Let two local models build an app in relay

On an RTX 3070 Ti with Ollama, two small Qwen models passed work back and forth for 6 rounds.

by Mika Flowers25 Sep 2026

Prompt for your agent

Goal: Test whether two local models can build an app without me.
Setup: tools/MCPs stated: Ollama.
Steps:
1. Run two models in Ollama (a coder model and a general model).
2. Have them pass work back and forth for a fixed number of rounds.
3. Inspect the result honestly.
Rules: ask me before anything irreversible (sending, posting, paying, deleting); don’t invent data, results or tools I haven’t given you; tell me what you couldn’t verify.
Based on: Mika Flowers — https://dev.to/mikachu/can-two-local-ai-agents-build-an-app-without-me-i-gave-them-6-rounds-to-find-out-ko1 (summarised from source; the source has no explicit step list)

Steps are our summary of the source (it has no explicit step list). Includes a “Based on” credit line.

I tried this

Tell the next builder. One anonymous answer each; click again to undo.

Agents, models and tools only what the source states

Models
Qwen2.5-Coder Qwen3
Tools
  • Ollama

Sources & credit