#demandgen #fieldmarketing rockstar | LOVE @Padres @Chargers @LAClippers | #pizzaiolo #bbq and passionate about cooking and formerly eating out #dadlife
San Mateo, CA
Joined December 2013
- Tweets771
- Following598
- Followers174
- Likes2.8K
David Dolnick retweeted
If an agent can rebuild your app in a few weeks, what are your customers actually paying you for?
I don't think it's lawyers.
A clone gets graded on matching the original, bugs and all, so the best it can do is tie. I wrote up what I'd build instead, and why we made all of Agent-Native free to fork:
builder.io/blog/the-best-a-c…
David Dolnick retweeted
Thanks to GrokBot, I merged more PRs last week than ever before.
And also, I'm not gonna keep using it.
My 16 bots stayed up all weekend while I slept, burning $100 deciding they had nothing to tell me. On Monday, when I actually needed them, they were out cold.
GrokBot is still the closest thing we have to a working always-on staff. It's just not there yet, and the reasons are architectural.
Here's what happened, and what I think always-on agents actually need.
builder.io/blog/grokbot-revi…
David Dolnick retweeted
Introducing Agent-Native: an open-source framework for building agentic apps.
Agents love walls of text. But humans don't.
An agentic app let's you interact with agents through a visual interface. Engage with agents visually, via text, or both at once.
Now in beta.
David Dolnick retweeted
Please, please, please stop installing skills.
Don't get me wrong. I still read skills or even have my agent run them to learn from them. But the skills that actually make me better at my job (and my life) are the ones that I keep rewriting. Often by hand.
When I fix something my agent made, I save the before and after, have the agent put to words what my edit did that the skill didn't, put that in the skill, and rerun the same input until it works right.
I wrote up all the why and how below.
builder.io/blog/stop-install…
David Dolnick retweeted
How many times have you explained the same login flow to your coding agent?
We kept doing that with every bug, so we turned the whole routine into skills. Now an agent picks up a bug report, reproduces it, fixes it, and hands us a tested PR to review.
Here's how to set it up yourself, starting with one bug.
builder.io/blog/build-an-age…
David Dolnick retweeted
An email agent spends more time deciding than writing.
So in Agent-Native Mail, those calls can go to Jev, a decision model. Here it checks every email for this week's invoices, and the agent only has to write the summary for a client.
David Dolnick retweeted
The least productive thing I can imagine doing is watching an agent work.
But I still do it, because I'm never really sure if the agent understood what I wanted it to do. So I end up reading the tool calls and watching files change.
I want to agree on what it's gonna build, leave it alone, and review what comes back. But an all-text plan that's several pages long just feels like homework, and it's easier to let the agent run, even if it wastes tokens, just so I can see the result.
What I need is a better way to verify the plan and review the result, just at a glance. Something where I can see the layout or the API flow and point to the part that's wrong.
Here's what I've been doing instead lately.
builder.io/blog/stop-watchin…
David Dolnick retweeted
I think there’s a slightly underappreciated reason coding agents work so well.
It’s not just that LLMs are getting better at code.
Software engineering happens to expose an unusually agent-friendly environment:
repo → context
terminal/tools → actions
git → state + reversibility
tests/CI → feedback
PRs → human verification
Put together, this creates a tight observe → act → verify → iterate loop.
In other words, we accidentally spent decades building a pretty good agent harness around software development.
Most SaaS products don’t have this yet. The model may be equally capable, but the surrounding environment gives it much less leverage.
Wrote up the idea + what I think SaaS can learn from coding agents:
builder.io/blog/the-real-rea…
David Dolnick retweeted
I used to work at Grafana.
The dashboard-only era is ending. That's why we built Agent Native Analytics.
A chatbot that generates a plausible chart and forgets it when the tab closes isn’t AI analytics. It’s a demo.
The future is durable work shared by agents and humans.
David Dolnick retweeted
Loom records the crime scene.
It doesn’t collect the fingerprints.
Agent-Native Clips records the bug AND captures console errors, failed requests, and status codes from the same session.
Free. Open source. Built for humans and coding agents.
David Dolnick retweeted
Nobody really gets what they’re giving you when it comes to AI slop code.
You know how it goes.
A teammate shows you an internal tool they built with AI. It works. It looks nearly finished. They just need you to “hook up the integrations.”
But you see auth, consent, production data, CRM writes, accessibility, analytics, error states, tests, deployment, monitoring, and someone who has to own the thing after launch.
The prototype took an afternoon. Making it something the company can depend on could take weeks.
So you rebuild it properly.
Then another team asks for almost the same tool, with different content and one new integration.
That’s how engineering ends up owning six versions of an internal tool nobody meant to build six times.
I wrote about why both obvious ways of handling this fail, and how to give teams more agency without turning developers into the permanent cleanup crew.
builder.io/blog/stop-rebuild…
David Dolnick retweeted
If AI makes every marketer, PM, and designer become a developer, then software is failing.
AI should make people better at the jobs they chose, not just give everyone a different one.
Some more thoughts in the article below on how we can do a better job.
builder.io/blog/what-agent-n…
David Dolnick retweeted
call me agent-pilled, but after I started building apps and agents this way, there is no turning back
David Dolnick retweeted
Your engineers now have real AI agents.
Everyone else just got a chat box.
Treat agents as users of your software, not features inside it.
Build a capability once, and your whole team and their agents can use it.
builder.io/blog/why-every-ag…
David Dolnick retweeted
Announcing the Builder Review Agent: in-browser testing of every PR
Stop shipping broken code. Let agents verify every change actually works.
• Clicks, types, and navigates
• Covers critical flows, edge cases, regressions
• Hands you findings, repros, & one-click fixes
As if I couldn't love you more @Padres! Waking up tied for first place, latest since 2010, and then I get this email. LFGSD!!!
If you are considering buying @Sonos , I 1000000000000% recommend you do not. The app had major problems last year and it STILL DOES NOT WORK. Insane. It was once such a great product. Now it's frustrating that it's a worthless piece of junk.
David Dolnick retweeted
Masterclass: We then dived into Upskilling Africa: How @Andela & @CloudNativeFdn are Creating Global Tech Opportunities. Attendees learned practical strategies to equip young tech talent with the skills needed to compete on the global stage.
#SafaricomDecode
