Product log
What's new in Call Coach IQ
We ship improvements every few weeks. Here's what's landed recently — new features, speed and reliability work, and the kind of small fixes that quietly make the product better.
November 2026
Every AI Voice Call Gets an Honest Outcome
Every call the voice agent answers now ends in one of four outcomes. A hangup counts as resolved only when the post-call review says the caller’s issue was settled, so a caller who hung up in frustration, or while waiting for a transfer they asked for, is no longer counted as a success. AI call pages also show the two post-call checks: promises the agent made but did not keep, and passages it misheard. Past AI calls have been reviewed as well, so earlier months on AI Outcomes show real figures instead of “awaiting review”.
Switch Phone Systems Yourself — Now Including NetSapiens
Company admins can now connect, update and switch their own phone provider from Admin → System → Phone System, so nobody else ever handles your API keys. Calls already imported from the old system keep working, its last few days can still be pulled in after the switch, and its credentials can be deleted once it is retired. NetSapiens joins as the 20th supported provider, including platforms resold under a provider’s own brand, and the manual “Fetch from API” import now works for every provider, not just one.
Email Assistant Keeps Up With Outlook
Replies, forwards and categories made directly in Outlook now reach the Email Assistant, so a draft closes when someone has already handled the email there. Admins choose which Outlook categories mean “handled”. Drafts are signed with the reviewer’s name, show the member’s NISC customer and account numbers with copy buttons, and say whether their Calix connection is up. Contact-form and voicemail emails are answered to the member, not the no-reply address or the phone system. The assistant also supports assignment and team metrics, and alerts admins when a watched mailbox goes quiet.
Customer Demographics on Customer Themes
A new Customer Demographics tab shows who is calling in: tenure, residential or business, services and bundles, internet plans by speed, members by service city or wire center, connects and disconnects per month, and tickets per member. NISC service and reason codes appear as readable labels, and former members are counted on their own. The tab covers members who contacted you in the last 90 days, and says so. Tooltips now explain every card and column on Customer Themes.
Business Insights: An Operations Page and One Date Range
Processing health, AI audit results and calibration issues now have their own Operations page, leaving Business Analytics to business questions. The date range you pick now follows you across Business Analytics, Operations, Sales Intelligence, Churn Risk, Customer Journey, Sentiment Analytics and Pivot Points, and travels in a shared link. Sections that appeared on two pages now live on the one that owns them, and churn-flagged customers are worked on Churn Risk, with a link from Customer Journey that opens that customer directly.
Newer Gemini Models
Gemini 3.8 Flash is now available for analysis, scoring, coaching and transcription, and Gemini 4 Argon for analysis, scoring and coaching on ComplianceIQ. Both support the lower-cost Flex tier. The AI voice agent now runs on Gemini 3.8 Live.
AI Voice Agent: Warmer Greetings and Transfers That Hold
When a caller’s number is on an account, the agent greets them by first name instead of also asking who is calling, and its “good morning” or “good afternoon” now comes from your own time zone. On a warm transfer, the caller is held while the agent reaches a colleague, the colleague hears a short summary before picking up, and the agent knows when a transfer did not go through. Live IQ now shows the caller-history lookup the agent makes as the call connects.
Coaching Flags and Customer Follow-Ups, Kept Apart
A manager’s private coaching flag and a task to call the customer back are now separate records. Assigning a follow-up no longer overwrites a coaching note, both panels always show on the call page, and agents can assign themselves a follow-up on their own calls without ever learning that a coaching flag exists.
Knowledge Base Reads Scanned PDFs
A PDF from a copier, which is page images with no text, no longer fails with “No readable text found”. The AI reads it instead, and keeps handwritten corrections as notes beside the printed text they change.
Search Results Show the Whole Call
Each AI Semantic Search result now shows the call’s date, duration, customer, direction and score beside the matched passage, and Call History gains a Duration column. Phone-menu recordings, such as pay-by-phone prompts, no longer show up as search evidence.
Admins Can Reset a Password, and See Live 2FA Status
Admins can email a user a password reset link or set a new password from Admin → People, and every reset is audit-logged. The Users table now shows each person’s current two-factor status, and the user and their admins are alerted when a 2FA factor is removed outside the app from somewhere that user has not signed in.
Numbers That Count What They Say
We audited the figures on Business Insights, the Realtime Dashboard, My Performance and AI Performance Reviews and fixed the ones that did not count what their label said. Call sentiment and retention saves now have one definition everywhere, and a customer kept on a cancellation call now counts as a save. More won sales carry their monthly price, and an unreported queue rate shows as unreported rather than 0%. On calls split between agents, each agent’s handle time now comes from their own part of the transcript rather than the length of the whole call.
October 2026
Customer Themes — What Customers Call About
Every customer call is now sorted into themes — slow speed, outages, Wi-Fi, billing disputes and more, plus an Emerging bucket for anything new — and counted by week and by area: the service city from NISC, the wire center, fiber network and cable, or a place the caller named. Fiber and copper are split out. When a theme reaches at least five calls a week and twice its usual level, admins get an alert company-wide and managers get one for their own team, and a theme.spike webhook fires. A new Insights Viewer role lets network and product engineers follow the counts and spikes without seeing customer quotes or call links. Insights IQ and up.
Outcomes Adds Team and Value Tabs
AI Outcomes is now Outcomes, with two new tabs. Team reports monthly results for people and AI together: repeat contacts, commitments kept by their deadline, the score change after coaching, and an at-risk retention measure. Value prices those outcomes with your own figures, showing the arithmetic on every line — including truck rolls avoided once NISC trouble tickets are connected.
Knowledge Base Answers With Citations
Ask the knowledge base a question and every sentence of the answer links to the passage it came from; when your content does not cover it, the answer says so rather than guessing. Admins and managers get a Content Gaps card listing the questions nobody could answer and the articles no answer has used, and Live IQ shows which knowledge the voice agent drew on during a call.
September 2026
AI Voice Agent — Now Answering Real Calls
The AI voice agent is answering live inbound calls end to end. It greets the caller, verifies who it is speaking to before releasing account detail, answers from your own knowledge base rather than guessing, checks service availability at an address, takes a callback request, and warm-transfers to a person or a queue with a spoken handover so the human knows the story before they say hello. Every call opens with an AI disclosure your company signs off word for word.
Live IQ — Watch Every AI Call in Flight
A new Live IQ board under Dashboards shows every AI call happening right now, side by side: what the caller heard, what the agent actually looked up to say it, and what the call is costing. Supervisors can step in and take a call over at any point. Callbacks the agent promised land in a queue where one person claims a row, so two people never ring the same customer.
Fair Scores on Poor Recordings
Calls whose audio was too degraded to judge fairly are now flagged and factored into scoring, so an agent is not marked down for a fault that belongs to the phone line. Call detail shows a quality banner, and the flag rolls up per agent, team and phone line — which is how you find the faulty handset or trunk behind it.
August 2026
Mobile App: Agent Workspace, Push and Two-Factor Sign-In
The iOS and Android app now covers the calls-and-coaching loop away from a desk: calls with transcript and audio, coaching and the dispute flow, commitments, training, the knowledge base and notifications — with push notifications end to end and two-factor sign-in, including forced enrollment where your company requires it.
Voice Agent Offers What the Caller Needs
The voice agent can now volunteer what will help — raising something outstanding on the caller’s account, or saying plainly when it cannot handle a request and what it can do instead — rather than only answering what it is asked. Every kind of offer is capped per call, with a hard ceiling across the call, and it goes quiet once a person is being fetched.
Legal Hold on Data Deletion
A scheduled company data deletion can now be blocked by a legal hold, placed and released only by our team. The hold is re-checked immediately before anything is purged, the request shows it is held rather than stuck, and an alert is raised while it stands.
Operational Alerts by Email, With Per-User Opt-Out
July 2026
Agent Burnout & Attrition Scoring
The platform now continuously scores every agent for burnout risk. When an agent's score reaches Critical, their manager receives an email alert, a "Critical for N days" streak badge appears on the burnout dashboard, and a persistent action panel lets managers log notes and acknowledge the alert to pause repeat notifications. Alert delay and re-alert intervals are configurable per company in admin settings.
Multi-Agent Call Detection & Split Attribution
Call Coach IQ now detects when more than one agent handles a single call — warm transfers, conference handoffs, team calls — and automatically creates a separate call record for each participant. Every agent gets their own score, AI coaching, and conversation dynamics, so no one's performance is hidden inside a shared call.
Warm Transfer Scoring Rubric
A dedicated scoring rubric is now available for warm-transfer calls, with criteria tuned to the handoff context rather than a standard call. Admins can toggle immediate coaching feedback on or off for this call type independently of other rubrics.
Customer Commitment Tracking
June 2026
19 Native Phone System Integrations
Call Coach IQ now connects directly to 19 phone platforms — Intermedia, RingCentral, NICE CXone, Genesys Cloud, Five9, 8x8, Talkdesk, 3CX, Aircall, Dialpad, CloudTalk, JustCall, Freshcaller, MiaRec, Zoom Phone, GoTo Connect, VitalPBX, Twilio, and VoIP.ms. Recordings pull in automatically the moment a call ends. Preferred-tier platforms also stream live agent status and queue statistics into the real-time dashboard. Setup guides and credential forms for every provider are available in Admin → System & Data.
Knowledge Base Agent Upload Approval Workflow
Agents can now submit documents and articles to the Knowledge Base directly from their workspace. Submissions enter a manager approval queue before going live — so agents can contribute their expertise without bypassing editorial control.
Visitor Chat Cites Its Sources
When the public visitor chat widget answers a question using your Knowledge Base, it now shows which articles it drew from. Visitors can click through to the source, and you can see exactly which content is driving engagement.
May 2026
Android App — Now Available
The Call Coach IQ mobile app is now on Android. Cloud builds are fully configured so the team can ship new versions directly to Google Play, and preview builds can be uploaded to Play Console in one step.
Over-the-Air Mobile Updates
JavaScript fixes and improvements are now delivered to the Android app instantly — no app store download required. Users get the latest version the next time they open the app.
Mobile App Icon & Splash Screen
The Android app now shows the official Call Coach IQ brand icon and splash screen, replacing the earlier placeholders.
Live Progress for Admin Maintenance Jobs
Long-running admin jobs — including embeddings reindex and data backfills — now stream real-time progress so operators can see exactly where a job stands. Jobs can also be cancelled mid-run without waiting for them to finish.
Smarter Job Resumption
When an admin backfill or reindex job is interrupted and restarted, it now skips work that was already completed. No more redundant processing or accidentally overwriting finished results on resume.
April 2026
Agent Workload Dashboard
Admins can now see calls per agent, total talk time, average handle time, longest call, calls/hour, and a 30-day score sparkline — all sortable, with stack-rank badges for top and bottom performers.
Utilization Heatmap
Click into any agent in the workload tab to see a 7×24 hour-of-day × day-of-week heatmap of their call activity. No extra query — it reuses the same data the table fetches.
Handle-Time Outliers
A new card surfaces calls that ran more than 2× the agent's median handle time for that call type — so coaches can spot the calls that actually deserve a closer look.
Cost-per-Call Telemetry
Every AI flow (transcribe, classify, score, analyze) now records token usage and an estimated cost. Admins get a 30-day rolling cost card on /admin with a per-plan-tier breakdown.
March 2026
Agent Score Disputes
Agents can challenge any AI-generated score directly from the call page. Managers review, respond, and resolve in-thread — every step is tracked.
Achievement Badges
Built-in gamification layer — agents earn badges for performance milestones, with company-wide celebration alerts.
Customer Journey View
See a customer's entire call history in one timeline — sentiment shifts, CSAT scores, and churn-risk flags side by side.
Faster end-to-end processing
Most calls now complete the full transcribe → classify → score → analyze pipeline in minutes.
February 2026
Ask Your Data
Natural-language search across your call corpus — ask "show me churn-risk calls from last week" and get a grounded answer with links back to the source calls.
Custom rubrics on every plan
Fully editable scoring rubrics, including separate rubrics per call type (sales, cancellations, tech support, general), are available on Starter and up.
Automatic PII redaction
Card numbers, SSNs, PINs, dates of birth, and security answers are now replaced with labeled placeholders before any transcript is stored.
Have an idea for what we should build next?
Customer requests directly drive our roadmap. Tell us what would make your QA program better and we'll get back to you.

