Daniel Strongin

Helping businesses learn and integrate AI

[Daniel Strongin @Strongin_]

@steipete Do you teach any of your agentic engineering anywhere?

[Daniel Strongin @Strongin_]

What are your top researching tools that you have your agents use?

I'm currently using:
- Perplexity
- Exa
- Tavily
- Google Deep Research (through the api)
- Good old fashioned web search in codex and claude code

[Daniel Strongin @Strongin_]

Kit finally released an MCP. I've been using their API, and it's working pretty well so not much changed in my workflow.

However, it seems to struggle with editing the body of email sequences.

Anyone else been making good use of Kits and MPC?

[Daniel Strongin @Strongin_]

@AlexFinn Yes sir

[Daniel Strongin @Strongin_]

@GaelBreton I had high hopes for the new anti-gravity. But yeah, it's blah.

[Daniel Strongin @Strongin_]

Anyone impressed with Google's latest releases? Especially Omni.

[Daniel Strongin @Strongin_]

Expo + React Native is why a non-coder can ship a real mobile app.

One project becomes an iPhone app, an Android app, and a website. An AI agent edits a file → your phone updates instantly. Package it into a real installable app when you're ready.

The prompt I used (paste into Claude Code or any coding agent in an empty folder):

"Set up an Expo + React Native app in this folder. Install everything, then start the dev server so I can scan the QR with Expo Go on my phone."

10 minutes later I was building on my phone.

[Daniel Strongin @Strongin_]

@karpathy Awesome! Can't wait to see what you learn with Anthropic trickle down to your educational material

[Daniel Strongin @Strongin_]

@trq212 Oh yeah, definitely have to do this. Yeah, there always are choices that are made for you that you don’t know about

[Daniel Strongin @Strongin_]

I’m getting more convinced the useful agent pattern is not “let it run everything.”

It’s:
1. agent writes the fix
2. tests prove the contract
3. repo log records the decision
4. external actions wait behind a human gate

Today: 28 tests, 3 issues closed, 6 automation pages shipped cleanly.

[Daniel Strongin @Strongin_]

@trq212 I use HTML for everything now. You opened up pandoras box lol

[Daniel Strongin @Strongin_]

@TheReviewRewind Thanks! 😊

[Daniel Strongin @Strongin_]

Using Claude Code to plan my honeymoon. France, June 4-23.

It's booked: 4 stays, 5 trains, 2 wine tours, a Michelin dinner, a Seine dinner cruise, Eiffel Tower top floor, Louvre, Musée d'Orsay, a food tour.

Budget in markdown, EUR auto-converts to USD. Every confirmation PDF lives in the repo.

[Daniel Strongin @Strongin_]

@TheReviewRewind @mattpocockuk It for sure helps a ton of actually implementing systems that work

[Daniel Strongin @Strongin_]

I’ve been using @mattpocockuk’s agent workflow ideas:

grill the design first, turn it into a PRD, split it into issues, then TDD each slice.

It turned duplicated automation into a shared runner that’s easier for AI agents to navigate, test, debug, and change.

[Daniel Strongin @Strongin_]

@mattpocockuk What about one skill orchestrating a bunch of small skills to complete a complex task

[Daniel Strongin @Strongin_]

Codex computer use is pretty freaking good.

It checked Telegram/Teams, found a song on Spotify, looked at email stats, and scanned messages/emails for anything needing attention. All from one concise prompt.

Starting to feel genuinely useful.

Using Computer Use to post this.

[Daniel Strongin @Strongin_]

Built a public system-bug-investigator skill for coding agents.

It keeps bug fixes from turning into symptom patches: identify the failure surface, trace related files/services, check blast radius, choose the safest first fix, then verify.

https://t.co/6eZXfb7eQd