Tag Archive
Posts connected to the announcement topic.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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 includes native support for Azure OpenAI models, and when paired with our dedicated Azure hosting plan, your data never leaves your own tenant.
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.
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.
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 includes native support for Anthropic AI models, making it easier to build governed workflows with Claude and other supported models.
AI Rule Engine now includes a visual workflow editor for exploring branches, editing nodes inline, and saving workflow drafts from an interactive canvas.
AI Rule Engine offers shared-host plans (Free, Pro, and Team) with no Azure subscription required, plus dedicated Enterprise hosting in your own Azure subscription.
AI Rule Engine now supports MCP so AI assistants can initiate workflows, read files, inspect ruleset run logs, and operate with per-instance permissions.
Build XML payloads inside AI Rule Engine with a dedicated XML create action, similar to the existing JSON create action.
Save projects as reusable templates, start new projects faster, and publish templates to the marketplace similar to extensions.
Organizations now own projects, templates, and extensions, while environments move to the organization level so teams can share infrastructure and reduce cost.
Extend and share AI Rule Engine functionality without writing code.
A New Era of Intelligent Automation
Introductory video and post about AI Rule Engine