversation coverage.

Test the staff workflow

Check tasks, record changes, denial and the exact human delivery action.

1

Check the selected record and all four tasks

Use a sandbox case with an unopened item delivered 12 days ago and an approved 30-day policy. Confirm the visible record ID and approved snapshot. Run every task with an empty question, then add a focus. Verify policy conditions, missing facts and source references. Summaries must state gaps when the snapshot is metadata or a limited excerpt rather than a complete interaction.

2

Prove record isolation and access denial

Launch a second record and confirm its ID/context replace the first in that new launch. Existing companion tabs remain pinned to their original record; finish/close them deliberately. For manual selection, edit the ID mid-response and prove tasks stay disabled until the next context load succeeds. Use a second staff account for a denied record: no snapshot/answer may appear and no model request may start. Test logout, account switch and session expiry.

3

Review delivery and recover from failure

Copy one completed suggestion and review it in the normal composer. No provider send, saved note, refund or call-control request may occur. Verify a partial stream never enables Copy suggestion. Interrupt the stream and deny the provider read; the prior/partial result must clear. Restore the service and retry manually while keeping the normal support workspace usable.

The entry or context does not load

Check platform assignment, direct origins and staff/provider access.

Verify the generated URL/artifacts, platform assignment and embedded sign-in. For parent messaging, verify both the direct source window and configured HTTPS origin; never use a wildcard. A 401 requires sign-in; 403 requires CSRF/tenant/record checks; 413 needs a narrower approved snapshot. Inspect redacted server diagnostics for provider/runtime failure. Reopen/reload after recovery without exposing the staff service publicly.

The result belongs to an old record

Check whether this surface follows selection or opens a pinned companion.

Compare the visible ID with the workspace. For a pinned launch, open a new launcher for the current record; a separate tab cannot follow the original workspace. For SDK/property binding, repeat the switch during the pending response and check the direct parent/SDK events and generation guard. Do not rely on a network abort alone. Discard an uncertain result before continuing.

Release and maintain assistance

Record the accepted app, permissions and rollback before expanding access.

1

Release to the pilot staff

Record the staff-host build, provider field allowlist/mapping, platform configuration and Voiceflow Environment/release. Repeat allowed/denied cases through the actual installed entry with a fresh staff session. Assign owners for policy freshness, identity/token lifecycle, SDK/app updates and incidents; rerun quality evaluation after changes.

2

Restore the reviewed deployment

Restore the saved External CRM/screen-pop configuration and disable only the pilot custom URL. Restore the recorded staff-host build and reviewed Voiceflow release, then repeat a fresh-session check.

Local review uses the starter’s labelled fictional fixtures; no SDK fixture or successful bundle proves provider installation, SSO, account permissions or real-model quality. Complete sandbox acceptance for this exact surface before release. For business-system tools, Import help articles and Human agent hand-off, keep the canonical Integration manuals.

Use the up and down arrow keys to select a result, Enter to open it, and Escape to close the search.