OpenAgents Episode 157: Chains of Thought and Action
We define a chain of thought and action (CoTA) as a series of reasoning steps and tool use whereby agentic AI systems show both the intermediate reasoning and the inputs and outputs of actions taken.
We plan a "GitHub issue solver" agent we'll build over the next few videos to show CoTA in action. A possible algorithm:
- Given a GitHub issue, build a repo map from issue (via automated script)
- Identify relevant files (via DeepSeek R1 for reasoning, Mistral Small(?) for structured output)
- Traverse and analyze codebase (file readers, AST parsers)
- Plan changes (DeepSeek R1)
- Generate and test code changes (CI/scripts)
- Create pull request with detailed explanation (GitHub API)
When this agent works well with full transparency, why would you ever use a closed-source alternative?
If you expect your models to show the full CoT, you'd better expect your agents to show the full CoTA!
More 👉 https://openagents.com/cota
Watch on X: https://x.com/OpenAgentsInc/status/1886297781138030777
https://stacker.news/items/874271
Christopher David /
npub1tl…k7fdm
2025-02-03 06:39:33
Author Public Key
npub1tlv67m7xvlyplzexuynmfpguvyet0sjffce3y8vu0suuyuwgzauqjk7fdmPublished at
2025-02-03 06:39:33Event JSON
{
"id": "b867a1196ef0f6a3b19b064a58d161671b15952a5a84e77d5329c89c71ad070d",
"pubkey": "5fd9af6fc667c81f8b26e127b4851c6132b7c2494e33121d9c7c39c271c81778",
"created_at": 1738564773,
"kind": 1,
"tags": [
[
"r",
"https://openagents.com/cota"
],
[
"r",
"https://x.com/OpenAgentsInc/status/1886297781138030777"
],
[
"r",
"https://stacker.news/items/874271"
]
],
"content": "OpenAgents Episode 157: Chains of Thought and Action\n\nWe define a chain of thought and action (CoTA) as a series of reasoning steps and tool use whereby agentic AI systems show both the intermediate reasoning and the inputs and outputs of actions taken.\n\nWe plan a \"GitHub issue solver\" agent we'll build over the next few videos to show CoTA in action. A possible algorithm:\n\n- Given a GitHub issue, build a repo map from issue (via automated script)\n- Identify relevant files (via DeepSeek R1 for reasoning, Mistral Small(?) for structured output)\n- Traverse and analyze codebase (file readers, AST parsers)\n- Plan changes (DeepSeek R1)\n- Generate and test code changes (CI/scripts)\n- Create pull request with detailed explanation (GitHub API)\n\nWhen this agent works well with full transparency, why would you ever use a closed-source alternative?\n\nIf you expect your models to show the full CoT, you'd better expect your agents to show the full CoTA!\n\nMore 👉 https://openagents.com/cota\n\nWatch on X: https://x.com/OpenAgentsInc/status/1886297781138030777\n\nhttps://stacker.news/items/874271",
"sig": "57cbee91dddaa2951160c468c619e0a3a1f7a9dc131a9b9e94653dcbcbaae70acda83cab20b11dfc43d7c8140014f32a712b884375ca7bd588172c1e33283bc3"
}