Erase the Person, Keep the Record
Removing someone's account clears their name and email address without erasing what they did. Every approval, edit, and run they touched stays readable, attributed to a Deleted user.
Category Archive
Category: Announcements
Posts filed under Announcements.
Approvals Now Carry a Name
Human intervention forms are answered by a signed-in member of your organization, in the environment that raised the request, and the decision is recorded against the person who made it.
Enterprise Governance Is Now Built In
Single sign-on, custom roles, deployment pipelines, a full audit log, access policy, org API keys, disaster recovery, and a compliance archive - one coordinated release for teams that have to answer to an auditor.
Deployment Pipelines: Promote Rule Changes Like Code
Project releases capture every ruleset, condition, and action set in one immutable numbered snapshot, and deployment pipelines move that snapshot through your environments with approval gates, drift visibility, and org-wide policy floors.
Custom Roles and Auditable Access Reviews
Define up to 25 additive roles of your own, decide separately who may see real PII in a trace, and export a dated point-in-time report of every person's access to every environment.
Single Sign-On: Bring Your Own Identity Provider
Organization members can now sign in through your own identity provider instead of a personal social account. Both OpenID Connect and SAML 2.0 are supported, with DNS-verified domain capture and optional enforcement.
Goal-Driven Evaluation: Start From the Answer You Want
Name the context keys a run should establish and the engine works backwards to find the rules that can produce them, firing only what the answer actually needs. Every run comes back with a proof tree that shows how the value came to be, or which input was missing.
See Which Rules Actually Fire
The new Analytics page shows how your rules behave in production: how often each rule fires, what decisions your RuleSets are producing, and how runs are turning out day by day.
Rules That Schedule Themselves: Effective and Expiration Dates
Give any rule an active date window and a policy change turns itself on and off. Schedule a price change weeks ahead, retire a promotion at midnight, and prove both work with a simulated run date in your tests.
Automatic Retraction: Conclusions That Take Themselves Back
Mark a rule as retractable and its conclusions are only true while the rule still matches. When the facts behind a decision move, the decision comes back out, and so does everything built on top of it.
Verify Your Rules Before They Run
The new Verify tab reads your RuleSet without running it and tells you what is wrong: rules that can never fire, rules that duplicate each other, two rules fighting over the same value, keys nothing supplies, and input combinations no rule covers.
Your AI Agent Can Now Complete Human-in-the-Loop Forms
Workflows that pause for human review no longer dead-end an AI agent. Over MCP, your assistant can read the pending form, submit your answers on your behalf, and bring back the final result — with a per-action switch that keeps in-person approvals in person.
New in AI Rule Engine: Inference, Traces, What-If, and More
A tour of what shipped this month — forward-chaining inference, explainable traces, what-if simulation, derived facts, the expression language, and collection conditions — with a link to the full story on each.
Forward-Chaining Inference: Rules That React to Their Own Results
Turn on Inference and your rules re-fire as their actions change the facts other rules read — one firing at a time by salience, only where inputs actually changed, until the run reaches a stable state.
Explainable Rule Runs: See Why, Not Just What
Most engines tell you the result. The inference trace tells you the reasoning — every firing in order, a green/red condition tree with the actual values, every context change, and a plain-language explanation on demand.
What-If Simulation: Change an Input, See What Flips
Edit the inputs and hit Compare. AI Rule Engine runs your RuleSet twice in the sandbox and shows exactly which rules and conclusions changed — each traced back to the input that moved it. No metered run, no side effects, nothing in your history.
Derived Facts: Values Your Rules Compute for Themselves
Stop passing in values you could compute. Derived facts are context values resolved on demand from other values — defaults, shared definitions, expressions, even lazy AI classifications — evaluated only when a rule actually reads them.
The Expression Language: ctx.price * ctx.qty, Anywhere a Value Goes
A small, deterministic expression language for computed values and conditions: read context with ctx.key, 32 built-in functions across strings, math, dates and arrays, null-safe with coalesce, and validated as you type.
Collection Conditions: One Clause Instead of a Loop
Aggregates and quantifiers let a single condition reason about a whole array. Sum the line items and compare, or ask whether any element clears a threshold — no extra rules, no manual unrolling.
A Redesigned RuleSet Editor, Now With a Decision Table
The RuleSet editor has been rebuilt around a DMN-style decision table: every rule is a row, every context key is a column, and you can author conditions and outputs inline without opening a single dialog.
AI Rule Engine Now Natively Supports Azure OpenAI
AI Rule Engine now includes native support for Azure OpenAI models, and when paired with our dedicated Azure hosting plan, your data never leaves your own tenant.
Generate a Complete Workflow from a Natural Language Prompt
AI Rule Engine now lets you create a new project by describing what you want to automate. The AI generates the rules, conditions, and actions that make up your workflow — no blank canvas required.
Rich Text Editor for Extensions
AI Rule Engine extensions now include a built-in rich text editor, letting you add formatted instructions, embed images, collect user input with a variety of field types, and control UI visibility with conditional blocks.
Introducing the Human Intervention Action
AI Rule Engine now includes a Human Intervention action that lets you design rich-text forms and collect user feedback in the middle of an automated workflow.
AI Rule Engine Now Natively Supports Anthropic AI Models
AI Rule Engine now includes native support for Anthropic AI models, making it easier to build governed workflows with Claude and other supported models.
Introducing the Visual Workflow Editor
AI Rule Engine now includes a visual workflow editor for exploring branches, editing nodes inline, and saving workflow drafts from an interactive canvas.
Start on a Shared Host — No Azure Subscription Required
AI Rule Engine offers shared-host plans (Free, Pro, Team, and Enterprise) with no Azure subscription required, plus dedicated hosting in your own Azure subscription on Enterprise.
Introducing Model Context Protocol (MCP) Support
AI Rule Engine now supports MCP so AI assistants can initiate workflows, read files, inspect ruleset run logs, and operate with per-instance permissions.
Introducing the XML Create Action for AI Rule Engine
Build XML payloads inside AI Rule Engine with a dedicated XML create action, similar to the existing JSON create action.
Introducing Project Templates for AI Rule Engine
Save projects as reusable templates, start new projects faster, and publish templates to the marketplace similar to extensions.
Introducing Organizations and Shared Environments for AI Rule Engine
Organizations now own projects, templates, and extensions, while environments move to the organization level so teams can share infrastructure and reduce cost.
Introducing No-Code Extensions for AI Rule Engine
Extend and share AI Rule Engine functionality without writing code.
AI Rule Engine Now Natively Supports ChatGPT Integration: Power Up with Multiple AI Models!
Exciting News: AI Rule Engine Now Natively Supports Gemini Integration!
Welcome to AI Rule Engine!
Introductory video and post about AI Rule Engine