New AI platform
Model picker for governance-approved models
The tool testing panel and the Studio AI assistant now show a model selector. It lists the models that your organisation's AI governance settings allow and marks the currently recommended model as the default.
New Quant Cloud
EmDash CMS application template
You can now create an EmDash CMS application on Quant Cloud from a template. EmDash is an open-source TypeScript CMS built on Astro. By default it keeps content in a SQLite database on a persistent volume. It switches to PostgreSQL automatically when you add a managed database to the application. To start, use the Deploy to Quant Cloud button in the template's README, or choose EmDash when you create an application from a template. Starter kit deployments now also generate the secrets that a template declares, such as signing keys, so the application starts without manual setup.
New QuantCode
Terminal coding agent launch
QuantCode is an AI coding agent that runs in your terminal and gets its models only from your organisation's Quant AI services. The first release, 1.0.0, is for Macs with Apple Silicon, and you start it with quantcode or qcode. To install it, run npm install -g @quantcdn/quantcode. To set it up, choose QuantCDN or QuantGov, sign in with your Quant account, and select an organisation. You choose from the models that your organisation's AI governance settings allow, and the default is Claude Sonnet 4.6. QuantCode reads and edits files, runs shell commands and gives tasks to sub-agents. It formats the files it edits and shows language server errors. You can add MCP servers, skills, custom slash commands and AGENTS.md project instructions, and you can resume, fork and undo sessions.
New QuantCode
Organisation agents and handoffs
Agents that your organisation creates in the Quant dashboard appear in QuantCode with their system prompts, models and skills. You switch agents with Tab. QuantGov organisations also get code, plan, security, review and debug agents that Quant manages, and the code agent is the default. When an agent completes its part of a task, it can suggest a handoff to one of these managed agents, and you confirm the switch. When you change organisation with /org, QuantCode loads the models and agents of that organisation.
New QuantCode
Desktop app and Homebrew install
QuantCode now has a desktop app for Macs with Apple Silicon. You sign in with your Quant account and use the same models and agents as in the terminal interface. To install the terminal interface, run brew install quantcdn/tap/quantcode. To install the desktop app, run brew install --cask quantcdn/tap/quantcode-desktop. You can also download both from the QuantCode releases page on GitHub (quantcdn/quantcode-releases). The terminal interface also runs on Linux (x64 and arm64). New versions are available only from Homebrew and the releases page. The npm package stays at version 1.0.0.
New QuantCode
Autonomous coding jobs on GitHub repositories
QuantCode can now work on your GitHub repositories as an autonomous job, without user interaction. To set it up, open the new QuantCode Agent page under AI Services in the dashboard. Install the QuantCode Agent GitHub App on your GitHub organisations or account, and choose the repositories. An AI platform Slack bot or workflow can start a job with one or more tasks. For a change request, the job plans the work, writes the code and tests, reviews the result and opens a pull request. For a review request, the job posts the review on the pull request. The QuantCode Agent page lists your organisation's jobs with their status, repository and a link to the pull request.
New QuantCode
AI spend display
QuantCode shows your AI spend for today and for this month. If your organisation sets per-user daily or monthly budgets, QuantCode also shows each budget and the percentage that you used. The spend is in the sidebar of the terminal interface and in the title bar of the desktop app. When you have used 80% or more of your daily budget, the desktop app shows a warning when you send a message.
New QuantSearch AI
Drupal faceted search and metadata field mapping
The quantsearch_ai Drupal module now supports flexible metadata field mapping. You can map any Drupal field to a custom metadata key that is sent to the search index, instead of relying on fixed title, body, summary and tags fields. You can enable faceted search on the search page block, and configure preset filters (JSON) on each search widget block. A preset filter applies to every search from that block, for example {"content_type":"policy"}. The block configuration form validates preset filter JSON before it saves.
New QuantSearch AI
Team members and invitations
On Enterprise plans, you can now invite people to your QuantSearch AI organisation from the dashboard settings page. You give each invitation the admin or member role. Invitees accept from the link in the email they receive. From the same page you can see the organisation's members, change their roles and remove them.
New Search
AI search v3 API
A new project-scoped AI Search API is available under /api/v3/organizations/{org}/projects/{project}/ai-search/. It is the first documented API for AI Search in Quant projects. It does not apply to the separate QuantSearch AI service at quantsearch.ai. It covers the full lifecycle. You can enable or disable AI Search and manage its settings (public access, request limits). You can ingest pages, list indexed pages with cursor pagination, and delete the index. You can also run semantic search and AI chat, get usage statistics and top query analytics, and trigger a crawl. The API documentation now covers these endpoints.
New Studio
Rich-text editing in the preview
When you edit an entry, you can right-click text in the live preview to make it bold, italic, underlined, struck through, code or a link. The same menu changes a block to a paragraph or heading, and inserts a paragraph, heading, list, code block or image below it. Double-click an image in the body to replace it from your media.
New Studio
Component props panel
Clicking a component in the live preview opens a resizable props panel with that instance's values. Changes you make there re-render the preview straight away, so you can try values out. They are not saved to the page source.
New Studio
Unsaved edits kept across page reloads
The Studio file editor now stores unsaved edits in browser local storage and restores them automatically if you refresh or navigate away before saving. Unsaved edits are stored per project and branch, so work on different branches stays separate. A dot marks files with unsaved changes, and a "Discard changes" action lets you abandon those edits when needed.
New Terraform
AI agent and Slack bot resources
The Terraform provider now includes quant_ai_agent and quant_slack_bot resources, allowing AI agents and their associated Slack bots to be managed as infrastructure. Both resources support full CRUD and import.
New Terraform
AI skill, vector database and governance resources
Provider v5.2.0 adds four resources: quant_ai_skill manages AI skills that you define inline, quant_ai_vector_collection and quant_ai_vector_document manage vector database collections and their documents, and quant_ai_governance manages your organisation's AI governance settings as code.
New Terraform
AI custom tool resource
A new quant_ai_custom_tool resource lets you define custom AI tools in Terraform. You can supply JavaScript edge function code directly in the resource configuration — the platform deploys it automatically and registers the tool endpoint.
New Terraform
AI agent overlay resource
A new quant_ai_agent_overlay resource lets your organisation customise a global AI agent without changing the base agent. A global agent is an agent that Quant manages, such as the QuantGov managed agent quantgov-code. You set its ID in agent_id, and the agents API marks global agents with isGlobal. An overlay can set the model and temperature, add text to the system prompt, add or disable tools and skills, choose vector collections and set a guardrail preset.