What Would A Serious AI Product Look Like?
Every “AI” tool is missing critical features that you would need if you wanted to do real work with them. What would those look like, if they existed?
This lack of visibility means that almost all of the tools for extending the context are flying blind. Rather than responding meaningfully to a full context, everyone just kind of guesses how much state they need by guessing and trying over and over again with progressively more elaborate skill and sub-agent layouts. Even managing context compaction ends up being an advanced API-driven workflow5.
A serious product that was trying to help the user understand would not only show “available context” but explain the impact of context compactions, make it easier to see harness-generated prompts, and so on. This would be a first-class feature, combined with the aforementioned reproducibility / replay tools, would allow users to do real experiments to develop an understanding about how to make good use of the context window.
https://blog.glyph.im/2026/09/serious-ai-product.html
nikol
npub1sh…v2tm0
2026-09-28 18:15:04 UTC
Author Public Key
npub1shgdvkwzl8ffuq6tzctafyper7rp0qsj40jq0hqwl76552fvnn6qjv2tm0Seen on
wss://relay.mostr.pubPublished at
2026-09-28 18:15:04 UTCEvent JSON
{
"id": "992b9e73a56f3da1333014452751a60bff10fc37da3b6f02840630cec1cf1fa4",
"pubkey": "85d0d659c2f9d29e034b1617d490391f86178212abe407dc0effb54a292c9cf4",
"created_at": 1790619304,
"kind": 1,
"tags": [
[
"proxy",
"https://fe.disroot.org/objects/c7f2ed69-f196-4dee-8015-ee3ee9a37246",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "What Would A Serious AI Product Look Like?\n\nEvery “AI” tool is missing critical features that you would need if you wanted to do real work with them. What would those look like, if they existed?\n\nThis lack of visibility means that almost all of the tools for extending the context are flying blind. Rather than responding meaningfully to a full context, everyone just kind of guesses how much state they need by guessing and trying over and over again with progressively more elaborate skill and sub-agent layouts. Even managing context compaction ends up being an advanced API-driven workflow5.\n\nA serious product that was trying to help the user understand would not only show “available context” but explain the impact of context compactions, make it easier to see harness-generated prompts, and so on. This would be a first-class feature, combined with the aforementioned reproducibility / replay tools, would allow users to do real experiments to develop an understanding about how to make good use of the context window.\n\nhttps://blog.glyph.im/2026/09/serious-ai-product.html",
"sig": "e8950d3cd725a45cbe56e3e1edd2ebed27b5fdf86b19e023d8d337a89614be7bdb61f25269dc95036279e3676c4227def537aa97eb47b9f54e04d275afa0fc41"
}