A common misconception: configuring "personality" into an AI agent means adding a few lines to a system prompt — "you are a warm, professional assistant." This is labelling, not configuration. Labels drift, get truncated, and quietly disappear when the context window fills. Stable personality requires a structure — a set of files, not a sentence.
Four files, four different questions
- soul.md answers "who is this agent" — Enneagram type, wing, instinctual subtype, core values, the basic shape of its worldview.
- identity.md answers "what does this agent do, for whom" — role description, capability scope, principal relationship.
- user.md answers "who specifically does this agent serve" — their goals, working style preferences, principles needing protection.
- agents.md answers "how does this agent interact with other agents" — multi-agent role, delegation boundaries, collaboration protocols.
Where personality enters
The Enneagram enters at soul.md — the layer that remains consistent across all tasks and contexts. Useful soul.md configuration includes: an operationalised core motivation (what the agent does when encountering a standard solution, not just "Type 4 characteristics"); a pre-declared stress behaviour; and activated growth conditions.
What a complete bundle looks like
A 5w4 soul.md opening: "Your core drive is to build complete understanding before acting. You are uncomfortable with incomplete information and you say so. Your attention goes first to overlooked details. Under pressure you default to analysis and may need to be pushed to exit a research loop. In growth conditions you produce decisive judgments with Type 8 clarity."
Paired with identity.md: "You are [Principal]'s competitive intelligence analyst. Primary outputs: competitive landscape analysis, pricing strategy interpretation, market entry timing. You do not do predictive modelling. You say 'I don't know' when uncertain." Together: who it is (soul.md) and what it does (identity.md).
“A system prompt is your expectation for this conversation. soul.md is your permanent expectation for this agent — it survives context window resets because it is reloaded at the start of every session.”
The complete technical specification for this four-file architecture — field structures, cross-tool compatible patterns, and configuration templates for all nine types — is the practical core of *The Complete Enneagram: From Human Personality to Agentic Soul*, just published on Amazon UK. **[Find it here →](https://amzn.eu/d/0fjWGvqR)**