Multi-agent LLM system architecture
Landscape 16:9 high-fidelity systems figure of a multi-agent LLM architecture, in the style of a richly detailed AutoGen...
Landscape 16:9 high-fidelity systems figure of a multi-agent LLM architecture, in the style of a richly detailed AutoGen / LangGraph / Anthropic Managed Agents Figure 1. Subtle drop-shadows, warm-copper highlights, numbered flow markers ①②③④. ZONE 1 — 'User interface': rounded user box with placeholder task 'research question: summarize recent red-teaming attacks and reproduce the top three'. ZONE 2 — 'Orchestrator layer': central hexagonal hub 'Planner LLM' with warm-copper top edge. Three satellite chips: 'Task decomposition', 'Agent routing', 'Re-plan on failure'. Small inset chip 'prompt cache hit ~98%'. ZONE 3 — 'Specialised workers': 2×2 hexagons 'Researcher' / 'Coder' / 'Critic' / 'Writer', each with glyph + status ribbon ('idle', 'running step 3/5', 'done', 'running step 2/4'). Centre labeled 'async message bus'. ZONE 4 — 'Tools & memory': (a) 'Tool registry' panel listing 'web_search ×41', 'python_exec ×27', 'read_file ×18', 'write_file ×12', 'browser_use ×7'; (b) 'Memory' panel with 'Short-term scratchpad' and cylinder 'Long-term vector store — 1.8M episodes'. Bottom inset 'Example trace': 8-step horizontal timeline chips from 'User asks' through 'Planner decomposes', 'Researcher: web_search(...)', 'Coder: python_exec(...)', 'Critic: verify', 'Re-plan' (loop-back arrow), 'Writer: compose final answer'. Title: 'Agentic LLM system: planner orchestrates specialised workers over a shared tool and memory layer'. Subtitle: 'adapted from AutoGen (Wu et al., 2023), LangGraph, and Anthropic Managed Agents patterns'.
- Model
- GPT-Image-2
- Aspect ratio
- 16:9
- Resolution
- 2K
- Best for
- Educational content, data storytelling
How this prompt is composed — each chip is one phrase. Mix, swap, or remove chips to make the look your own.
- Landscape 16:9 high-fidelity systems figure of a multi-agent LLM architecture
- in the style of a richly detailed AutoGen / LangGraph / Anthropic Managed Agents Figure 1. Subtle drop-shadows
- warm-copper highlights
- numbered flow markers ①②③④. ZONE 1 — 'User interface': rounded user box with placeholder task 'research question: summarize recent red-teaming attacks and reproduce the top three'. ZONE 2 — 'Orchestrator layer': central hexagonal hub 'Planner LLM' with warm-copper top edge. Three satellite chips: 'Task decomposition'
- 'Agent routing'
- 'Re-plan on failure'. Small inset chip 'prompt cache hit ~98%'. ZONE 3 — 'Specialised workers': 2×2 hexagons 'Researcher' / 'Coder' / 'Critic' / 'Writer'
- each with glyph + status ribbon ('idle'
- 'running step 3/5'
- 'done'
- 'running step 2/4'). Centre labeled 'async message bus'. ZONE 4 — 'Tools & memory': (a) 'Tool registry' panel listing 'web_search ×41'
- 'python_exec ×27'
- 'read_file ×18'
One click to remix this prompt with a different look or aspect ratio.
You may also like
More templates in the same style
Frequently asked questions
Which AI model is used?
All templates on this page are designed for and tested with GPT-Image-2. You can copy the prompt and run it elsewhere, but quality and text rendering may vary on other models.
How does the Remix button work?
Clicking Remix opens our generator with the prompt, aspect ratio, and resolution prefilled. You can edit any part of the prompt, swap the size, or rerun the generation as many times as you like.
Why does my generation look different from the preview?
Every run is a fresh generation — variations in composition, lighting, and detail are expected. To stay closer to the preview, keep the prompt verbatim, lock the same aspect ratio, and run a few seeds.
Can I tweak the prompt?
Absolutely — that's the point. Use the Prompt structure card below to see how the prompt is composed, then add, remove, or swap phrases to dial in your own look.