meet OpenRouter for Sales and Growth team
no more 50+ subscriptions
working with Claude, ChatGPT or any agent
Jell will find your customers and engage with them
Today we're launching RouterGrowth, OpenRouter for sales
Your agent can write code. It still can't find you a customer
The data it needs is spread across 50 tools, 50 logins and 50 subscriptions
We put it behind one key/MCP: intent signals, contacts, email, LinkedIn, WhatsApp and more
Pay per call - Just Jell it
We analyzed how @claudeai’s Opus 5.5 writes compared with Opus 5 across high-reasoning Text Arena outputs.
10 of 12 writing measures moved in a better direction.
Opus 5.5 should be easier to read:
- Long content words fall from 41.7% to 38.6%, the lowest share of any Claude model we analyzed.
- Sentences are 17% shorter on average, dropping from 12.14 to 10.03 words.
The tradeoff is length. Answers get 6% wordier, rising from 453 to 481 words on average, making Opus 5.5 give the longest answers across the Opus family.
It also sounds less recognizably AI on two familiar tells:
- 95% fewer em dashes
- 73% fewer semicolons
But a new giveaway may be emerging. Hedges and caveats such as “perhaps” and “arguably” rise 97%, from 0.39 to 0.77 per 1,000 words, the highest rate of any Claude model we analyzed.
What do you think: does Opus 5.5 read more naturally?
omg i had to test it myself and am stunned how good this is
this product launch video was fully created by opus 5.5 with just one prompt
i just told opus to go pick a SaaS and create a professional product launch video
prompt below:
@aliscodes love to see it - next step: have Jell write each of the 20 a first line from their own site, then send from its own inbox. curious how many reply 👀
ok i tested this.
gave my agent one prompt, find 20 saas founders who might need a saas audit, with their linkedins and emails. had all 20 back in about three minutes, with the emails run through waterfall enrichment so they're checked across several providers, not just one.
it even ranked them by fit and told me which few weren't worth pitching.
that whole lookup cost me 72 cents.
@RouterGrowth
This is what makes RouterGrowth interesting.
Your AI agent can find prospects, discover creators, monitor competitors, track what ChatGPT says about your brand, and even research competitor ads.
Instead of juggling 50 GTM tools, you give your agent one key and let it run the workflow.
That’s a pretty big shift.
Claude Code can build me an entire app before breakfast but ask it to find one actual customer and it just stares at you like an idiot.
This new mcp fixes that bit it seems inside where you already work (in my case, claude).
Finds leads, finds contact info, then sends the messages as well, email, linkedin, and whatsapp...
Bro, this is like openrouter but for GTM.
I used to use like 12 tools ranging from apollo to hunter and more and this just gave me one api for my agent to fetch everything from getting leads to verification and to even outreaching.
It was the worst thing to connect like 50 tools and now with one api I can fetch everything single thing from instagram to outreaching on linkedin.
This is nuts
I pulled all of our competitors ads on Meta, right from Claude code.
This can help you find absolute winners that you can use for your own ads
Go check it out ⬇️
Today we're launching RouterGrowth, OpenRouter for sales
Your agent can write code. It still can't find you a customer
The data it needs is spread across 50 tools, 50 logins and 50 subscriptions
We put it behind one key/MCP: intent signals, contacts, email, LinkedIn, WhatsApp and more
Pay per call - Just Jell it
Today we're launching RouterGrowth, OpenRouter for sales
Your agent can write code. It still can't find you a customer
The data it needs is spread across 50 tools, 50 logins and 50 subscriptions
We put it behind one key/MCP: intent signals, contacts, email, LinkedIn, WhatsApp and more
Pay per call - Just Jell it
the right way to use model capabilities is not to ship 10x more features to prod
it's to spend more time understanding your users, trying experiments, building prototypes, learning about things you don't understand so that you can ship things that actually work