Director of Engineering & Co-founder @madebymonogram — agentic AI systems, composable apps & elegant engineering.
Atlanta, GA
Joined May 2011
- Tweets586
- Following615
- Followers177
- Likes1K
Claudio retweeted
What do answer engines say about you?
AEO Audit finds out. Give it a URL and it asks ChatGPT, Claude, Gemini, and Perplexity the questions your customers are asking, then scores how you show up and tells you what to fix first.
Ours found we were blocking some of the bots trying to cite us. Fixed that.
Claudio retweeted
One sentence in, a finished deck out. Deck Studio writes every slide in your brand's colors, typeface and logo, then lets you edit by typing or just asking.
Grab a spot on the waitlist at tools.monogram.io
We’ve built a bunch of tools at @madebymonogram because we needed them ourselves. Over time, we started using them with our clients too.
Now we’re opening Monogram Tools up for anyone to use.
Here’s a little teaser 👀
mngr.am/
New in @SubcoreAI:
Someone on your team reads a real customer conversation and sees the agent do something odd on turn 3.
Where does that go? Usually Slack, with a link to the whole conversation. A week later nobody can find turn 3.
We let them leave the note on turn 3 itself.
Claudio retweeted
"Which prompt is production actually running?"
Most teams answer that with someone pasting a version into a doc. An assertion, and it goes stale quietly.
Our console derives it. The deployment announces its compiled prompts, live traffic reports its own hash, and we compare.
Spent Monday at Vercel's Agent Certification Bootcamp in NYC before Vercel Ship. Highlight: Eve, their open source agent framework. An agent is just a directory of files, tools in TypeScript, instructions in Markdown, durable execution and evals built in.
Claudio retweeted
The full Certified Solution Partner cohort:
• AKQA - @AKQA
• Americaneagle.com - @_Americaneagle
• Artisan Studios
• Blazity - @blazity
• Code and Theory - @codeandtheory
• Grid Dynamics - @GridDynamics
• Horizontal - @HztlDigital
• Jakala
• Monogram - @madebymonogram
• UNRVLD - @unrvldagency
• Verndale - @VerndaleTweets
Congrats to these solutions firms!
Quick gut check I've been using while building AI systems:
- Are we storing everything or only what matters?
- Can the system update what it "knows" about a user over time?
- Can that knowledge be inspected and corrected?
- Do our evals catch edge cases and regressions?
The hard part is not generating responses.
It's building systems that learn in a reliable way.
The hardest part of building AI agents isn't the AI.
It's making them predictable.
Users expect:
- consistent answers
- reliable actions
- no weird edge cases
Getting there means:
- strict tool schemas
- defensive prompts
- evals for edge cases and regressions
- retries and validation
- logs for everything
AI feels magical in demos.
Production is engineering.
Claudio retweeted
🚨BREAKING: Microsoft just solved the "Agent Loop" problem.
Agent Lightning is an open-source framework that lets agents learn from their own mistakes using Reinforcement Learning.
Your agent fails a task → Agent Lightning analyzes why → Updates the prompt automatically → Next run succeeds.
100% Opensource.
Claudio retweeted
We now support Bun on Vercel.
Bun is an open runtime pushing the frontier on DX and performance.
Start building and see our latest benchmarks.
vercel.fyi/buntime
Legends, old friends, and new faces—Interrupt 2025 delivered. A full day of honest conversations on building AI agents, what’s working, what’s not, and how to get to prod. Shoutout to the @langchain crew for a great event.
