Soto Systems Lab/Automations/Rev 2026.06/Status: Live

Most “AI agents” are advanced automation.
That’s where the money is.

Operator view: a map of automation levels, where ROI actually lives, and two working examples you can click through. No vendor pitches, no hype.

SEC. 01

The Levels

Adapted from Cobus Greyling’s 5 Levels, simplified for operators. The marked rows are where production systems live reliably right now.

LvlNameWhat it actually isExampleRisk
0ManualA human does every stepSpreadsheet passed between teamsSlow, error-prone
1Scripted AutomationCron jobs, scripts, deterministic chains. No LLM.Weekly poll of HR system, scripted provisioningLow — breaks loudly
2Smart FormsDeterministic chain + LLM for one step (parse, draft, classify). Existing rules still route.Seller describes case in chat → AI fills routing fields → rules routeLow — LLM translates, doesn’t decide
3Action-Taking AgentLLM plans across multiple steps with intermediate feedback. Takes actions in narrow, known domains. Human approves irreversible steps.Onboarding pipeline: detect new hire → draft → provision → flag exceptionsMedium — needs guardrails, audit logs, human approval gates
4Autonomous OperatorLLM makes every decision dynamically“Just handle it” agentHigh — this is where prod incidents come from
5Digital EmployeeFully autonomous, persists state, learns continuouslyNot reliably achievedDon’t try
SEC. 02

Where ROI Lives

The pattern that works

Level 2 to low Level 3. Deterministic workflow + an LLM plugged into the one step that actually needs it — parsing messy input, drafting personalized copy, classifying ambiguous cases. Fortune 500 production agents run about five steps, call one model, and hand to a human for approval. That’s the shape of every system delivering measurable ROI right now.

What MIT found in 2025

95% of enterprise AI deployments delivered zero measurable bottom-line impact. The failure isn’t the model — it’s the approach. Teams build Level 4 when Level 2 would have worked and been reliable.

SEC. 04

Example 1 — Onboarding GUI (Level 1, scripted)

Before: a spreadsheet of new hires passed between HR, IT, and enablement. After: an operator uploads the same sheet, the tool maps titles to tools, drafts emails, generates provisioning queries. Click to send. No LLM required.

onboarding-gui.app

Level 1 · Scripted

Parsed New Hires

No sheet loaded. Click upload to simulate.

Output

Pick an action to generate output.

How it's done: sheet parsed locally, title-to-tool mapping comes from a YAML config the ops team owns. Email drafts open in Outlook. Provisioning commands are shell + SOQL the operator runs themselves. Zero AI in this loop — and that's the point.

GUI writes
  • Cron polls HR — detects hires & leavers
  • Maps job title → tool stack
  • Sends templated welcome emails
  • Runs provisioning + license cleanup
  • Records assigned course + checklist
Deterministic · No LLM · Runs on a schedule
Onboarding
Database
who got hired · their tools · their course · their checklist
Agent reads
  • Reads the GUI's database
  • Answers new hire questions in chat
  • Guides them through their course + checklist
  • Can't answer? Finds the tool/topic owner
  • Messages that expert and routes the answer back
LLM + tools · Talks to people & other agents

The GUI does the deterministic work and leaves behind a clean record of every hire. The agent treats that record as its source of truth — then does what the GUI can't: hold a conversation, walk someone through their course, and reach out to the right expert when it hits a question it can't answer. The GUI runs the process; the agent helps the human.

SEC. 05

The Agent — Levels 1 → 4

The GUI fires the trigger and keeps the database current. The agent reads from it and builds on top — answering, guiding, and reaching out to humans and other agents. Click through each level to see what gets added.

onboarding-agent.demo

Level 1 · Read-only
I'm three days in — what am I supposed to be doing this week?
You're on the New Hire Path → Sales course — 2 of 8 modules done. Next up: "Pipeline Hygiene." Your checklist still has "Book intro with your manager" open.
How do I set up my sequencer signature?
I don't have that documented — best to ask your manager or the enablement team.

How it's done

Reads the GUI's database to know who this person is — their assigned course, their checklist, their tool stack. RAG over onboarding docs answers the rest.

When it doesn't know, it dead-ends at "ask someone." That's the ceiling of Level 1 — it talks, it never acts.

Reads DBRAGRead-only