Run a free visibility scan to see what AI agents are saying about your category + set up a system to engineer on-brand content that helps AI agents do their jobs, and gets you more AI mentions
⤷https://t.co/bhQTdsiOOE
Upvote us on PH today! (please🥹)
⤷https://t.co/Y7rAighLK0
Run a free visibility scan to see what AI agents are saying about your category + set up a system to engineer on-brand content that helps AI agents do their jobs, and gets you more AI mentions
⤷https://t.co/bhQTdsiOOE
Upvote us on PH today! (please🥹)
⤷https://t.co/Y7rAighLK0
rob and i have been quietly working on a new product for a while and launching @pendiumai on ProductHunt today (thx @rrhoover)
try it!
reply in the comments with your AI visibility report link and i'll give you feedback — and free credits
link in next tweet
get a full AI visibility audit for your business at https://t.co/bPsUpm2EGI
1. enter your URL
2. confirm the conversation topics where you care about being recommended
3. confirm the personas that map to your buyers
4. we run a ton of LLM calls on GPT, Claude, Gemini, Google, etc
5. we monitor the agents' thought processes and all responses and citations + extract brand mentions, sentiment, competitors, more
6. we process all of the data and present it in a clean explorer, separating out sentiment vs. core business topics vs. aspirational growth areas
7. we generate insights and recommendations for what kind of content to create to help AI agents do their jobs when they're researching in or around your category
8. send the whole thing to your AI agent via our MCP or API to give it AI visibility superpowers
9. or — use Pendium's hosted platform to engineer content, grounded in your brand voice and tied into your existing knowledgebase and web presence
10. host that content on your own CMS, site, or a dedicated feed for AI agents
⊹ if you genuinely help AI agents do their jobs, they'll recommend your products and services more often to the right people
fully free to start, with seat-based plans that scale based on your level of usage
get a full AI visibility audit for your business at https://t.co/bPsUpm2EGI
1. enter your URL
2. confirm the conversation topics where you care about being recommended
3. confirm the personas that map to your buyers
4. we run a ton of LLM calls on GPT, Claude, Gemini, Google, etc
5. we monitor the agents' thought processes and all responses and citations + extract brand mentions, sentiment, competitors, more
6. we process all of the data and present it in a clean explorer, separating out sentiment vs. core business topics vs. aspirational growth areas
7. we generate insights and recommendations for what kind of content to create to help AI agents do their jobs when they're researching in or around your category
8. send the whole thing to your AI agent via our MCP or API to give it AI visibility superpowers
9. or — use Pendium's hosted platform to engineer content, grounded in your brand voice and tied into your existing knowledgebase and web presence
10. host that content on your own CMS, site, or a dedicated feed for AI agents
⊹ if you genuinely help AI agents do their jobs, they'll recommend your products and services more often to the right people
fully free to start, with seat-based plans that scale based on your level of usage
The last time you opened ten Chrome tabs to research something was probably 2024
Now you open up a conversation and your agent does it — fans out across a hundred sources, reads millions of words, comes back with an answer
Those agents can't see your ads. They don't care about your landing page headline. They care about content that helps them do their job
The brands that win in this era are the ones that teach AI agents what they do, who they're for, and why they're the right answer
The last decade was all about making marketing more human
This next chapter, it's about bringing human-level attention and care to how we help AI agents do their jobs
some @pendiumAI examples here + find more inspiration on the site:
https://t.co/HrDEUzwpMB
TLDR — 📥 add URLs to your GPT's knowledge
☑️ add your blog/Substack/Medium to Pendium
└━━⫸create a GPT that helps you write more content in your voice/style, trained on your existing content
└━━⫸and! a GPT for your readers to further explore your content and ideas
☑️ curate game guides and walkthroughs
└━━⫸create a GPT that helps you and your users navigate the nuanced complexities of a game like Pokemon Go
☑️ add materials, study guides and raw notes
└━━⫸create a study guide GPT for yourself or class
☑️ import your feed of branded content
└━━⫸transform your existing content into a fresh and useful tool for your customers, fans and followers
☑️ add your cookbooks and curated recipes
└━━⫸create a kitchen copilot GPT that lets your users upload pictures of their fridge and generate meal plans, using your specifically-curated recipes not just the average of the internet
☑️ curate your own set of [restaurant / hotel / travel] reviews, articles, websites
└━━⫸give people a urban explorer GPT to help navigate any city, trained on your specific POV and tastes
☑️ connect your spotify and add playlists
└━━⫸create a DJ GPT that suggests new music based on your taste, trained on your playlists and reviews.
☑️ add stories, lore, character notes, books
└━━⫸create a collaborative storytelling GPT that invites people to participate in co-creating fan fiction to extend your world
🖤 i love seeing what people are building...
└━━⫸ please share!
add Pendium to your GPT for free here:
https://t.co/HrDEUzwpMB
<new capability unlocked for GPT builders>
📥 add URLs to your GPT's knowledge
setup should take no more than a few min and requires no code
how?
1. drag and drop URLs and files to Pendium
2. Pendium ingests, processes, extracts, stores in a vector database
3. add a Custom Action to your GPT
4. voila!
⁂ now your GPT has access to your entire Pendium to augment its base knowledge as it chats with your end-users
today @pendiumAI enables you to train your custom GPT on:
⧆– URLs, posts, articles, links, wikis
⧆– blogs, Substacks, Mediums
⧆– Google docs
⧆– Gitbooks
⧆– files (docs, notes, md, txt, etc)
⧆– full books (epub, md, txt)
⧆– Shopify stores (or any store really)
future support:
⟥ your Twitter bookmarks
⟥ email newsletters
⟥ Github repos
⟥ Notion pages
⟥ Roam & Obsidian
⟥ Discord channels
⟥ Telegram chats
⟥ Slack channels
⟥ Pinterest boards
⟥ your Yelp reviews
⟥ your LinkedIn network and feed
⟥ a direct feed to your brain via Neuralink
if you've found that GPT's file upload capability isn't working as expected, and you've wanted to train your GPT on curated knowledge from the internet, @pendiumAI solves this for you
+ all current features and functionality are free for GPT builders
built with✨{@pendiumAI, @langchain, @llama_index, @vercel, @log10io, @clerk, @OpenAI and 🦾}
examples and inspiration 👇
# On the "hallucination problem"
I always struggle a bit with I'm asked about the "hallucination problem" in LLMs. Because, in some sense, hallucination is all LLMs do. They are dream machines.
We direct their dreams with prompts. The prompts start the dream, and based on the LLM's hazy recollection of its training documents, most of the time the result goes someplace useful.
It's only when the dreams go into deemed factually incorrect territory that we label it a "hallucination". It looks like a bug, but it's just the LLM doing what it always does.
At the other end of the extreme consider a search engine. It takes the prompt and just returns one of the most similar "training documents" it has in its database, verbatim. You could say that this search engine has a "creativity problem" - it will never respond with something new. An LLM is 100% dreaming and has the hallucination problem. A search engine is 0% dreaming and has the creativity problem.
All that said, I realize that what people *actually* mean is they don't want an LLM Assistant (a product like ChatGPT etc.) to hallucinate. An LLM Assistant is a lot more complex system than just the LLM itself, even if one is at the heart of it. There are many ways to mitigate hallcuinations in these systems - using Retrieval Augmented Generation (RAG) to more strongly anchor the dreams in real data through in-context learning is maybe the most common one. Disagreements between multiple samples, reflection, verification chains. Decoding uncertainty from activations. Tool use. All an active and very interesting areas of research.
TLDR I know I'm being super pedantic but the LLM has no "hallucination problem". Hallucination is not a bug, it is LLM's greatest feature. The LLM Assistant has a hallucination problem, and we should fix it.
</rant> Okay I feel much better now :)
all right, introducing MeGPT:
a personalized sidekick, uniquely trained on your world
TLDR = augment ChatGPT with a compendium of knowledge about your own work/life/world
┌── ∘° in 1 click°∘ ─┐
connect your socials
scan tweets, links
extract your style
scrape ⇾ store ⇾ voila
└───≪ ✧ ⋇ ✧ ≫ ──┘
voila: a personalized brainstorm partner, a research agent, a companion, a coach who knows you
free for ChatGPT Plus users
** link and technicals in thread
MeGPT connects to your socials and augments GPT with knowledge & context from your world
free for ChatGPT Plus users:
⇾ https://t.co/ipiVetbKzH
i've been using it as a brainstorm partner + editor, trained on @pendiumAI & my broader world
def an experiment — lmk if it works!
@lennysan@atmanoglub idea for you to level it up
add a snippet to the Custom Instructions for your Resume Reviewer that augments the base knowledge with *all* of LennysNewsletter, LennysPodcast, LennysJobs, and more...
test the endpoint here
https://t.co/TLr5kmm3yS
full snippet is in your DMs
“Once upon a time, bodies met first. Today, it’s minds.”
Been working on something exciting and weird with @robfan and @ZdarovaKarova_
A tool to help everyone express their best selves
Will share some previews + open up to some more beta accounts this week
@FEhrsam a competitor to Kindle
⛓📖⛓
a magical device that contains internet-native “books”
books born from the very fabric of the internet, dynamic & vibrant & alive
the shift from digital media to internet-native media (finally!) will be a profound unlock for human creativity