SuperProcess SuperProcess
← Platform
Agents

Agents that do real work under process control.

Agents read evidence, return structured fields, and call only the tools they are allowed to use. The workflow decides when they run, when they stop, and who approves the outcome.

Agent task anatomy

One bounded worker inside one workflow step.

Step

Extract invoice fields

Allowed tools

Reader, validator, risk screen

Human gate

Required above policy threshold

Trace

Prompt, tool calls, output, reviewer

What agents are

Not chatbots. Not scripts. Process workers.

The simple version: an agent is software that can understand context, choose an action, use tools, and produce work. The enterprise version needs boundaries, approvals, and a trace.

An agent is a bounded worker

It receives a task, reads the context, decides what to do next, and returns structured work.

A workflow tells it when to act

The agent does not wander across the company. A process step gives it a specific job.

Governance tells it what is allowed

Tool access, data scope, approval rules, and output schemas are defined before it runs.

SP
Supply Planner Agent
agent · S&OP workflow
Deployed
Provider options
OpenAI
planning reasoning model
also available
Anthropic Mistral Private LLM
Tool access
4 on · 1 off
SAP
inventory, capacity, orders
Slack
planner questions and approvals
Sheets
scenario table and assumptions
Optimize API
scenario optimization service
Email
external recipient access
Prompt · NLP
Natural-language task
converted into bounded agent steps at runtime
prompt v4
prompt

You are the supply planning agent for the North America S&OP cycle.

Use approved demand, inventory, capacity, and assumptions sources to compare feasible plans.

Produce three options with service, margin, and expedite-risk tradeoffs.

Summarize the recommendation and wait for planner approval before any system writeback.

retry 3x · 60s timeout planner approval before writeback

Invoice extractor agent · version 7 · deployed to production

How teams create one

Define the job before the model starts reasoning.

A useful production agent is not just a prompt. It is a versioned unit of work with inputs, outputs, tools, policies, evals, owners, and deployment history.

Instructions

What the agent is responsible for and what it must not do.

Output schema

The exact structured result the workflow expects back.

Tools

The approved functions and systems it may call.

Policy

Confidence, risk, cost, and approval rules for the step.

Why this matters

Frameworks make agents easy. Keeping them safe takes primitives.

Structured work

Inputs and outputs are enforced

The agent receives clear evidence and returns structured fields. Schema drift fails in staging, not silently in production.

Tool governance

Every call scoped, rate-limited, logged

Tools declared as typed functions. Authn, scopes, and rate limits live with the tool — not in ad-hoc middleware.

Model portability

Swap models, keep workflows

Change the model behind an agent without rewriting the process. Define fallback chains per step.

Agent lifecycle

Define. Evaluate. Deploy. Observe.

01

Define

Schema-first agent: inputs, outputs, tools, model, evals.

02

Evaluate

Run a golden test set. Regressions block the deploy.

03

Deploy

Agent work runs as a versioned, replayable activity.

04

Observe

Every invocation traced — prompt, tools, tokens, cost.

Build agents your operations team can actually trust.

We'll scope one agent for one workflow — end-to-end, production-ready.