---
title: "Mercury: an agentic work platform | McIntosh Systems"
description: "Mercury combines persistent memory, controlled procedures, verifiable outputs, and auditable agent work. Choose models, providers, and where you deploy it."
url: "https://mcintoshsystems.com/systems/mercury"
---

Mercury

# Agentic work you can verify.

Agents with lasting memory, controlled procedures, and verifiable work. Choose your models, providers, and deployment environment.

[Discuss a Mercury deployment](https://mcintoshsystems.com/contact)

## Context and evidence stay with the work.

### Persistent memory

Carry business context, preferences, and lessons forward across conversations and model changes.

**How memory works**

Stored memories have revision history and references to their source. Corrections update the effective record while keeping earlier revisions available for review. Conversation history remains separate from the model’s active context.

### Controlled procedures

Give recurring work defined steps, required decisions, and completion criteria.

**How procedures work**

Published procedure versions are retained. Work pins the version it follows, so a later revision does not silently change an existing task. Publication authority and tool permissions are controlled separately.

### Verifiable outputs

Keep deliverables, completion requirements, and the checks supporting the result.

**What counts as verification**

Verification can require source-system confirmation, an authenticated human decision, or an agent assessment with supporting references and stated limits. Agent judgment is identified separately from external confirmation. The workflow determines the evidence required.

### Auditable execution

Inspect execution traces, tool results, and approval decisions alongside the work.

**What is recorded**

Work records, conversation history, tool receipts, and server-side audit events preserve the context of execution. Access and configured retention govern what can be reviewed. Sensitive credentials are handled separately from conversation content.

## Your models. Your providers. Your infrastructure.

### Model agnostic

Choose models for the task, balancing capability, cost, and data requirements.

### Provider agnostic

Change supported providers while keeping Mercury’s stored context and work history.

### Host agnostic

Deploy on premises, in your cloud account, or in a hosted environment, with the runtime configured for your host.

## We put Mercury to work in your business.

We deploy agents for document processing, recurring reports, and tasks across connected applications, with procedures, permissions, and completion checks.

Agents use files, browsers, and applications within their granted access. Scheduled routines require a running deployment.

[Our AI implementation work](https://mcintoshsystems.com/services/ai-implementation)

## Before deploying Mercury

**What work can we give Mercury?**

Give Mercury real workloads that follow your team’s processes and procedures. It works independently on its own computer, using files, browsers, and applications to carry out time-consuming or regularly repeated tasks. Define the outcome, permissions, and completion checks, then assign work in conversation or schedule a routine. Your team can focus on strategic decisions while Mercury handles the work.

**Can we change models or providers?**

Yes. Stored memory and history remain independent of the provider. Switch supported models and providers; tool support and task performance vary by model.

**Can Mercury run in our own environment?**

On premises, in your cloud account, or in a hosted environment. We configure application storage, computer runtime, and scheduling; capabilities depend on the host and setup.

**Who decides what an agent may do?**

Tool grants and action policies define authority. Procedures can require human decisions and evidence. Inspect, pause, cancel, or resume work; assigning a task never grants new system access.

## What work would you give an agent?

Tell us the outcome you need, the systems involved, and who should review the result.

[Discuss a workflow](https://mcintoshsystems.com/contact)

## Structured data

```json
[
  {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "Organization",
        "@id": "https://mcintoshsystems.com/#organization",
        "name": "McIntosh Systems",
        "url": "https://mcintoshsystems.com/",
        "description": "Business process consulting, custom software, integration, and AI to improve time-consuming manual work.",
        "email": "hello@mcintoshsystems.com",
        "logo": {
          "@type": "ImageObject",
          "url": "https://mcintoshsystems.com/apple-touch-icon.png",
          "width": 180,
          "height": 180
        }
      },
      {
        "@type": "WebSite",
        "@id": "https://mcintoshsystems.com/#website",
        "url": "https://mcintoshsystems.com/",
        "name": "McIntosh Systems",
        "publisher": {
          "@id": "https://mcintoshsystems.com/#organization"
        },
        "inLanguage": "en"
      },
      {
        "@type": "WebPage",
        "@id": "https://mcintoshsystems.com/systems/mercury#webpage",
        "url": "https://mcintoshsystems.com/systems/mercury",
        "name": "Mercury: an agentic work platform | McIntosh Systems",
        "description": "Mercury combines persistent memory, controlled procedures, verifiable outputs, and auditable agent work. Choose models, providers, and where you deploy it.",
        "isPartOf": {
          "@id": "https://mcintoshsystems.com/#website"
        },
        "about": {
          "@id": "https://mcintoshsystems.com/#organization"
        },
        "inLanguage": "en",
        "breadcrumb": {
          "@id": "https://mcintoshsystems.com/systems/mercury#breadcrumb"
        }
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://mcintoshsystems.com/systems/mercury#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "Home",
            "item": "https://mcintoshsystems.com/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "Mercury agentic work platform",
            "item": "https://mcintoshsystems.com/systems/mercury"
          }
        ]
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "@type": "FAQPage",
    "mainEntity": [
      {
        "@type": "Question",
        "name": "What work can we give Mercury?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Give Mercury real workloads that follow your team’s processes and procedures. It works independently on its own computer, using files, browsers, and applications to carry out time-consuming or regularly repeated tasks. Define the outcome, permissions, and completion checks, then assign work in conversation or schedule a routine. Your team can focus on strategic decisions while Mercury handles the work."
        }
      },
      {
        "@type": "Question",
        "name": "Can we change models or providers?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Yes. Stored memory and history remain independent of the provider. Switch supported models and providers; tool support and task performance vary by model."
        }
      },
      {
        "@type": "Question",
        "name": "Can Mercury run in our own environment?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "On premises, in your cloud account, or in a hosted environment. We configure application storage, computer runtime, and scheduling; capabilities depend on the host and setup."
        }
      },
      {
        "@type": "Question",
        "name": "Who decides what an agent may do?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Tool grants and action policies define authority. Procedures can require human decisions and evidence. Inspect, pause, cancel, or resume work; assigning a task never grants new system access."
        }
      }
    ]
  }
]
```