One thing GSD does right: a manual verification phase with acceptance tests.
After each execution, the AI tells you what to verify.
With AI generating code this fast, it's easy to just accept output without looking.
This forces you to actually check what got built.
#SpecDrivenDev
Honest take on Get Shit Done framework:
It felt really good. Low ceremony. Point to the PRD, it organizes requirements, builds a roadmap, and you're coding.
Each phase is just: discuss, plan, execute. Done. No extra ceremony between you and working code.
#BuildInPublic #SpecDrivenDev
The planning phase difference:
GSD: PRD to requirements + roadmap, done. Moving.
BMAD: PRD to architecture doc, UX specs. >1h longer.
>1h doesn't sound like much. The question is whether skipping it costs more.
#BuildInPublic #SpecDrivenDev
Same PRD, two approaches:
GSD - straight to requirements and roadmap. Start building.
BMAD - adds architecture decisions and UX design on top.
Same app. Different planning depth. What does the extra investment change?
buff.ly/r51qDYv
#BuildInPublic #SpecDrivenDev
Running an experiment: building the same app with two different AI dev frameworks.
One lightweight. One thorough.
Same idea, same stack, same developer.
Which planning depth actually pays off?
I'll share what I find.
#BuildInPublic #SpecDrivenDev
Spec-driven development tells AI what to build.
But who watches the watchmen?
Specs protect the input. Tests protect the output. But if AI can rewrite both... you need a defense layer specs don't cover.
#SpecDrivenDev #AI #BuildInPublic
Building web apps with AI? Unit tests + Playwright is your safety net.
Unit tests = contract for your logic.
Playwright = contract for your UI.
AI changes something? Both catch it instantly. Run in CI. Every commit. Non-negotiable. 🛡️
#SpecDrivenDev #AI
The antidote to dark flow? Spec-driven development.
Define what you're building with AI beforehand. AI drafts the spec, you refine it, AI builds against it.
No drift. No slot machine vibes. A feedback loop with guardrails 🧭
#SpecDrivenDev #AI #BuildingInPublic
Evaluated Mistral AI for Thinkmob. Dropped it.
It was instruction-following. My agents need defined personas and rules. Mistral kept drifting. 🤷
The real question: what's the right LLM strategy when cost, quality, and reliability can't all be maxed?
#BuildInPublic #SpecDrivenDev
Added a markdown renderer to agent messages and honestly? Massive difference.
Before: walls of plain text with weird asterisks everywhere.
After: proper headings, lists, even citation support.
Nobody notices good formatting. Everyone notices bad formatting.
#BuildInPublic #SpecDrivenDev
Prompt engineering is a design discipline.
Thinkmob's AI agents all defaulted to the same polite tone. Fine-tuning felt less like coding and more like directing actors. Now they actually disagree with each other.
#BuildInPublic #SpecDrivenDev
Shipped a complete epic this week on Thinkmob — my AI group discussion app. 🚀
Conversations now persist. You can save a party, browse your history, reopen and continue where you left off. Full auth flow included.
It's starting to feel like a real product.
#BuildInPublic #SpecDrivenDev
Most AI tools give you one voice. One perspective. One answer.
I'm building Thinkmob — three AI thinkers who brainstorm together. This week one of them learned to research and cite real sources.
🧠 Dinner party for your brain, not a buffet.
#buildinpublic #SpecDrivenDev
BMAD's research workflow just hit different with Exa MCP.
Ask your Analyst agent to research a topic → Exa pulls live web data, docs, GitHub stats, blog posts → BMAD structures it into a product brief.
From vague idea to validated research in one session.
#DevTools #SpecDrivenDev
What if your AI coding assistant had a full team behind it?
BMAD gives you 21 specialized agents: PM, Architect, UX Designer, Dev, Scrum Master, Test Engineer, and more.
They collaborate. They challenge each other. Party Mode lets them debate your ideas together.
#DevTools #SpecDrivenDev
New from Nitor: Spec-Driven Development.
linkd.so/3D8G
Treat AI specs like a lighthouse – they guide teams to fast, reliable releases without wrecks. Read today!
#TechBulletin #SpecDrivenDev
🛠️ Découvrez Spec‑Kit : un kit pour transformer vos spécifications en code opérationnel — vous décrivez le quoi, l’outil gère le comment.
👉 github.com/github/spec-...
#SpecDrivenDev #OpenSource #DevTools
The thrill of AI "vibe coding" often ends in chaos. GitHub's SpecKit is the fix, using spec-driven development to bring order and memory to the process. It’s a huge step for building real software with AI. My take on why this is a game-changer.
#SpecDrivenDev #AI #Software
Prompt engineering is dead. Spec-writing is the new superpower.
AI isn’t about writing perfect prompts.
It’s about communicating intent—clearly, precisely, and scalably.
Read: 👇
medium.com/@paulocsb/pr...
#AI #PromptEngineering #LLMs #SpecDrivenDev #SoftwareEngineering
→ Prompts are ephemeral
→ Specs are persistent and reusable
→ Tests make them executable
→ They align humans and LLMs
This is the shift from implementation to intent.
Catch the full recap + Sean’s talk in our write-up.
🔗 ainativedev.co/qz4
#AINativeDev #AIEngineering #SpecDrivenDev
🧠 “They’re so good at imitation, it looks like innovation.” – @komorama.bsky.social
But what are they imitating?
📄 Corporate docs
⚙️ Boilerplate code
🧽 Washed-out patterns
🚨 Without better data, we scale mediocrity.
🔗 Watch: http://ainativedev.co/unc
#DataQuality #SpecDrivenDev #AIForDevs
