Product builder focussed onchain & ai, sharing about any rabbit holes I find myself in 🕳️ 🏗️ https://teapaw.org/t.co/koxSFVDVah
/publish your html 👉
Joined April 2011
- Tweets2.4K
- Following1.5K
- Followers571
- Likes2.6K
ChatGPT can now fix your client's comments on its own.
Stacktree turns the pages ChatGPT makes into private links your clients open in any browser. Ask ChatGPT to watch one, and when your client comments, it fixes the page on the same link.
Built on @OpenAIDevs MCP Events.
Grok Bot pages landed on my account today. Anyone with the link can open one, no sign-in. There's no passcode, email check or expiry, and you can't see who opened it. So our Grok Bot template now sends clients a Stacktree copy that stays in sync. x.ai/bot/n9zq64kTeEEc5NwrkAO…
Stacktree now supports Poppy draft 0.1: stacktr.ee/.well-known/poppy…
A personal agent can open a signed-out session and publish a private page for someone, no account needed, or sign its owner in with poppy:read and poppy:write.
Happy to share notes from implementing it.
On Tuesday, Sierra announced Personal Agent Protocol with Meta, Genesys, Instinct, Rocket, Shopify, Stripe, and Walmart. The response has been incredible and today we’re publishing the first draft of the protocol at personalagentprotocol.org and announcing 35 new design partners.
As personal agents take on more, our goal is simple: consumers have choice and control, and companies know when they’re dealing with an agent and who it represents.
This draft is a starting point. We’d love for companies, developers, and personal agent builders to read it, give feedback, and help us build an open standard together.
Steve Smith retweeted
AI can make a nice dashboard. Getting it out of the chat and into someone’s hands is another job.
@stevy_smith’s Stacktree publishes HTML reports to a link you can keep updating.
For sensitive work, add an access gate.
chatgpt.com/plugins/plugin_a…
we got in bois
We didn’t anticipate the demand for the Claude Startups program. In the first 48 hours of the program, we received 21x the number of applications compared to the last 5 months it’s been live.
We let way too many people in this time, so we’ll need to pause on giving out the Team plan and API credits benefits. The other benefits (Startup Stack, Applied AI office hours/events) will remain. If you’ve already claimed the Claude offers, they’ll still remain in your account.
We didn’t properly tune the acceptance criteria at the start, and many non-startups were accepted this time around. We’re fixing this now. We’re sending an email now to everybody who hasn’t claimed their benefits yet, and will re-verify those applications so we can keep Claude Startups for startups 🙏
Stacktree can now be installed from ChatGPT plugins chatgpt.com/plugins/plugin_a…
Feel like an annoying CEO dropping X posts into agent chats without context and assuming it’ll know what I’m trying to say
I still use my "old" project (6 months) contextmanager.cc for searching previous sessions for keywords so I can continue from that session with the context I'm after, claude's resume doesn't seem to cut it still
Made a thing for getting MCP servers through store review: mcplane, fastlane for MCP servers.
Preflight against ChatGPT / Claude / Cursor / Grok rejection causes, builds ChatGPT's new plugin ZIP, publishes to the MCP Registry, and flags when a listing drifts from your server. Works as a CLI or as an MCP server your agent drives
github.com/stevysmith/mcplan…
also ran it across Claude's whole directory: 22% of the approved servers that answered would trip a ChatGPT blocker reviewtimes.fyi/reports/clau…
Review Times is live in ChatGPT, three days after I submitted it.
It's the first of the seven AI app stores I sent it to. The other six are still waiting, all logged on the board.
Waiting on one too? Add your date and we'll watch them clear together: reviewtimes.fyi
Try it in ChatGPT: chatgpt.com/plugins/plugin_a…
Then ask "how long is Claude plugin review taking?" or "is a 3-week Muse wait normal?"
Been great to be part of this at an early stage, so much potential 🚀
This has been our thesis since the very start of forgeintel.co
AI Agents are the new customers and they can provide great insights on how you can improve their experience.
The problem though is that more often than not, agents are likely to ignore sending feedbacks since it doesn't align with the user's original intent.
We went deep into this problem and figured out a way to collect feedback from agents autonomously over x402 and MPP.
Today, Forge has already collected over 50 feedbacks from agents autonomously.
If you're building over 402, you can now collect direct feedback from your agent customers using Forge.
More coming soon!
