An agent with a job, memory, and an owner.

What you leave with

• A production agent on a defined loop, not a sandbox chat.
• Starter institutional memory with proposed, accepted, and ask states.
• A written permission model and a runbook.
• One instruction session for the people who will govern it.
• Thirty days of correction after launch.

How the install runs

1. 1.Name the loop. Write the repeating work in one sentence and name the human who can reject the output. If you cannot name the loop, do not buy seats or start an install.
2. 2.Run a Field Survey. Spend two to three weeks mapping the loop, the tools you already pay for, and the facts an agent would need. Helixfield prices this diagnostic at $9,500. It does not include a production agent.
3. 3.Choose the current door and method. Pick the platform that fits access, data residency, cost, and owner preference — Grok bots, OpenAI Astra, Claude, Gemini, Cursor, a mixed bench, or what just shipped. The method we install now is Loop & Graph. When a stronger method lands, we move.
4. 4.Seed institutional memory. Write the facts, rules, systems, people, and open questions the agent must pack. Label each proposed, accepted, or ask. Chat history is not the memory.
5. 5.Wire only the tools the loop needs. Connect the applications the job actually touches. Write permissions down. An agent that can click every app is a liability.
6. 6.Evaluate on live work. Score the agent on real jobs, not a scripted demo. Missing facts become asks. Invented numbers fail the evaluation.
7. 7.Teach the owner. The owner learns the verbs of the current method: pack, act, extract, ingest. They must be able to reject a bad fact and refuse an outbound draft.
8. 8.Accept the handoff. A named human accepts the system before it touches clients. Client-facing output stays drafted until someone says send. Thirty days of correction follow launch.