Devin Dickerson
149 posts

Devin Dickerson
@Dev_TheAnalyst
Principal Analyst at Forrester Research | Adjunct Lecturer At Tulane University #cloudnative #Serverless #Edge #Developers #AI My thoughts are my own.
New Orleans, LA Katılım Nisan 2022
521 Takip Edilen214 Takipçiler

To all the Firebase developers exploring new AI workflows: welcome! 🤝
Import your Firebase Studio projects into Antigravity to pick up where you left off. You'll have access to Gemini models, Agent Skills, and a built-in Browser Agent.
Antigravity supports core Firebase services including Auth, Firestore, and Hosting via the Firebase MCP server. It also adds new integrations like Google Search and Nano Banana, with the flexibility to run locally or over SSH to a VM.
Firebase@Firebase
Firebase now integrates with @GoogleAIStudio, accelerating your path from prompt to production 💫 With a single prompt, you can build full-stack apps connected to Firestore for secure storage and Firebase Authentication for user identity.
English

@GoogleAIStudio This is an exciting one. I really liked the workflow of starting with AI Studio, getting as far as I could, and then transitioning into the ide with CLI or antigrav
English

@DarthBlep @stitchbygoogle Ha! I ask questions for a living I guess
English

@Dev_TheAnalyst @stitchbygoogle Commenting because Devin be asking the right questions
English

@simpsoka @stitchbygoogle Exactly what I was looking for thank you.
English

@Dev_TheAnalyst @stitchbygoogle Try the redesign agent. Docs here: stitch.corp.google.com/docs/learn/des…
You can give it a live URL, or upload a screenshot/image.
English

@MongoDB @forrester It was a pleasure having this conversation with the team. Thanks for having me!
English
Devin Dickerson retweetledi

Watch @forrester’s Devin Dickerson and MongoDB’s Pete Johnson and Shilpa Kolhar talk about why your data architecture is the real foundation for AI that lasts.
In episode 1 of Building the AI Era, you'll hear what actually holds teams back, like:
• Why “lift and shift” often carries technical debt forward
• Why flexible data models are critical in the AI era
• Why leading teams are thinking data-first, not feature-first
Watch Episode 1 now! 👉 mongodb.social/6012B6pudA
English

mongodb.social/6044B6puni
@MongoDB This was one of the most interesting conversations I've had about the AI era and the first episode just dropped! If you are interested in the state of AI for modernization and the hard to solve brownfield use cases watch the first episode!
English

Perk up when the DORA team does research into software delivery.
The surveyed Google engineers to understand how AI tools impacted their work, and where they struggled.
The advice is very actionable.
dora.dev/insights/balan…

English

@LSUbaseball If you are an MLB fan get to know the name Jake Brown. 5 tool player
English

"Most of you reading this are likely past the first few [levels of agentic engineering], and you should be eager to reach the next one because each subsequent level is a huge leap in output, and every improvement in model capability amplifies those gains further." bassimeledath.com/blog/levels-of… < which level of agentic engineering are you working at? Great post here what's needed to progress through each stage.

English

I’ve spent years warning teams against “the big rewrite.”
After talking with Dane Knecht (CTO) and Steve Faulkner (Engineering Director) at Cloudflare about an entirely agentic rewrite of Next.js, I’m rethinking what technical debt even means in the agentic development era.
New blog 👇
forrester.com/blogs/when-the…
English
Devin Dickerson retweetledi

It's obvious that the big analyst firms need to make a transition. Faster analysis, more original data, better sense of what's happening on the ground.
@forrester is now bringing their AI-based analysis service into existing enterprise tools.
forrester.com/blogs/human-in…
English

@OfficialLoganK The Vibe Coding 'Hero' feature most needed. Ha
English

Tldr ( x friendly thoughts ). Context drives agent experience. Some of the richest context for a real app with real customers lies in prod data and real user activity. Figuring out how to orchestrate your context architecture for both SDLC agents and your prod agents is absolutely critical. Full report tells enterprises how to get there.
English

@Dev_TheAnalyst @rseroter if you have any thoughts, i'd love to hear them! or a link to the report??
i am continually surprised at how little attention the problem of three pillars / context stripping gets, even in the era of AI and LLMs.
English

"It is not just the width of your data that matters when it comes to getting great results from AI ... But capturing and preserving relationships is at the heart of all of it." charitydotwtf.substack.com/p/your-data-is… < @mipsytipsy with a great post why AI agents need better observability data

English

@mipsytipsy @rseroter forrester.com/blogs/dont-fea… here is one of the blogs from Carlos. Our full report is linked in the blog.
English

@rseroter I still have hit or miss results with my own Agent Skills but I love seeing context opinionation becoming part of the product stack.
English

Hey, look at that.
The popular Agent Development Kit just snuck some agent skills into their docs repo.
These skills will help you create, evaluate, deploy, and observe ADK agents better.
github.com/google/adk-doc…

English




