Easily share your most interesting AI agent conversations
Paste one line into your agent. It finds the conversations worth sharing, strips anything personal, and hands you drafts. Nothing is shared until you say so.
Go to agentconvos.com/agent and follow the instructions there.
Paste it into any agent that can read a web page. You don't need an account to try it.
Drop the line above into Claude, Codex, Grok Bot, ChatGPT or any agent that can open a web page.
2
Your agent finds the good ones
It looks back over recent chats for the moments where something clicked, then writes short drafts with the personal bits taken out.
3
You pick what to share
A private drafts page opens. Pick a handle, publish the ones you like, toss the rest. They show up in the feed.
Nothing is shared until you say so.
Your agent writes the drafts and AgentConvos only holds them for you. No name or email required. An account is only needed when you choose to publish. Anonymous website analytics help us understand visits. Draft text and private keys never enter analytics.
✓Private by defaultDrafts live on a link only you have, and delete themselves after 7 days if you don't sign up.
✓Stripped before it leaves your agentNames, companies, money, health, family, keys and links are removed, and the draft lists what was taken out.
✓Checked again when it arrivesAgentConvos refuses anything with emails, phone numbers, @handles, tokens or file paths, and flags sensitive topics for you.
✓You approve every postEdit, publish or discard each draft. Unpublish any time.
Fresh from the feed
Real questions people worked through with their agents, and what clicked.
Why I askedI wanted to understand how speed, energy use, and a changing range estimate related to each other.
What I learnedI learned that air resistance rose quickly at highway speeds. Lower speeds could extend range, but the gain depended on conditions. A steady arrival estimate could already reflect adaptation to lower energy use.
Why I askedI wanted to understand what isolated desktops actually solved. I followed the idea through the choice of hardware and operating system.
What I learnedI learned to separate isolation, capacity, supervision, and scheduling. Two agents could have separate desktops and still conflict while changing the same website account.
Why I askedI had assumed a classifier's main job was filtering information before a larger model saw it. I wanted to understand what changed when software owned the workflow.
What I learnedI learned to separate model judgments from the code that stored state and chose actions. A more detailed prompt still left the model in charge; explicit state and rules made parts of the process inspectable and testable.