Changelog · Sep 14 – 20 2026 · 27 changes
What shipped the week of Sep 14
Every week we tell you what changed in ioZen, why we did it and what you get out of it. Each change says which plans get it.
What changes for you this week
Your Intake Bot looks more like your brand in fewer steps: Brand Kit guides you in three steps, saves on its own and uses your color on the options and the answer field. On the Process Board you track an amount on each card and see each column's total. On Business and Enterprise, Agent Blocks can hold a conversation toward an objective, like a sales advisor.
Jay
Intake Bot · Actionsample
Destination wizard
Name the appdone
Connect itdone
Field mappingaccepted
Record datadummy
Test recordsent
Newest first
Change by change
- 8 NEW
- 16 BETTER
- 3 FIXED
- NEW
Action destination wizard for Intake Bot sends
- The problem
- Adding an action block didn't walk you through naming, connecting, field mapping and a test record.
- What we did
- Adding an action block now starts with a wizard. Name the app, connect it, accept or reject native field mapping, see extra keys to create in the destination, and send a real test record with dummy data.
- How it helps
- You name the app, connect it, review the field mapping and send a real test record with dummy data.
- NEW
Sales amounts on Process Board cards
- The problem
- A Process Board card couldn't carry a sales amount, and columns showed only the card count.
- What we did
- A Process Board can track a sales amount on each card in one currency and show the column total next to the card count.
- How it helps
- You track a sales amount on each card in one currency and see the column total next to the card count.
- BETTER
Save a clean extracted value after AI validation
- The problem
- Strict Validation and Socratic Negotiation stored the full reply, not only the value that met the field goal.
- What we did
- Strict Validation and Socratic Negotiation can now store only the clean value that meets the field goal, instead of the full reply. Extract Value also asks for missing parts when the goal requires them, for example first and last name.
- How it helps
- You store only the clean value that meets the field goal, and Extract Value asks for missing parts such as first and last name.
- BETTER
WhatsApp settings split by number, with Click-to-WhatsApp readiness
- The problem
- WhatsApp settings weren't split by number, and nothing showed whether Click-to-WhatsApp conversions could send.
- What we did
- WhatsApp settings now use a left sidebar with per-number pages for routing, business profile, Click-to-WhatsApp conversions, and tracked links. Templates and billing stay workspace-wide. The ads section and the Intake Bot marketing settings now show whether Click-to-WhatsApp conversions can actually send, including when the bot's submission tracking is off.
- How it helps
- You get a page per number for routing, business profile, conversions and tracked links, and you see whether Click-to-WhatsApp conversions can send.
- BETTER
Brand Kit no longer generates visual packs
- The problem
- Brand Kit generated paid visual-pack art.
- What we did
- Website match still recommends looks. Image beside stays as an upload. ioZen no longer generates paid visual-pack art.
- How it helps
- Website match still recommends looks, and you upload your own image for Image beside.
- NEW
Autonomous Agent Block objective loop
- The problem
- Autonomous Agent Blocks didn't run an objective-driven loop with a cap on model calls per turn.
- What we did
- Autonomous Agent Blocks now run an objective-driven loop with a hard cap of three model calls per turn. Understand flags objections before any new question. Discovery probes, semantic exit, prior-answer context, and transcript dedupe stay on this type. Custom outcome values are validated in code. When the block has knowledge and the respondent has stated a need, the agent recommends concrete options from that knowledge instead of asking another question, and asks at most one question per message. The add-menu card is on in development and off on every plan.
- How it helps
- You get an objective-driven loop capped at three model calls per turn, and with knowledge the agent recommends options and asks at most one question per message.
- NEW
Autonomous profiles
- The problem
- An Autonomous Agent Block didn't have a sales advisor profile to start from.
- What we did
- Start an Autonomous Agent Block from a sales advisor profile. The catalog copies objective, skills, outcomes, and guidance onto the block. Later catalog edits do not change live blocks. Compose applies profile guidance after the system contract and before custom instructions and Voice Pack.
- How it helps
- You start an Autonomous Agent Block from a sales advisor profile, and later catalog edits don't change live blocks.
- NEW
Agent objectives can use earlier answers
- The problem
- Agent Block objectives couldn't reference earlier Intake Bot fields.
- What we did
- Agent Block objectives can now reference preceding non-private Intake Bot fields. The editor inserts field variables at the cursor, and web, test, and channel conversations resolve them from the available submission context.
- How it helps
- You insert field variables from earlier non-private fields into an objective, and conversations resolve them.
- NEW
Agent Discovery keeps volunteered context
- The problem
- Agent Blocks couldn't keep details a respondent volunteered without asking an extra question.
- What we did
- Agent Blocks can now keep relevant details a respondent volunteers, such as an anniversary or who they are shopping for, without asking an extra question. Advisors and Collectors can keep passive context, while extra follow-up questions are limited to Autonomous blocks. Probe answers and observations appear in submission details while remaining self-reported secondary context in intelligence, exports, and webhooks.
- How it helps
- You see volunteered details, such as an anniversary or who they're shopping for, in the submission details.
- BETTER
Applying a Brand Kit look is one action
- The problem
- Applying a Brand Kit look asked you to choose between merge and replace.
- What we did
- Apply writes the Brand Kit look onto the bot. There is no merge or replace choice. Welcome text and avatar stay.
- How it helps
- You apply the look in one action, and the welcome text and avatar stay.
- BETTER
Brand Kit drafts save on their own
- The problem
- Look edits in Brand Kit didn't save automatically, unlike the Intake Bot Design tab.
- What we did
- Look edits in Brand Kit save automatically, the same way the Intake Bot Design tab already does.
- How it helps
- Your look edits in Brand Kit save on their own.
- BETTER
Brand Kit is look then use, and unused looks can be deleted
- The problem
- Drafts and looks that no Intake Bot used couldn't be deleted.
- What we did
- Brand Kit is two steps: edit the look with the live preview, then use it on Intake Bots. Drafts and looks that no Intake Bot uses can be deleted.
- How it helps
- You edit the look with the live preview, use it on Intake Bots, and delete drafts and unused looks.
- BETTER
Header logo and conversation icon are separate
- The problem
- The header and the conversation shared one mark, and color and shape cropped the file itself.
- What we did
- Header and conversation share one mark (uploaded logo or Lucide/emoji). Color and shape apply to the plate behind it, not as a crop of the file.
- How it helps
- You use one mark (uploaded logo or Lucide/emoji), and color and shape apply to the plate behind it.
- NEW
Upload the Image beside photo
- The problem
- You couldn't upload your own photo for Image beside.
- What we did
- Image beside now asks for a 16:9 landscape photo (at least 1280 × 720, PNG JPEG or WebP, under 900 KB). Photos that miss the crop are rejected with a plain reason.
- How it helps
- You upload a 16:9 landscape photo, and one that misses the crop is rejected with a plain reason.
- BETTER
Image beside keeps questions in the chat
- The problem
- Image beside didn't keep the live question in the conversation.
- What we did
- Image beside is chat first. Wide screens can keep a photo on the left. The live question stays in the conversation, and phones show only the chat. A painted header still carries the brand mark.
- How it helps
- You keep the live question in the chat, with a photo on the left on wide screens and only the chat on phones.
- BETTER
Intake choices and the answer field use the brand color
- The problem
- Option buttons and the Type your answer field didn't follow the brand color.
- What we did
- Option buttons use the brand color as picked. The Type your answer field sits on a lifted surface with a brand border, a brand caret, and a readable placeholder.
- How it helps
- Your option buttons use the brand color as picked, and the answer field has a brand border and caret.
- BETTER
Logo sits on a readable plate
- The problem
- The logo had no plate behind it to keep it readable.
- What we did
- Colors includes Behind the logo: none, light, dark, or a custom plate. The mark stays bare until you pick one.
- How it helps
- You choose a plate behind the logo: none, light, dark or custom.
- NEW
Agent Block V3 and Business entitlement
- The problem
- Collect and Instruct were two separate blocks.
- What we did
- Collect and Instruct collapse into one Agent Block. Choose Structured or Agent-led conversation style, define typed outputs, attach grounded Documents and deterministic Decision tables, and use Agent-led Discovery as self-reported secondary context in Submission Intelligence, its summary, JSON, CSV, XLSX, webhooks, and action/CRM handoff. Agent Block authoring requires Business or Enterprise; existing published Pro blocks keep serving.
- How it helps
- You build one Agent Block with Structured or Agent-led style, typed outputs, Documents and Decision tables, on Business or Enterprise.
- BETTER
Brand Kit drops licensed fonts, page images, and visual packs
- The problem
- The Brand Kit Advanced drawer let you upload a licensed font or page image, pick a directed composition, or generate a paid visual pack.
- What we did
- The Brand Kit Advanced drawer is gone. Operators no longer upload a licensed font or page image, pick a directed composition there, or generate a paid visual pack. Match a website or pick a starting look, then edit the look and apply it.
- How it helps
- You match a website or pick a starting look, then edit the look and apply it.
- BETTER
The look editor fits on one screen
- The problem
- Choosing a look meant scrolling past every control.
- What we did
- Choosing a look no longer means scrolling past every control. Colors, type, feel, flow, and fine-tune open one at a time and keep their change count when closed, the look catalog opens as a dialog instead of holding a grid open beside the editor, and your own font, composition shells, the paid visual pack, and notes moved into an Advanced drawer. Website match now lists its three recommendations as flat miniatures, holds the progress bar short of full until the looks are actually on screen, and generated visual pack art is compressed to fit its size budget instead of being rejected.
- How it helps
- You open one group of controls at a time, and the look catalog opens as a dialog.
- BETTER
Every look stays a conversation
- The problem
- A look could be an all-at-once form, and a single question left an empty band above the input.
- What we did
- The all-at-once form layout is gone. A look can now be a conversation, one question at a time, or a single full-page question, and the website analyzer can no longer propose a form. In the one-question and full-page layouts the question and its answer sit together, centered in the step, so a single question no longer leaves an empty band above the input.
- How it helps
- Your looks are a conversation, one question at a time or one full-page question, with the question and answer together.
- BETTER
Typefaces are hosted Google Fonts
- The problem
- Brand Kit and Intake Bot Design didn't pick typefaces from a hosted Google Fonts set by name.
- What we did
- Brand Kit and Intake Bot Design now pick from hosted Google Fonts by name, including Inter, Space Grotesk, Playfair Display, Lora, and IBM Plex Mono. Website match still maps the site stack onto that set.
- How it helps
- You pick a typeface by name, such as Inter, Space Grotesk, Playfair Display, Lora or IBM Plex Mono.
- BETTER
Everyday look controls, with Advanced tucked away
- The problem
- Everyday controls and expert ones like size, composition, progress, header and motion were shown together.
- What we did
- Brand Kit and Intake Bot Design now show colors, typeface, corners, spacing, how questions arrive, and how answers look. Size, composition, progress, header, and motion sit under Advanced. Website match still writes the full look.
- How it helps
- You see colors, typeface, corners, spacing, how questions arrive and how answers look, and the rest sits under Advanced.
FIXED
What you reported is fixed.
Fewer snags for you and your clients while they're being served.
the fixes count too. they're most of it
Website match shows wait time and keeps looks on this draft
Backgrounds actually paint, and wordmarks stop crowding the header
Side-by-side looks the same in preview and on the live bot