The barrier to launching a product keeps getting lower.
The barrier to being seen keeps getting higher.
Knowing your customer is what makes the visibility count.
19
Shipping the AI feature was the easy part.
Getting people to use it every week was the real job.
What moved usage wasn't a better model or more features. It was putting AI where customers already work, inside their existing workflows.
28
Replit Agent tip: put the acceptance test in the prompt.
"Done when a new user can sign up, create a project and see it on the dashboard" beats "build signup."
Fewer rounds of fixes. Every time.
1
19
ChatGPT now lets businesses claim a profile and see how often they get mentioned.
SEO had Search Console. This feels like the start of that for AI search.
openai.com/index/introducing…
1
22
Most AI features don't fail on the model.
They fail on distribution.
If customers have to go looking for it, they won't.
A smart aspect that people might not realize is @Replit Agent will typically search through old tasks queue before fully starting something new, even if you prompt what feels like a new idea/ask. This is good because if there is an old task in the queue, for example I'm working on a project with 400+ task history, and you forgot something you never implemented, Agent will recommend you use the previous task, or merge into the new, to save on a) time b) tokens (don't write a new plan if you don't need to!)
5
167
Replying to @Kaygeeartworks
Haha yeah it’s a good reminder for us all - and in the future I might need to do some automating to keep up!
2
25
Updating my Replit Prompt SKILL. With all of the recent changes Replit team has been shipping I realized its getting outdated!
Replying to @geronco
I use multiple, not only one. So this workflow can work across ChatGPT, Claude, etc
1
1
19
Been experimenting with an interesting vibe code workflow. This has helped keep historical perspective and 'team' of agents working across a project to stay on same page, while I am still in loop.
1. Design a feature
2. Design review across agents
3. Document result, feasibility etc. into Linear issue for historical record/tracking
4. Implement/build and report back results/outcomes back into Linear issue(s) for the result and tracking
I've found this works well for agent to agent collaboration and human in the loop. All of this is possible through MCP for some basic automation. I typically never create/edit issues in Linear unless I really need to.
1
4
135
Mark Mathson retweeted
conversions aren't happening. did you fix your funnel first?
here's 30 funnel types mapped to how you sell. find yours.
Cool to see the recent Google PageSpeed Insights update adding in 'Agentic Browsing' to see how well a site is optimized for that or not. Definite sign Agentic Browsing is worth optimizing for.
1
40
It’s fun seeing employees of a company you really admire logging in and using something that you built.
1
43






