The Agent Isn't the Thing You Design

Description and use

Enterprise AI workflows often center on agents, complicating auditability. ICM replaces the agent with a folder‑structured context, enabling a single agent to perform sequential stages with editable intermediate outputs.

Problem

Enterprise AI workflows often center on agents, leading to complex, hard‑to‑audit pipelines.

Outcome

Using ICM, a single agent can perform multi‑stage workflows with versioned, editable outputs, reducing agent overuse and improving auditability.

Workflow

• Define a stable reference folder (Layer 3) with rules and constraints.
• Create numbered stage folders (e.g., 01‑research, 02‑draft, 03‑review) each containing a CONTEXT.md contract.
• Run the agent to read the contract and reference folder, generate output into the stage’s output folder.
• Allow a human to edit any output file before the next stage runs.
• Iterate stages sequentially, committing changes to Git for auditability.
• Use a pipeline to automatically run validators between stages.
• Repeat until final output is approved and frozen.

Evidence

If the prompts and context for each step already live as files in a well‑organized folder tree, one agent reading the right files at the right moment can do the job a multi‑agent framework would do.

Source

One agent, three stages. Each stage reads its contract plus the shared rules and writes to a folder the next stage reads.

Source

Every output is an edit surface. A person can open any intermediate file and fix it, and the next stage picks up the fix.

Source

If the output comes back wrong, fix the contract it read, commit and rerun.

Source