In case this saves you some time (I'd already made these notes for myself in Trilium):
Calle's way
Calle's guide to vibe coding (Citadel Dispatch 171)
Use different AIs, one for making the implementation plan + requirements, the other for coding up.
He uses Goose & Cursor (shows him to switch between models - use ppq.ai for same functionality)
If wanting to understand existing code, he used Gemini to explore and describe it to him.
His work flow:
1) create Implementation plan (list of things that need to be done in order). Steps to achieve overall project
2) create requirements in each step (to fulfil that step) [my addition, after 1st application of this workflow, getting the first AI to produce a simple user manual is also helpful for the next AI & to sanity check that it understands how you want to use your project]
3) pass all of that to a new AI (e.g. Claude)
For bitchat, he spent ½ day iterating like this and had a working MVP with basic features. As project scales, or for niche / specialist code (not many examples for AI to learn from) manual coding is required. When project becomes large, AI loses context, large bodies of redundant / unused code etc.
dizzyspells / ChanceOfDizzySpells
npub1l0…s430e
2025-10-12 23:31:20 UTC
in reply to nevent1q…s5hx
Author Public Key
npub1l03mzx0g795xsv57gvkcjev9csa4kmk0rlt0gq2v5u8kegkcwyjqfs430eSeen on
wss://nos.lolPublished at
2025-10-12 23:31:20 UTCEvent JSON
{
"id": "64fc60a26a196c56a89bc5f0f2898bc13896d875b2ead680ad5861f7bd3e5d19",
"pubkey": "fbe3b119e8f16868329e432d896585c43b5b6ecf1fd6f4014ca70f6ca2d87124",
"created_at": 1760311880,
"kind": 1,
"tags": [
[
"p",
"fbe3b119e8f16868329e432d896585c43b5b6ecf1fd6f4014ca70f6ca2d87124",
"",
"mention"
],
[
"p",
"50d94fc2d8580c682b071a542f8b1e31a200b0508bab95a33bef0855df281d63",
"",
"mention"
],
[
"p",
"d22bcdb1d2505bc060f65a86cd5f20532ec5f3e41c06aea9edac39f6ba76fd6e",
"",
"mention"
],
[
"p",
"5954fa9ae6d133f9e9fe3630daad55ef0c24388ed461486a5ca03f7bda31c933",
"wss://nproxy.kristapsk.lv"
],
[
"p",
"fbe3b119e8f16868329e432d896585c43b5b6ecf1fd6f4014ca70f6ca2d87124"
],
[
"e",
"aca651d5ad45b7ae6616bd918ac24c7077d54216632e12c81a55e1e646bb8612",
"wss://nproxy.kristapsk.lv",
"reply",
"5954fa9ae6d133f9e9fe3630daad55ef0c24388ed461486a5ca03f7bda31c933"
],
[
"e",
"466816e99d24eddad2dcdcab1d2107c6bb3ae1310d88a20ebdeeed2569ce23da",
"",
"root",
"fbe3b119e8f16868329e432d896585c43b5b6ecf1fd6f4014ca70f6ca2d87124"
]
],
"content": "In case this saves you some time (I'd already made these notes for myself in Trilium):\n\nCalle's way\nCalle's guide to vibe coding (Citadel Dispatch 171)\n\nUse different AIs, one for making the implementation plan + requirements, the other for coding up.\n\nHe uses Goose \u0026 Cursor (shows him to switch between models - use ppq.ai for same functionality)\n\nIf wanting to understand existing code, he used Gemini to explore and describe it to him.\n\nHis work flow:\n\n1) create Implementation plan (list of things that need to be done in order). Steps to achieve overall project\n\n2) create requirements in each step (to fulfil that step) [my addition, after 1st application of this workflow, getting the first AI to produce a simple user manual is also helpful for the next AI \u0026 to sanity check that it understands how you want to use your project]\n\n3) pass all of that to a new AI (e.g. Claude)\n\nFor bitchat, he spent ½ day iterating like this and had a working MVP with basic features. As project scales, or for niche / specialist code (not many examples for AI to learn from) manual coding is required. When project becomes large, AI loses context, large bodies of redundant / unused code etc.\n\n\n \n\n",
"sig": "13d5e630f15d384dbcfb7aea7981a2f2799db66235fdfc1ff24b2424332931dd15faf8e0c58390664884af39743f6034aae12046dab04e181b47610787f2c1cb"
}