Latest version: v1.9.0

Changelog

Follow our journey as we build the future tools for businesses. Here you'll find all updates, new features, and improvements.

v1.9.0 12 May 2026 21 changes

Routine Engine v2, AI Platform & Voice Agent UX Overhaul

The largest internal refactor in Worqs' history — paired with visible improvements across every surface. The Routine engine is rewritten from scratch with three 'kinds' (scheduled, event-driven, reactive), declarative spotter rules, finding merging, a voice runtime, and tight integration with briefings and the Worqs Assistant. A brand-new AI Platform replaces the legacy memory tables with atoms, conversations, entities, and working context — all four agent surfaces now share a unified memory core. The voice agent got a thorough UX redesign with hero cards, multimodal screen content, and a simplified field-collection flow. Compliance cycles, an mTLS proxy for secure outbound integrations, SMS signatures, and lower Telnyx latency round out the release.

Routine engine v2 — scheduled, event-driven, and reactive as first-class 'kinds' with declarative spotter rules AI Platform — unified memory core with atoms, conversations, entities, and working context across all agent surfaces Voice agent — complete UX redesign with hero cards, card carousel, and unified field-collection flow Compliance cycles — version-tracked review cycles with drafts, approval, and evidence package export mTLS proxy via Cloudflare Worker for secure outbound integration calls with certificate provisioning Per-tenant SMS signatures + denser Live prompt and faster turn-taking in telephony
Show less
New Feature

Routine engine v2 — three kinds in a unified framework

Routines now come in three distinct kinds: scheduled (run on calendar), event-driven (fired by state transitions and role-bearers on the entity), and reactive (listen in on active AI conversations). The editor is kind-aware and hides irrelevant sections per kind, with a three-card picker as the new entry point. The list page groups routines by kind and surfaces reactive-coverage hints.

New Feature

Declarative spotter rules for reactive routines

Reactive routines use a declarative rule interpreter that runs over each conversation turn. A generator rewrites natural-language spotters into structured rules with tenant terminology support; rules are stored in the database and regenerated via Inngest. The result is faster and cheaper detection than per-turn LLM calls.

New Feature

Reactive routines in Worqs Assistant and voice agent

The AI Bar and voice agent now run spotter rules on every user turn and can suggest (or directly launch) a relevant routine when signals are detected. The voice agent additionally has a 'propose-objection' window with a sentiment gate so suggestions land in the right tone. Active routine sessions are exposed through a resume tool in both agents.

New Feature

Conversation engine for routines — voice + text runtime

A full conversation engine with text runtime, voice runtime, and telephony scaffolding lets routines collect fields, follow up, and close autonomously. The scheduler ticks every five minutes with a tolerance window, Realtime broadcast keeps the list view live, and an admin tab shows sessions and analytics. Briefings now persist routine findings as memory atoms.

New Feature

Routine finding merging and concurrent sessions

Multiple routines sharing the same fire pattern and assignment are automatically merged into a single group in the list view — no more double-pinging the same recipient. Opportunistic spotters can propose a routine launch from an ongoing conversation, and users can start a routine manually at any time.

New Feature

AI Platform — unified memory core

The old memory and session tables have been replaced by a new AI Platform built on three primitives: conversations (with rolling summary), memory (atoms in six categories, four-level scope: platform → tenant → user → entity), and working context (token-budget-aware prompt assembly). All four agent surfaces — AI Bar, Architect, Voice, and Phone — read and write through the same core. Migration runs as shadow-write for a safe rollout.

New Feature

Three memory recall tools with RRF fusion

Agents can now query memory three ways — by topic, by entity, or on the timeline — and results are fused via Reciprocal Rank Fusion. Atoms can also decay or be archived automatically via a nightly Inngest job, and sensitivity classification is baked into the extraction prompt so private data is handled correctly from the start.

New Feature

Pattern miner with cross-conversation aggregation

The platform aggregates patterns across multiple conversations — when the same observation recurs across different users or sessions, a rule is proposed that administrators can review and confirm in a new pattern-review UI. Includes recall rate limits, a platform metrics page, and quota enforcement.

New Feature

Voice agent — complete UX redesign

The voice page has been rebuilt from scratch: new VoiceInterface shell, seven types of hero cards (list, document excerpt, diagram, image, markdown, form, confirmation), a card carousel instead of overwriting, a new mute pill with tap and 500 ms long-press, a voice menu with voice picker, ambient gradient background, and a status bar with the Worqs logo. Render crashes and hydration mismatches are fixed via layout:false.

New Feature

Unified field-collection flow in voice

A single field-collection flow now handles both issues and business objects. Values for reference fields (user, department, location, BO) are resolved against existing entities, and a dropdown is shown when the match is ambiguous — tap-to-select works for both lists and option fields. Sticky-hero ensures the card doesn't flip back to the welcome screen while the user is thinking.

New Feature

Voice→chat handoff with summary

When a user transitions from voice to text, the handoff carries a one-line summary so the chat agent can pick up exactly where the voice session left off. A per-(tenant, entity) cache for context-delta cuts navigation latency by 50-150 tokens.

New Feature

Compliance cycles with drafts and evidence packages

Reviews are now organized into version-tracked cycles: create via wizard, collect evidence, submit for approval as a draft, and publish atomically only once approval lands. Cycle tab with a framework activity timeline, skip log for proposed edits, an auditor view, and evidence package export. A 'force cycle' gate prevents publishing outside an active cycle where required.

New Feature

AI implementation consultant — rebuilt

The compliance consultant has been rewritten from scratch with multi-step planning, single-click framework cards, and updated guidance for the adoption flow. Multi-framework adoption lets several frameworks share the same evidence links simultaneously. A post-adoption prompt reminds the user to start a review cycle.

New Feature

mTLS proxy via Cloudflare Worker

Outbound integration calls that require mTLS (Nextus, banks, certain government APIs) are now routed through a Cloudflare Worker that handles client certificates for you. Includes a certificate provisioning service, HMAC signing, automatic expiry monitoring, a runbook, and a new mTLS configuration surface in the integrations UI.

New Feature

Per-tenant SMS signatures

Tenant administrators can configure an SMS signature that is automatically appended to outbound messages — including an opt-out hint for GDPR compliance where required.

New Feature

Custom views — storage foundation

The first step in a system for tenant-authored detail, list, and relation views. Storage tables, schema versioning, and support for EnterprisePicker, Icon, and Image sources are in place. The live author UI and runtime compiler land in the next release.

Improvement

Telephony — denser Live prompt and faster turn-taking

The Gemini Live system prompt in the call engine has been densified by 53%, VAD thresholds are trimmed, and post-tool mute is shorter for faster turns. The transfer lifecycle in phone-worker now handles the bridge, initiation phase, and deferred WS-close correctly — outbound transfer legs are no longer hung up prematurely and the Gemini inference meter is stopped when the bridge is up.

Improvement

Atomic conversation writes + nightly partitioning

Conversation messages are now written via an atomic RPC that removes a TOCTOU race on concurrent writes. A nightly Inngest job provisions next month's partition for the tool-call log so writes never stall on a missing partition.

Bug Fix

Telnyx webhook visibility and delivery

Closed gaps where Telnyx webhooks could be silently dropped — all events are now logged to `telnyx_webhook_log` and missing events can be traced. The phone number list now shows numbers even when the tenant doesn't have an active subscription.

Bug Fix

Voice agent — multiple stability fixes

ClientContent 1007 close on mid-session updates is fixed, duplicate speech from parallel tool calls is deduped, screenContent from multiple tool families (document, business_object, utilization_report) is normalized at the API boundary, and flow tools now get an explicit speakable response so the agent doesn't go silent mid-flow.

Bug Fix

Issue filtering and attachments

The issues page now filters against the correct table — `file_attachment` instead of the non-existent `issue_attachment`. Entity references in memory atoms could go stale on rename, which has also been fixed.

v1.8.0 27 April 2026 14 changes

Billing Platform, Smarter AI Router & Voice Agent

One of the platform's biggest releases: a complete billing engine with EU VAT, metered telephony, and dunning; a hybrid AI router that learns from your queries and now handles 93.7% of Worqs Assistant traffic; the voice agent migrated to Gemini Live 2.5 native audio; the Architect agent can now read the web, draw workflow diagrams, and propose design diffs directly in chat. Plus: bulk import of business objects from CSV/Excel/JSON, the first iteration of AI-driven document assessment, and a substantially improved telephony and messaging stack.

Complete billing platform with EU VAT, dunning, and purchasable SMS and call-minute packs Hybrid AI router that learns from user queries — Worqs Assistant at 93.7% accuracy Voice agent migrated to Gemini Live 2.5 native audio + new per-tenant voice router Architect agent v2: web access, workflow flowcharts, ERD overview, and design-diff in chat Bulk import of business objects from CSV / Excel / JSON with AI-driven column mapping Telephony / SMS chain generalized to 'message received' — works for SMS, email, and voice
Show details
v1.7.0 17 April 2026 9 changes

AI Agent, Categories & Documentation with Diagrams

The AI Agent is here: automate entire workflow steps with tool-use, learn from your decisions, and a rule engine that makes the agent smarter with every run. Full visibility through a three-level automation dashboard. Group business objects into categories, render system diagrams directly in your documentation, and several important fixes in the approval flow.

AI Agent — automate workflow steps with supervised or autonomous execution Learning system — the agent improves continuously from your approvals and corrections Three-level automation dashboard with drill-down Categories for business objects Mermaid diagrams in your tenant documentation
Show details
v1.6.0 16 April 2026 14 changes

Fill with AI, Views, Enterprise Scoping & Voice

Upload a document, snap a photo, or record a voice memo — AI fills in the form for you. Custom views with resource planning and timesheets. Enterprise scoping isolates data per subsidiary. Gemini Live 3.1 delivers faster voice interaction.

Fill with AI — extract field values from documents, images, and audio Custom views with resource planning and timesheets Enterprise scoping for multi-company groups
Show details
v1.5.0 15 March 2026 8 changes

Proactive Routines, Telephony & AI Architect

Routines make your AI assistant proactive — it monitors your business objects and issues and reports what's relevant in the morning briefing. Built-in telephony with AI call scripts and automatic transcription. The Architect builds entire systems for you in a multi-agent pipeline.

Proactive AI routines with natural language builder Built-in telephony with AI call scripts Multi-agent architect pipeline
Show details
v1.4.0 18 February 2026 13 changes

Compliance, AI Chat & Generation Rules

Major release with a complete compliance framework for ISO and EU regulations, an entirely new AI chat experience with rich cards and tools, and automatic generation rules for calculated fields.

Compliance framework with 15 standards New AI chat with tools and rich cards Generation rules for automatic field values
Show details
v1.3.0 28 January 2026 11 changes

BIM Viewer, Customer Portals & Voice Agent

Major release introducing 3D BIM model viewing, customer-facing portals, and an AI voice agent for hands-free interaction.

Interactive BIM/IFC 3D model viewer Customer portal with branded access AI voice agent for natural conversation
Show details
v1.2.0 6 January 2026 5 changes

Native Approvals & Admin Dashboard

Major release introducing native approval workflows and a comprehensive system admin dashboard.

Complete approval system with delegation support System admin dashboard for multi-tenant management Stripe billing integration
Show details
v1.1.0 15 December 2025 5 changes

Floor Plans & Advanced Visualizations

Introducing floor plan visualization and 14 new ways to view your business object relationships.

Interactive floor plan editor 14 relationship visualization types Schema DSL for AI-powered configuration
Show details
v1.0.0 1 November 2025 5 changes

Initial Release

The first public release of Worqs - The Operating System for Your Business.

Custom business object types Visual workflow builder Document generation
Show details

Never Miss an Update

Subscribe to our changelog and get notified about new features and improvements directly in your inbox.