Edit the full opening greeting on voice campaigns
Write the exact first words your outbound Voice AI says, including a {first_name} placeholder, instead of only splicing a short opening line into the assistant greeting.
What's New
New features, improvements, and fixes across the IrisAgent platform. Updated regularly.
October 2026
Make Voice AI calls sound more natural
Faster turns, short phone-safe answers without spoken URLs, immediate replies to connection checks, and pronunciation replacements so brand names and units sound right. Follow-ups cut filler lag and keep outbound answers brief.
Wait times and priority scores are easier to read
Long waits roll up into days (or larger units) across Needs Attention and related views. Ticket Priority Score in the sidebar shows a whole-number score and a readable wait time across Salesforce, Zendesk, Freshdesk, and Intercom.
Brand reply guidelines no longer replace the real answer
Tone and closing guidelines stay style-only. Chat answers keep the factual reply from your knowledge base instead of shipping a check-in or sign-off alone.
Score any conversation for escalation risk
Paste a ticket thread or look up an open case on the new Escalation Score page to see why-now reasons, sentiment trend, and priority factors. Nothing you paste is saved.
Ask Support Analyst why a case is escalating
Support Analyst can answer with the escalation score, why-now reasons, sentiment trend, and priority factors from the same attention snapshot as Cases that need attention.
Outlook accounts finish self-serve setup
Connecting an Outlook mailbox no longer leaves the dashboard stuck on account setup. Self-serve onboarding completes so Case Triggers and the rest of the app unlock.
Tune how your outbound Voice AI assistant sounds and behaves
A new Outbound assistant tab lets admins set the voice, language, response timing, interruption sensitivity, silence timeout, maximum call length, and recording for campaign calls. Open it from the Configure voice button on the Voice Campaigns page.
Support Analyst finds every escalation and answers from past tickets
Ask for escalations and Support Analyst now combines attention scores, escalation tags, and ticket text, labeling which signal each case matched. It can also search prior ticket conversations for exact terms and cite the tickets behind its answer.
See customer impact and product signals for every topic
Topic detail pages now show impacted customers, active attention, and revenue at stake, with a table of affected accounts. The topic treemap adds Feature requests, Bugs, and Performance views, and the weekly briefing adds a Product signals section compared with last week.
Connect Outlook shared and support mailboxes
You can now connect a shared or support mailbox in Outlook, not only the signed-in user's own inbox. If a connection fails because of mailbox access, IrisAgent explains what to fix instead of showing a generic error.
September 2026
Tell recipients why you are calling with a voice campaign opening line
Add an optional opening line to an outbound voice campaign and Voice AI says it right after introducing itself, so recipients know why you are calling. Campaign details now show each recipient's call status and outcome, with a test call preview beside the campaign.
Ask Support Analyst from Slack and Microsoft Teams
Mention the IrisAgent bot in Slack or message it in Microsoft Teams and Support Analyst answers from your ticket data, with links, headings, and tables formatted for chat. In Teams it can also read text from screenshots you attach.
Spot cases where customer sentiment is getting worse
Escalation scores now account for a recent drop in case sentiment. Escalating cases show a Worsening cue, and the details drawer shows recent sentiment scores and how much they changed.
Zendesk chatbot picks the conversation back up after an agent releases it
When an agent ends a human messaging session in Zendesk Agent Workspace, the IrisAgent bot now starts a fresh session so the customer can keep getting help.
See which customers need attention on Customer Health
Customer Health now leads with a Customers Needing Attention queue that ranks accounts by health and active escalation signals. Each row shows recommended action, rationale, driving cases, revenue, and owner so you know who to intervene with first.
Find cases that need attention with Act now and High priority views
The new case attention explorer surfaces escalating and high-priority open cases above Customer Health. Switch between Act now, High priority, and All open cases, search by case number, and open score breakdowns in a side panel.
Support Analyst answers with grounded charts
Ask Support Analyst a question and get bar, line, stacked bar, or pie charts grounded in your ticket data, with an accessible data table alongside the visualization.
See who changed a procedure and what they changed
Every saved procedure now has a Revision history tab with a timeline of edits, who made them, and clear before-and-after field diffs in unified or side-by-side view.
Weekly briefings now flag cases that need attention
Your weekly Slack and email Support Analyst briefing includes a Cases that need attention section with the highest-risk Critical or Escalating open cases, plus links into the full attention queue.
Save Outlook AI replies as drafts instead of sending
Choose Draft or Send per AI reply trigger for Outlook. IrisAgent can create a threaded reply draft in Outlook for your team to review, without sending it automatically.
See richer chat AI impact metrics and daily trends
Chat Performance now includes visitor messages, procedure-assistance rate, feedback scores, channel filters, and a daily trend chart you can switch between total, AI-answered, and agent-routed chats. Case AI Trend sits with Case Performance and shares its date range.
Tag Zendesk Messaging tickets when chat hands off
On the chatbot Handoff tab, add optional Zendesk ticket tags for live-chat escalation. When the bot hands off, IrisAgent applies those tags and passes Switchboard control to Zendesk Agent Workspace.
Add named agent actions to procedures with @
The procedure editor now has an Agent actions palette for Check status page, Call API, Create ticket, and Escalate. Type @ to insert them, and jump into a procedure right after you connect Statuspage, a custom API, or Zendesk actions.
Export billable resolution conversations as CSV
From Billing, export the itemized conversations that counted toward resolution usage. The CSV includes UTC timestamps and direct links back into IrisPortal so you can audit what was billed.
Embed AI Search inside Confluence
Drop the existing AI Search widget into Confluence with your shared widget key so your team can search, get grounded answers, and leave feedback without leaving the wiki. Framing is limited to trusted HTTPS origins you configure.
Transfer Voice AI calls to a live phone number
Configure a destination number, optional extension, and caller-facing transfer message so Voice AI can blind-transfer when a procedure says to hand off or when there is no answer. International numbers are validated and transfers to your inbound Voice AI line are blocked.
August 2026
Ask Support Analyst from the Zendesk sidebar
Agents can analyze the open ticket or ask IrisGPT in plain English without leaving Zendesk. The IrisAgent Assistant keeps ticket context across turns so follow-ups stay grounded in the case in front of you.
Turn a ticket reply into a knowledge article from Suggested Resolution
When IrisAgent has no answer, or after an agent posts a substantive public reply, Suggested Resolution prompts you to save an article draft in Support Analyst. Thin thanks-style replies and internal notes stay out of the way.
Keep Jira and Zendesk tickets in sync automatically
Configure which fields flow between a Jira issue and its linked Zendesk tickets, and IrisAgent keeps both sides current as engineering makes progress. Agents can link, unlink, and prefill Jira issues from a customizable template right inside the Zendesk sidebar.
Support Analyst answers questions about teams, agents, and custom fields
You can now ask Support Analyst about ticket group metrics, agent response latency, brands, and any custom field on your tickets, and filter by update time in plain English. Searches use your local dates, resolve real agent names, and hold on to verified evidence even on very large investigations.
Voice AI speaks more languages, with previewable personas
Voice assistants can now be provisioned in more languages (including Arabic) with a transcriber tuned for multilingual speech. New assistant settings let you tune how the AI sounds, and you can listen to a preview of each voice persona before assigning it.
Write AI tags and classifications back to your tickets
IrisAgent can now write its own classifications and tags directly into your helpdesk ticket fields, and you map which AI output goes to which field yourself. Your existing routing, views, and reports pick up AI-generated context without any extra work.
Drop a suggested resolution into a Salesforce email draft
Agents can insert an AI suggested resolution straight into a Salesforce case email draft in one click, then edit before sending. Suggested resolutions also show their source article prompts, so it is clear what the answer is based on.
One product catalog across knowledge, procedures, and cases
Define your product lines once in a shared catalog, then assign articles, Jira projects, procedures, and cases to them from a single consistent picker. Product-scoped answers stay accurate because product assignments now stay reconciled everywhere IrisAgent looks for content.
Test a procedure without leaving the editor
Procedure details now include a built-in chatbot tester, so you can try a procedure end to end as you build it. You can also filter procedures by channel, mark fields as required, and see enabled AI recommendations alongside everything else in All Procedures.
Connect more than one Jira instance
Teams running separate Jira instances (for example one per product or per acquired company) can now connect all of them, map projects to products, and create or search issues across every provider from the agent sidebar. Support Analyst can look up live Jira issues across them too.
Full multi-brand support for Zendesk
If you run several brands in one Zendesk account, IrisAgent now ingests knowledge per brand, classifies incoming cases by brand ID, and keeps answers scoped to the right one. Private Zendesk images also render correctly in chat answers, and Zendesk tokens refresh without manual reconnection.
Reach customers proactively with outbound SMS campaigns
You can now build, schedule, and send outbound SMS campaigns from IrisAgent, using a number we provision for you or a Twilio number you already own. Delivery failures surface directly in the dashboard so you can see which messages landed and which did not.
Let Voice AI make outbound calls for you
Voice AI can now run outbound calling campaigns: pick a purpose, route it through your Smart Operating Procedures, and test the whole flow with a draft campaign before real customers hear it. Complete call transcripts are stored for every outbound and inbound call.
See every connected source in one place
A new All Sources view lists every knowledge base, website, and ticketing connection you have set up, with live article counts, source URLs, and connection status. You can also start onboarding and explore the product before connecting a single data source.
Send conversation emails from your own domain
Email replies from IrisAgent now go out from your own verified sending domain, so customers see your brand rather than a generic address. Domain setup and verification are self-serve under Deploy and complete automatically once your DNS records resolve.
Hand off to a live agent in Salesforce Messaging
The AI chatbot can now transfer a conversation straight into Salesforce Messaging (Messaging for In-App and Web), carrying the full transcript with it so the agent picks up mid-thread. Setup is guided in the dashboard, including SCRT URL validation and a short walkthrough video.
Configure your chatbot with a live preview beside you
Chatbot configuration is now split into focused tabs (appearance, behavior, deployment) with a live preview that updates as you type. You can also preview a bot in mock mode before any data source is connected, so you can see exactly what customers will get before you go live.
Shopify answers now show real product cards
When a shopper asks about an item, the chatbot replies with a rich Shopify product card instead of a plain text description. Store connections also stay healthy on their own now that expiring Shopify tokens are refreshed automatically.
Case answers include the most relevant screenshots
When an article contains multiple images, case answers now pick the ones that actually match the step being explained instead of the first image found. Images sourced from Confluence and Jira also render correctly in the Salesforce sidebar.
Reply to Salesforce cases and post private notes from the sidebar
Agents can now send a case reply or leave an internal private note on a Salesforce case without leaving the IrisAgent sidebar. The sidebar also gets a single launcher for both Support Analyst and IrisGPT, and keeps your chat going as you move between cases.
Answers now run on a refreshed set of frontier models
Three rounds of benchmarking across 15 models led to a dozen production model swaps, including newly added Kimi K3 and DeepSeek V4 Flash. Every customer gets the higher-scoring model for each task with no configuration change on your side.
Contacts and email replies now live in Conversations
Every conversation now carries an editable contact record, and outbound email replies show up in the same thread as the chat. Conversations are also labeled by source, so you can tell chat, voice, and email traffic apart at a glance.
More control over how Voice AI answers
You can now set answer guidelines for Voice AI from Deploy settings, shaping tone and what the assistant should or should not say on a call. A new product filter scopes voice answers to a single product line, so callers only hear knowledge relevant to what they bought.
See exactly what the AI did in every chat and voice conversation
Chat and voice logs now show which procedure matched, the details the AI captured from the customer, and the workflow state it reached. New filters by chatbot configuration and agent request make it much faster to find the conversations you care about.
IrisAgent for Shopify: install in a click and answer order questions
Install IrisAgent on your Shopify store through the Shopify app and add the chat widget with a theme app embed, no code required. The AI can then look up order status, products, and other read-only store data to answer "where is my order" questions directly.
Topic analytics now covers chatbot conversations
Topics now cluster chat conversations alongside tickets, with a chat filter and a detail view for each topic showing volume, representative conversations, and insights. Chat-only teams finally get the same view of what customers are asking about.
Pay-per-resolution only counts grounded, clean resolutions
A conversation only counts as a billable resolution when the answer was grounded in your knowledge. Chats that show red flags, such as a frustrated customer or a failed attempt, are now disqualified, so what you pay for lines up with what actually got resolved.
Support Analyst now analyzes chatbot conversations
Support Analyst is no longer limited to ticket data. Teams running the AI chatbot can now investigate chat conversations in plain English, asking questions like why deflection dropped or which topics drive the most handoffs.
Cleaner chatbot replies and automatic escalation when there is no answer
Internal data the bot collects during a conversation no longer leaks into the reply text, and clarifying questions or errors are no longer counted as answers in your metrics. When the bot genuinely has no answer, it now escalates instead of stalling, and the no-answer message is translated for the customer's language.
July 2026
Support Analyst redesigned around Find, Prove, Improve
Support Analyst is reorganized into three clear steps: find an issue, prove it with data, then improve it. Suggested prompts are now grounded in what the system can actually answer, and you can jump straight into Support Analyst from an AutoQA review or a case with the context already loaded.
Start grading with a default AutoQA rule pack
New AutoQA accounts now come with a labeled pack of default rules covering the fundamentals of a good support reply. You can start reviewing on day one and tune or replace the rules as you go, instead of writing a rule set from scratch.
Get a weekly Support Analyst briefing
Support Analyst now compiles a weekly briefing on what changed in your support data: emerging issues, notable shifts, and suggested next steps. It is read-only, so you get the summary without anyone needing to run a single query.
AutoQA reviews show their evidence and accept your corrections
Each review now displays the case evidence and the surrounding messages behind every flagged moment, so you can see why a rule failed without opening the ticket. Admins can override a score when the AI got it wrong, human and AI reviews are shown separately, and you can filter reviews by sentiment, priority, and CSAT.
Weight your AutoQA rules by what matters most
AutoQA scorecards now support per-rule weights, so a missed compliance step can count for more than a formatting nit. Scores reflect your team's real quality bar instead of treating every rule the same.
Connect your status page yourself
Point IrisAgent at your public status page from Data Sources, with an enable toggle, provider picker (Instatus today), and URL validation. Turning on live incident awareness no longer needs a setup request to our team.
Answers now run on Claude Opus 5 and Gemini 3.6
Claude Opus 5 and Gemini 3.6 Flash are now supported, and our weekly benchmark moved seven production paths (chat, AutoQA, article generation, and batch case answers) onto the best-scoring model at each price point. You get the same answer quality or better, with faster responses.
Use live incident status inside your procedures
Smart Operating Procedures can now include placeholders that resolve to your live status page: whether an incident is open, its name, its stage, and its link. Write the exact wording you want customers to see during an outage, and insert the placeholders with one click from the procedure editor.
Onboarding email shows the topics we found in your tickets
During setup, your onboarding email now lists the support topics IrisAgent discovered in your data, each linking straight into the dashboard. You can see what the AI learned about your business before you go live.
Salesforce sidebar works on Experience Cloud and adds one-click copy
The IrisAgent sidebar now runs on Experience Cloud Case record pages, and agents can copy a suggested resolution, dynamic resolution, or case summary with a single click. Asking IrisGPT a question also submits with Enter.
Live status page incidents now answer customer chats
IrisAgent can now poll your public status page (starting with Instatus) and use active incidents to answer customers during an outage. Instead of waiting on an agent, people asking about a known issue get the current incident status right away.
Stronger answers for non-English customers
Language handling got a broad upgrade: Polish and Ukrainian are now detected in the chatbot, fallback replies are written in the customer’s own language instead of defaulting to English, and long knowledge base articles and uploaded PDFs are translated in full rather than being cut off partway. Non-English customers get complete, native-language answers.
More precise article retrieval behind every answer
We now index each question and answer pair in an article separately, and long articles are processed in full instead of being skipped. The AI pulls the specific passage that answers the question, so both chat and case answers cite better sources.
Case answers come back noticeably faster
The answer pipeline now runs its verification passes in parallel and follows a deterministic model cascade. Agents spend less time waiting for a suggested resolution to appear on a ticket.
Answers now run on GPT-5.6 and Grok 4.5
We refreshed our model leaderboard with the latest frontier models, including OpenAI's GPT-5.6 family and Grok 4.5, so every AI answer runs on the most accurate model available. We also added automatic fallbacks so answers stay reliable even if a provider has an outage.
See what share of your cases IrisAgent has processed
Impact performance cards now show the number and percentage of cases IrisAgent processed, so you can read deflection and resolution metrics against real coverage instead of guessing at the denominator.
QA your AI answers for grounding in Support Analyst
Ask Support Analyst to grade an AI answer you already sent against the articles it cited. It checks whether the cited articles were relevant and whether every claim is supported, then tells you if a defect was a retrieval miss or a model hallucination.
See procedure analytics and outcomes right in the procedures list
The procedures table now shows impact summaries and feedback outcomes for each Smart Operating Procedure, so you can tell at a glance which procedures are helping and which need attention without opening each one.
See CSAT next to AutoQA scores
AutoQA now shows each ticket's customer satisfaction score right alongside its AI quality score, so you can see where a low CSAT lines up with a QA miss and coach to the tickets that matter most.
Spot failing QA rules at a glance with the rule heatmap
A new rule-by-week heatmap shades each cell by how often that QA rule failed, so a manager can spot a problem rule or a bad week instantly and click straight into the failed reviews behind it.
Annotate and share AutoQA reviews with your team
You can now add reviewer notes to any AutoQA review (at the review level or on a specific rule) and share a review with teammates through a direct link and side panel, so discussing findings and coaching no longer means hunting for a ticket ID.
Assign Smart Operating Procedures to specific chatbots
Map each procedure to the chatbots that should follow it, so different bots (for different products, brands, or audiences) run only the procedures that apply to them.
Pay-per-resolution billing excludes handoffs and preview chats
For customers on outcome-based pricing, resolution billing now excludes conversations that hand off to a human and internal dashboard preview chats, so you are only billed when the AI actually resolves a real customer's issue.
Support Analyst answers faster and searches tickets by meaning
The ticket agent now streams its answer and shows each step live (searching tickets, drafting the answer) instead of leaving you on a spinner. It also searches your tickets by meaning, so a question like "customers frustrated about billing" finds the right conversations even without exact keyword matches.
Approve or reject AutoKB drafts in one click
AutoKB drafts knowledge base articles from resolved tickets, and you can now approve or reject each draft right from the dashboard, so getting new knowledge reviewed and published is a single click.
Chain a prerequisite action into a custom API step
A custom API action can now run a prerequisite action first and feed its result into the next call, so you can build multi-step automations (look something up, then act on it) directly inside a procedure.
See which conversations each procedure impacts
Each procedure's detail page now shows the real cases and chats where it matched and shaped the AI answer, with permalinks to those conversations, so you can see the impact of a procedure instead of guessing.
June 2026
Support Analyst now suggests procedures and drafts AI answers
Support Analyst gained two new skills: it can suggest a Smart Operating Procedure from your tickets (with a one-click create card and how-to or action typing) and draft an AI answer to a ticket on demand. You get from raw tickets to reusable procedures and ready-to-send answers without leaving the analyst.
Control which source URLs power your chat answers
You can now set customer-level source URL filters so the AI chatbot only grounds answers in the pages and articles you trust, and excludes the ones you don't. Changes take effect immediately, giving you tighter control over where chat answers come from.
Attach screenshots to the AI chatbot and AI search
Customers can now attach screenshots or images to their question in the AI chatbot and AI search. IrisAgent reads the image and uses it to answer, so people can show a problem (an error screen, a receipt, a settings page) instead of struggling to describe it.
Track pay-per-resolution usage on your Billing page
For customers on outcome-based pricing, the Billing page now shows your resolution usage, so you can see exactly how many resolutions IrisAgent delivered and what you are paying for. You only pay when the AI actually resolves a customer's issue.
AutoQA now grades long tickets reliably
AutoQA grades 100% of your tickets, and it no longer stops short on very long conversations. Reviews that previously failed to complete on lengthy tickets now finish cleanly, so your QA coverage stays complete.
Add a payment method for seamless billing
Securely save and manage credit cards on file directly in your IrisAgent settings, powered by Stripe, so paying for IrisAgent is simple and seamless. Card details are handled entirely by Stripe and never touch IrisAgent's servers.
Rewrite customer terms to match your knowledge base
Add rewrite rules that map the words customers use (like "acct") to the terms your articles actually use (like "account") before the AI searches. This improves which articles get retrieved for both chat and case answers, and does not change the answer shown to the customer.
Support Analyst: ask your ticket data anything, in plain English
Support Analyst is an AI analyst that sits on top of your tickets. Ask a question in plain English and it plans and runs the right skills for you: natural-language search, ticket deep dives, sentiment analysis, instant analytics and agent performance, account overviews, conversation QA, proactive trending-issue alerts, AutoKB article drafting and knowledge-gap detection, plus audio-transcript and multilingual support.
Find and fill knowledge base gaps
IrisAgent now surfaces the questions your customers ask that your knowledge base can't answer, and can draft the missing article for you, so you can close coverage gaps faster.
Answers now run on the latest frontier models
We re-evaluated our model leaderboard and added the newest models from Anthropic, OpenAI, and Google, so every AI answer runs on the most accurate, up-to-date model available.
AutoKB removes duplicate knowledge automatically
AutoKB drafts knowledge base articles from resolved tickets and now detects near-duplicates automatically, so your agents and customers see one clean, authoritative answer instead of several conflicting drafts.
Build procedures faster with API steps and impact estimates
Smart Operating Procedures now show an API panel when a connection exists so you can wire action steps without leaving the page, estimate the impact of each procedure, and catch duplicates as you create them.
Self-serve Slack integration with OAuth
Connect IrisAgent to Slack yourself in a few clicks with the new OAuth flow, deploy across multiple workspaces, and get AI case answers and updates delivered right in Slack.
Manage product segmentation from the dashboard
Map cases to product lines directly from the UI with a new case product classifier, so routing, tagging, and analytics stay accurate without engineering help.
Redesigned topics, agent performance, and customer overview
We redesigned the topics, team performance, and customer overview pages so you can see failed QA reviews, the biggest increases and decreases in ticket categories, and the most common tags at a glance.
May 2026
AutoQA adds tag filters, date ranges, and team views
AutoQA grades 100% of your tickets and now supports tag filters, date ranges, and a team performance view, so you can pinpoint quality issues and coaching opportunities across your whole team.
A faster, guided onboarding wizard
New customers can get set up faster with a step-by-step onboarding wizard that walks you through connecting your data sources and deploying your first AI agent.
New knowledge sources: HubSpot KB and KnowledgeOwl
Connect your HubSpot knowledge base and KnowledgeOwl so IrisAgent can ground answers in more of your existing content, with support for syncing deletions automatically.
Trending incident detection with Slack alerts
IrisAgent now detects spikes in ticket categories and notifies you in Slack when a trending incident emerges, so you can get ahead of issues before they flood your queue.