How it works

It works the way a careful person would.

A chatbot writes the first thing that sounds right. AssistantGeneral runs a real loop — planning, gathering facts, doing the work, and checking itself before it answers.

02The engine

It doesn't guess. It works.

A chatbot writes the first thing that sounds right. AssistantGeneral runs a real loop: it plans, gathers, acts, and checks itself, the same way a careful person would.

123456PlanSTEP 1 / 6
Why it's trustworthy

Four habits that keep its answers honest.

The loop isn't just for show — each step exists to stop the failures that make people distrust AI.

Answers from your files

It retrieves the facts it needs from your own documents and points to the exact source it used — no made-up references.

Does the work with real tools

It builds files, runs numbers, queries databases and calls apps, rather than describing what you could do.

Checks before it trusts

A groundedness gate confirms every claim is backed by a real source; a review pass catches and fixes its own mistakes.

Shows its working

A live plan tracker, an activity log and an inference trace let you see every step and tool call it made.

Under the hood

From your question to a finished answer.

A technical walk-through of what actually happens between you asking and the agent replying.

  1. 01

    Route

    The request is classified and routed to the right model — local by default, or a cloud provider if that task is configured to use one.

  2. 02

    Plan

    A planning pass decomposes the request into concrete steps before any tool runs, the same way a careful person sketches an approach first.

  3. 03

    Retrieve

    Hybrid retrieval pulls grounding context from your knowledge base: vector similarity and keyword search are fused with Reciprocal Rank Fusion, then reranked and deduplicated.

  4. 04

    Act

    Tools execute under policy: file operations, document generation, connector queries, workflow steps — each gated by the three-tier permission model.

  5. 05

    Verify

    A groundedness gate checks every substantive claim against a retrieved source. Anything unsupported triggers a closed re-retrieval pass before it can reach the answer.

  6. 06

    Review

    A review pass re-reads the full output, looking specifically for errors, placeholders and inconsistencies, and repairs them before finishing.

  7. 07

    Finish

    You get the answer or the finished file — plus a full trace of every step, tool call and source it used to get there.

And none of it phones home.

The whole loop runs on your machine by default. See exactly how your data is protected.

Talk to the team that actually builds the software.

Pilots, licensing, demos, security questionnaires, or a question you are not sure is a question yet. All of it lands with engineers and product leads rather than a routing layer, and none of it starts a drip campaign.

Half an hour, no slide deck
A walkthrough with someone who built the thing. Bring the awkward questions.
A pilot in your environment
Every feature unlocked, installed with us on the call, configured for your setup.
Or just email
sales@royalsoftworks.com, answered by a person within one business day.

Send us a message

Tell us what you are trying to do. A person reads it and replies within one business day.

Goes straight to our own mail server. No CRM, no tracking pixels, no marketing list.