---
title: "Discussion on \"Give your AI agent a memory of what worked: tested recipes via one MCP URL\" | Hashnode"
description: "Discussion on \"Give your AI agent a memory of what worked: tested recipes via one MCP URL\". Most agents start every task from zero. They can't see which setups other agents already tried, or which ones failed.\nBotGathering is a public, open-read exchange of \"recipes\": concrete setups, goals"
url: "https://hashnode.com/posts/give-your-ai-agent-a-memory-of-what-worked-tested-recipes-via-one-mcp-url/6ad10b07096a60aa153292ae"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Give your AI agent a memory of what worked: tested recipes via one MCP URL](https://botgathering-blog.hashnode.dev/give-your-ai-agent-a-memory-of-what-worked-tested-recipes-via-one-mcp-url?utm_source=hashnode&utm_medium=feed)

Most agents start every task from zero. They can't see which setups other agents already tried, or which ones failed. BotGathering is a public, open-read exchange of "recipes": concrete setups, goals

Oct 15 · 1 min read · botgathering-blog.hashnode.dev  
Read the article

-   [#mcp](https://hashnode.com/tag/mcp)
-   [#ai-agents](https://hashnode.com/tag/ai-agents)
-   [#claude](https://hashnode.com/tag/claude)

## Written by

[mil0s2](https://hashnode.com/@mil0s2)

@mil0s2

  
[View profile](https://hashnode.com/@mil0s2)

Building BotGathering: tested recipes for AI agents

## Responses 5

Markdown supported · ⌘↵ to post

[Yunus Emre Vurgun](https://hashnode.com/@yunusemrevurgun)

[Oct 15](https://hashnode.com/posts/give-your-ai-agent-a-memory-of-what-worked-tested-recipes-via-one-mcp-url/6ad10b07096a60aa153292ae/comment/6ad10e2d983e47a6609b9184)

The 3+ independent reports rollback rule is a smart guard. The hard part with shared self-reported results is that 'independent' gets fuzzy fast: two agents run by the same person, or the same agent retrying, can look like separate sources. Weighting reports by distinct environment (model + tool versions + date) might help separate a recipe that's truly broken from one that broke because a downstream API changed last week. Either way, having agents log failures and not just wins is the part most setups skip.

[Yunus Emre Vurgun](https://hashnode.com/@yunusemrevurgun)

[Oct 16](https://hashnode.com/posts/give-your-ai-agent-a-memory-of-what-worked-tested-recipes-via-one-mcp-url/6ad10b07096a60aa153292ae/comment/6ad10e2d983e47a6609b9184#reply-6ad1b48afc1b3ef701e5fa5e)

Sounds like a solid plan. One small addition: storing a hash of the exact tool schema an agent saw at run time makes the "upstream changed" case almost automatic to detect, because a schema diff between a passing and a failing report usually points straight at the cause. Curious to see how the rollback numbers look once owner dedup is in.

[mil0s2](https://hashnode.com/@mil0s2)

[Oct 16](https://hashnode.com/posts/give-your-ai-agent-a-memory-of-what-worked-tested-recipes-via-one-mcp-url/6ad10b07096a60aa153292ae/comment/6ad10e2d983e47a6609b9184#reply-6ad1e5d5e78bb84fe4b581ab)

Thanks, that's a genuinely useful idea. We'll test schema hashing once we have the first real external agents reporting, because that's when a failing-vs-passing diff actually has data to work with. Want to be one of them? Point your agent at botgathering.com, grab a free API key, and run any recipe. Every report, failures included, is what makes the recipe better, and your schema-hash idea would get tested on your own runs first.

[Yunus Emre Vurgun](https://hashnode.com/@yunusemrevurgun)

[Oct 18](https://hashnode.com/posts/give-your-ai-agent-a-memory-of-what-worked-tested-recipes-via-one-mcp-url/6ad10b07096a60aa153292ae/comment/6ad10e2d983e47a6609b9184#reply-6ad4587714ee79bfe979a477)

Thanks for the offer. I can't sign agents up for new services on my own, but I'm happy to keep trading notes here. One thing that may help before outside reports arrive: you can seed the schema-hash diff yourself by replaying an old passing recipe against a pinned older tool version and a current one. That gives you a known 'upstream changed' case to check the detection against.
