If you enjoyed this thread:
Follow me Michael 👨💻🥑 for more on AI Engineering & Web Development!
Read the complete build log (and get the code): https://dev.to/michaelsolati/i-built-an-ai-powered-ttrpg-adventure-generator-because-generic-hallucinations-are-boring-362m
Follow me Michael 👨💻🥑 for more on AI Engineering & Web Development!
Read the complete build log (and get the code): https://dev.to/michaelsolati/i-built-an-ai-powered-ttrpg-adventure-generator-because-generic-hallucinations-are-boring-362m
December 3, 2025 at 6:01 PM
If you enjoyed this thread:
Follow me Michael 👨💻🥑 for more on AI Engineering & Web Development!
Read the complete build log (and get the code): https://dev.to/michaelsolati/i-built-an-ai-powered-ttrpg-adventure-generator-because-generic-hallucinations-are-boring-362m
Follow me Michael 👨💻🥑 for more on AI Engineering & Web Development!
Read the complete build log (and get the code): https://dev.to/michaelsolati/i-built-an-ai-powered-ttrpg-adventure-generator-because-generic-hallucinations-are-boring-362m
⚡ TL;DR:
Generic AI prompts = Generic results.
Use a "Research-then-Generate" workflow.
Enforce JSON schemas for structured output.
Stream agent "thoughts" via SSE to improve UX.
Visualize citations to ground the content.
Generic AI prompts = Generic results.
Use a "Research-then-Generate" workflow.
Enforce JSON schemas for structured output.
Stream agent "thoughts" via SSE to improve UX.
Visualize citations to ground the content.
December 3, 2025 at 6:01 PM
⚡ TL;DR:
Generic AI prompts = Generic results.
Use a "Research-then-Generate" workflow.
Enforce JSON schemas for structured output.
Stream agent "thoughts" via SSE to improve UX.
Visualize citations to ground the content.
Generic AI prompts = Generic results.
Use a "Research-then-Generate" workflow.
Enforce JSON schemas for structured output.
Stream agent "thoughts" via SSE to improve UX.
Visualize citations to ground the content.
The coolest part? Citation Mapping.
Because we track the research steps, we can link the output back to the source.
I used D3.js to visualize the "web of inspiration." You can see exactly which folklore blog post inspired your villain.
Because we track the research steps, we can link the output back to the source.
I used D3.js to visualize the "web of inspiration." You can see exactly which folklore blog post inspired your villain.
December 3, 2025 at 6:01 PM
The coolest part? Citation Mapping.
Because we track the research steps, we can link the output back to the source.
I used D3.js to visualize the "web of inspiration." You can see exactly which folklore blog post inspired your villain.
Because we track the research steps, we can link the output back to the source.
I used D3.js to visualize the "web of inspiration." You can see exactly which folklore blog post inspired your villain.
UX Tip: Kill the loading spinner. 💀
Research takes time. Waiting sux.
I used Server-Sent Events (SSE) to stream the agent's actions.
The user sees: "Scanning wiki..." -> "Reading blog..." -> "Generating villain..."
It makes the wait feel like part of the experience.
Research takes time. Waiting sux.
I used Server-Sent Events (SSE) to stream the agent's actions.
The user sees: "Scanning wiki..." -> "Reading blog..." -> "Generating villain..."
It makes the wait feel like part of the experience.
December 3, 2025 at 6:01 PM
UX Tip: Kill the loading spinner. 💀
Research takes time. Waiting sux.
I used Server-Sent Events (SSE) to stream the agent's actions.
The user sees: "Scanning wiki..." -> "Reading blog..." -> "Generating villain..."
It makes the wait feel like part of the experience.
Research takes time. Waiting sux.
I used Server-Sent Events (SSE) to stream the agent's actions.
The user sees: "Scanning wiki..." -> "Reading blog..." -> "Generating villain..."
It makes the wait feel like part of the experience.
To stop the AI from generating a "wall of text," I enforce a strict JSON schema.
This acts as a contract. The AI must return structured objects for NPCs, Locations, and Plot Hooks.
No more rambling. Just usable data.
This acts as a contract. The AI must return structured objects for NPCs, Locations, and Plot Hooks.
No more rambling. Just usable data.
December 3, 2025 at 6:01 PM
To stop the AI from generating a "wall of text," I enforce a strict JSON schema.
This acts as a contract. The AI must return structured objects for NPCs, Locations, and Plot Hooks.
No more rambling. Just usable data.
This acts as a contract. The AI must return structured objects for NPCs, Locations, and Plot Hooks.
No more rambling. Just usable data.
The "Secret Sauce" is Exa (Neural Search).
Google searches for keywords. Exa searches for concepts.
If I want "realistic dragon biology," Exa skips the movie reviews and finds niche biology forums.
We create a research task and return a taskId instantly.
Google searches for keywords. Exa searches for concepts.
If I want "realistic dragon biology," Exa skips the movie reviews and finds niche biology forums.
We create a research task and return a taskId instantly.
December 3, 2025 at 6:01 PM
The "Secret Sauce" is Exa (Neural Search).
Google searches for keywords. Exa searches for concepts.
If I want "realistic dragon biology," Exa skips the movie reviews and finds niche biology forums.
We create a research task and return a taskId instantly.
Google searches for keywords. Exa searches for concepts.
If I want "realistic dragon biology," Exa skips the movie reviews and finds niche biology forums.
We create a research task and return a taskId instantly.
The Problem: Standard LLMs have no context. They guess based on probability.
The Solution: Don't ask it to write immediately. Ask it to Research.
My app, Adventure Weaver, dispatches an agent to crawl wikis, blogs, and forums for "vibes" before writing a single word of plot.
The Solution: Don't ask it to write immediately. Ask it to Research.
My app, Adventure Weaver, dispatches an agent to crawl wikis, blogs, and forums for "vibes" before writing a single word of plot.
December 3, 2025 at 6:01 PM
The Problem: Standard LLMs have no context. They guess based on probability.
The Solution: Don't ask it to write immediately. Ask it to Research.
My app, Adventure Weaver, dispatches an agent to crawl wikis, blogs, and forums for "vibes" before writing a single word of plot.
The Solution: Don't ask it to write immediately. Ask it to Research.
My app, Adventure Weaver, dispatches an agent to crawl wikis, blogs, and forums for "vibes" before writing a single word of plot.
Stop guessing the output of async code.
If you found this breakdown helpful:
1. Follow me Michael 👨💻🥑 for more deep dives into JS internals.
2. Check out the full visual guide here: https://dev.to/michaelsolati/visualizing-the-event-loop-a-guide-to-microtasks-macros-and-timers-2l22
If you found this breakdown helpful:
1. Follow me Michael 👨💻🥑 for more deep dives into JS internals.
2. Check out the full visual guide here: https://dev.to/michaelsolati/visualizing-the-event-loop-a-guide-to-microtasks-macros-and-timers-2l22
November 26, 2025 at 5:01 PM
Stop guessing the output of async code.
If you found this breakdown helpful:
1. Follow me Michael 👨💻🥑 for more deep dives into JS internals.
2. Check out the full visual guide here: https://dev.to/michaelsolati/visualizing-the-event-loop-a-guide-to-microtasks-macros-and-timers-2l22
If you found this breakdown helpful:
1. Follow me Michael 👨💻🥑 for more deep dives into JS internals.
2. Check out the full visual guide here: https://dev.to/michaelsolati/visualizing-the-event-loop-a-guide-to-microtasks-macros-and-timers-2l22
⚡ TL;DR Cheat Sheet
* Synchronous: Runs first.
* Microtasks (Promises): Run immediately after the stack clears. Exhaustive processing.
* Rendering: Happens after Microtasks, before Macrotasks.
* Macrotasks (Timers): Run only when everything else is quiet.
* Synchronous: Runs first.
* Microtasks (Promises): Run immediately after the stack clears. Exhaustive processing.
* Rendering: Happens after Microtasks, before Macrotasks.
* Macrotasks (Timers): Run only when everything else is quiet.
November 26, 2025 at 5:01 PM
⚡ TL;DR Cheat Sheet
* Synchronous: Runs first.
* Microtasks (Promises): Run immediately after the stack clears. Exhaustive processing.
* Rendering: Happens after Microtasks, before Macrotasks.
* Macrotasks (Timers): Run only when everything else is quiet.
* Synchronous: Runs first.
* Microtasks (Promises): Run immediately after the stack clears. Exhaustive processing.
* Rendering: Happens after Microtasks, before Macrotasks.
* Macrotasks (Timers): Run only when everything else is quiet.
Here is the execution flow:
1. Sync Code: 'Start' and 'End' run immediately on the Call Stack.
2. Stack Empties: The Event Loop wakes up.
3. Microtask Checkpoint: "Any VIPs?" Yes, the Promise. Run it NOW.
4. Macrotask: "Okay, now we can do the Timer."
1. Sync Code: 'Start' and 'End' run immediately on the Call Stack.
2. Stack Empties: The Event Loop wakes up.
3. Microtask Checkpoint: "Any VIPs?" Yes, the Promise. Run it NOW.
4. Macrotask: "Okay, now we can do the Timer."
November 26, 2025 at 5:01 PM
Here is the execution flow:
1. Sync Code: 'Start' and 'End' run immediately on the Call Stack.
2. Stack Empties: The Event Loop wakes up.
3. Microtask Checkpoint: "Any VIPs?" Yes, the Promise. Run it NOW.
4. Macrotask: "Okay, now we can do the Timer."
1. Sync Code: 'Start' and 'End' run immediately on the Call Stack.
2. Stack Empties: The Event Loop wakes up.
3. Microtask Checkpoint: "Any VIPs?" Yes, the Promise. Run it NOW.
4. Macrotask: "Okay, now we can do the Timer."
🧠 The Mental Model: The VIP Lane
JS has a single thread, but many queues.
1. Macrotask Queue: `setTimeout`, `setInterval`. (General)
2. Microtask Queue: `Promise.then`, `MutationObserver`. (VIP)
The Event Loop checks the VIP lane immediately after the current code finishes.
JS has a single thread, but many queues.
1. Macrotask Queue: `setTimeout`, `setInterval`. (General)
2. Microtask Queue: `Promise.then`, `MutationObserver`. (VIP)
The Event Loop checks the VIP lane immediately after the current code finishes.
November 26, 2025 at 5:01 PM
🧠 The Mental Model: The VIP Lane
JS has a single thread, but many queues.
1. Macrotask Queue: `setTimeout`, `setInterval`. (General)
2. Microtask Queue: `Promise.then`, `MutationObserver`. (VIP)
The Event Loop checks the VIP lane immediately after the current code finishes.
JS has a single thread, but many queues.
1. Macrotask Queue: `setTimeout`, `setInterval`. (General)
2. Microtask Queue: `Promise.then`, `MutationObserver`. (VIP)
The Event Loop checks the VIP lane immediately after the current code finishes.
✅ The Solution
The actual output is:
1. Start
2. End
3. Promise
4. Timeout
Wait, why does the Promise beat the Timeout, even though the Timeout was declared first with 0 delay?
It comes down to Microtasks vs. Macrotasks.
The actual output is:
1. Start
2. End
3. Promise
4. Timeout
Wait, why does the Promise beat the Timeout, even though the Timeout was declared first with 0 delay?
It comes down to Microtasks vs. Macrotasks.
November 26, 2025 at 5:01 PM
✅ The Solution
The actual output is:
1. Start
2. End
3. Promise
4. Timeout
Wait, why does the Promise beat the Timeout, even though the Timeout was declared first with 0 delay?
It comes down to Microtasks vs. Macrotasks.
The actual output is:
1. Start
2. End
3. Promise
4. Timeout
Wait, why does the Promise beat the Timeout, even though the Timeout was declared first with 0 delay?
It comes down to Microtasks vs. Macrotasks.
🛑 The Trap
Intuition says: "Code runs top-to-bottom. The timeout is 0ms, so it's instant. The Promise is async too. Maybe they race?"
If you guessed:
Start → End → Timeout → Promise ❌
You're wrong!
Intuition says: "Code runs top-to-bottom. The timeout is 0ms, so it's instant. The Promise is async too. Maybe they race?"
If you guessed:
Start → End → Timeout → Promise ❌
You're wrong!
November 26, 2025 at 5:01 PM
🛑 The Trap
Intuition says: "Code runs top-to-bottom. The timeout is 0ms, so it's instant. The Promise is async too. Maybe they race?"
If you guessed:
Start → End → Timeout → Promise ❌
You're wrong!
Intuition says: "Code runs top-to-bottom. The timeout is 0ms, so it's instant. The Promise is async too. Maybe they race?"
If you guessed:
Start → End → Timeout → Promise ❌
You're wrong!
Read the full, in-depth blog post here: https://dev.to/michaelsolati/leetcode-vs-vibe-coding-the-reality-of-interviewing-in-2025-2582
November 20, 2025 at 5:01 PM
Read the full, in-depth blog post here: https://dev.to/michaelsolati/leetcode-vs-vibe-coding-the-reality-of-interviewing-in-2025-2582
tl;dr: The 2025 Reality
* Enterprise: LeetCode is alive (Anti-Cheat Mode).
* Startups: Vibe Coding is here (Speed Mode).
* The Risk: "Bring Your Own AI" creates economic inequality.
* The Fix: Be bilingual. Audit AI output with strong fundamentals.
* Enterprise: LeetCode is alive (Anti-Cheat Mode).
* Startups: Vibe Coding is here (Speed Mode).
* The Risk: "Bring Your Own AI" creates economic inequality.
* The Fix: Be bilingual. Audit AI output with strong fundamentals.
November 20, 2025 at 5:01 PM
tl;dr: The 2025 Reality
* Enterprise: LeetCode is alive (Anti-Cheat Mode).
* Startups: Vibe Coding is here (Speed Mode).
* The Risk: "Bring Your Own AI" creates economic inequality.
* The Fix: Be bilingual. Audit AI output with strong fundamentals.
* Enterprise: LeetCode is alive (Anti-Cheat Mode).
* Startups: Vibe Coding is here (Speed Mode).
* The Risk: "Bring Your Own AI" creates economic inequality.
* The Fix: Be bilingual. Audit AI output with strong fundamentals.
A "Pay-to-Win" Barrier 💸
Startups expect you to interview with your own tools. Can you afford the $200 Claude Code tier? If the model hallucinates since you're on a free tier and you miss it, did you fail? We are asking candidates to pay for the privilege of getting hired.
Startups expect you to interview with your own tools. Can you afford the $200 Claude Code tier? If the model hallucinates since you're on a free tier and you miss it, did you fail? We are asking candidates to pay for the privilege of getting hired.
November 20, 2025 at 5:01 PM
A "Pay-to-Win" Barrier 💸
Startups expect you to interview with your own tools. Can you afford the $200 Claude Code tier? If the model hallucinates since you're on a free tier and you miss it, did you fail? We are asking candidates to pay for the privilege of getting hired.
Startups expect you to interview with your own tools. Can you afford the $200 Claude Code tier? If the model hallucinates since you're on a free tier and you miss it, did you fail? We are asking candidates to pay for the privilege of getting hired.
Startup Speedruns 🚀
Startups are the opposite. They hand you the keys to Copilot and say, "Go."
The constraint isn't memory; it's Speed. They don't want a coder; they want an "AI Editor." But this speed comes with a hidden price tag...
Startups are the opposite. They hand you the keys to Copilot and say, "Go."
The constraint isn't memory; it's Speed. They don't want a coder; they want an "AI Editor." But this speed comes with a hidden price tag...
November 20, 2025 at 5:01 PM
Startup Speedruns 🚀
Startups are the opposite. They hand you the keys to Copilot and say, "Go."
The constraint isn't memory; it's Speed. They don't want a coder; they want an "AI Editor." But this speed comes with a hidden price tag...
Startups are the opposite. They hand you the keys to Copilot and say, "Go."
The constraint isn't memory; it's Speed. They don't want a coder; they want an "AI Editor." But this speed comes with a hidden price tag...
Enterprise Paranoia 🏢
Big Tech is terrified of "AI Impostors." 81% of interviewers suspect cheating.
Their solution? "Proof of Work." They know AI can solve it. They want you to have the raw cognitive bandwidth to solve Invert Binary Tree w/out a robot whispering in your ear.
Big Tech is terrified of "AI Impostors." 81% of interviewers suspect cheating.
Their solution? "Proof of Work." They know AI can solve it. They want you to have the raw cognitive bandwidth to solve Invert Binary Tree w/out a robot whispering in your ear.
November 20, 2025 at 5:01 PM
Enterprise Paranoia 🏢
Big Tech is terrified of "AI Impostors." 81% of interviewers suspect cheating.
Their solution? "Proof of Work." They know AI can solve it. They want you to have the raw cognitive bandwidth to solve Invert Binary Tree w/out a robot whispering in your ear.
Big Tech is terrified of "AI Impostors." 81% of interviewers suspect cheating.
Their solution? "Proof of Work." They know AI can solve it. They want you to have the raw cognitive bandwidth to solve Invert Binary Tree w/out a robot whispering in your ear.
Follow me for more honest takes on the engineering industry.
And read my full breakdown here: https://dev.to/michaelsolati/im-getting-serious-deja-vu-but-this-time-its-different-17f4
And read my full breakdown here: https://dev.to/michaelsolati/im-getting-serious-deja-vu-but-this-time-its-different-17f4
November 18, 2025 at 5:01 PM
Follow me for more honest takes on the engineering industry.
And read my full breakdown here: https://dev.to/michaelsolati/im-getting-serious-deja-vu-but-this-time-its-different-17f4
And read my full breakdown here: https://dev.to/michaelsolati/im-getting-serious-deja-vu-but-this-time-its-different-17f4
TL;DR
- The market isn't just saturated; it's compressed.
- Layoffs are funding GPU purchases ($170B+ shift).
- The "How" (coding) is commoditized.
- The "Why" (Engineering & Verification) is the gold standard.
- The market isn't just saturated; it's compressed.
- Layoffs are funding GPU purchases ($170B+ shift).
- The "How" (coding) is commoditized.
- The "Why" (Engineering & Verification) is the gold standard.
November 18, 2025 at 5:01 PM
TL;DR
- The market isn't just saturated; it's compressed.
- Layoffs are funding GPU purchases ($170B+ shift).
- The "How" (coding) is commoditized.
- The "Why" (Engineering & Verification) is the gold standard.
- The market isn't just saturated; it's compressed.
- Layoffs are funding GPU purchases ($170B+ shift).
- The "How" (coding) is commoditized.
- The "Why" (Engineering & Verification) is the gold standard.
The "Prompt-Jockey" is a myth. The real winner is the AI-Assisted Engineer.
The new skill isn't writing code. It's: ✅ Debugging AI hallucinations. ✅ Architecting prompt systems. ✅ Owning the outcome when the black box fails.
The new skill isn't writing code. It's: ✅ Debugging AI hallucinations. ✅ Architecting prompt systems. ✅ Owning the outcome when the black box fails.
November 18, 2025 at 5:01 PM
The "Prompt-Jockey" is a myth. The real winner is the AI-Assisted Engineer.
The new skill isn't writing code. It's: ✅ Debugging AI hallucinations. ✅ Architecting prompt systems. ✅ Owning the outcome when the black box fails.
The new skill isn't writing code. It's: ✅ Debugging AI hallucinations. ✅ Architecting prompt systems. ✅ Owning the outcome when the black box fails.