OpenRuna
Sign in
← Collections

ATLAS GIC Agent Prompts

Example agent prompt structures from the ATLAS multi-agent trading system — macro regime, sector desk, superinvestor filter, and CIO portfolio synthesis.

Four layered agent prompts from the [ATLAS GIC](https://github.com/chrisworsey55/atlas-gic) open-source framework. These are **example structures** showing role, inputs, analysis framework, JSON output schema, and constraints for each layer. **Run in order:** Macro Agent → Sector Desk → Superinvestor → CIO Agent. Trained production prompts with autoresearch-optimised rules are proprietary; these placeholders are MIT-licensed from the public repository.
  1. 1.

    Layer 1 — Macro Agent

    Macro Agent

    Assess overall market environment and emit RISK_ON / RISK_OFF / NEUTRAL regime signals for downstream trading agents.

    Open
  2. 2.

    Layer 2 — Sector Desk

    Sector Desk Agent

    Identify the best long and short opportunities within a sector, informed by the macro regime from Layer 1 agents.

    Open
  3. 3.

    Layer 3 — Superinvestor

    Superinvestor Agent

    Filter portfolio ideas through a named superinvestor philosophy and produce hold/add/trim/exit verdicts with conviction scores.

    Open
  4. 4.

    Layer 4 — CIO Agent

    CIO Agent

    Synthesise all agent views weighted by Darwinian scores and produce final portfolio actions with risk commentary.

    Open

Overview

ATLAS GIC Agent Prompts is a free collection on OpenRuna. Example agent prompt structures from the ATLAS multi-agent trading system — macro regime, sector desk, superinvestor filter, and CIO portfolio synthesis.

What this collection does

"ATLAS GIC Agent Prompts" is a collection you can copy, adapt, and run with any modern AI assistant. Example agent prompt structures from the ATLAS multi-agent trading system — macro regime, sector desk, superinvestor filter, and CIO portfolio synthesis. It is catalogued next to similar resources on OpenRuna, so the rest of the toolkit you need is close by. Paste it straight into a chat, drop it into a system prompt, or store it as a reusable skill.

Use cases

  • Hand "ATLAS GIC Agent Prompts" to a new teammate so their collection output matches your team's quality bar from day one.
  • Use "ATLAS GIC Agent Prompts" when you need a repeatable collection for professional work without rewriting instructions every time.
  • Reach for it during planning or review sessions when you want consistent, AI-assisted structure.
  • Combine it with related tools and prompts in the same OpenRuna category to build an end-to-end workflow.

Example output

Ask the model to apply "ATLAS GIC Agent Prompts" to your scenario and it returns a structured answer — clear sections, actionable steps, and assumptions stated upfront — ready to paste into docs, tickets, or code comments. A short follow-up turn usually tightens the result to exactly what you need.

Tips by platform

Claude

In Claude, paste the full collection as your first message or add it to Project instructions, then ask Claude to confirm assumptions before it executes. For longer collections, iterate inside the artifact panel.

ChatGPT

In ChatGPT, start a fresh chat and paste this collection verbatim, then follow up with "apply this to [your context]." Pick a current GPT model for coding or reasoning tasks.

Cursor

Add this collection to your Cursor rules and invoke it from Agent mode for repeatable results. Link back to its OpenRuna page in the rule so the source stays discoverable.

Frequently asked questions

What is "ATLAS GIC Agent Prompts"?
It is a collection listed on OpenRuna — Example agent prompt structures from the ATLAS multi-agent trading system — macro regime, sector desk, superinvestor filter, and CIO portfolio synthesis. You can copy and adapt it for ChatGPT, Claude, Cursor, or any other AI assistant.
Is "ATLAS GIC Agent Prompts" free to use?
Most OpenRuna resources are open or CC0-licensed. Check the license shown on this page before commercial use; premium collections are clearly marked as such.
How do I get the best results from this collection?
Replace any placeholders, add your project context, and ask the model to confirm its assumptions first. Iterate over 2–3 follow-up turns rather than expecting a perfect first response.
Does "ATLAS GIC Agent Prompts" work with both Claude and ChatGPT?
Yes — it is model-agnostic text, so it runs on Claude, ChatGPT, Gemini, and Cursor. The tips on this page cover each of those assistants specifically.
Where can I find resources related to "ATLAS GIC Agent Prompts"?
Scroll to the Related resources section on this page, or open the matching category hub on OpenRuna to find connected prompts, tools, agents, and datasets in the same topic area.

Related resources