Rawghu Writes

Lost in GPS, Found in Art 🎨
🏍️ Avenger ಅಲೆಮಾರಿ🚴
#AvengerAlemaari #NomadNavigator #StarvaGPSArt Enthusiast
#AnimeShredder #Naruto #DojoMode ⛩️

[Rawghu Writes @Raw_ghav]

For the King Kiccha!👑
25 KMS Cycling for 25th Dec Release.
Maxing out the tribute to @kicchaSudeep sir and @Max_themovie.

#MaxTheMovie storms into theaters on Dec 25!

#SudeepFan #MaxRelease #GPSArt #CycleArt #MaxTheMovie #KicchaSudeep #CyclingEnthusiast #MaxMovieOn25Dec

[Abhishek @HeyAbhishek]

This AI workflow is wild 🤯

I just used ChatGPT Image 2.0 and Seedance 2.0 to create emotional animated video in minutes

Easy step by step workflow below 👇

[Rawghu Writes @Raw_ghav]

@everestchris6 FABLE

[Chris @everestchris6]

Claude fable + Hermes finds restaurants before they open, builds their launch kit and mails the owner a postcard

the launch kit: the ad creatives, a cinematic reel and a NFC review card

here's how you can use this system to sell to restaurants:

- it watches every new restaurant license filing in the county
- it matches each filing to building permits at the same address
- it skips the chains and hotels, keeps the independents
- claude fable reads the filings and calls the cuisine and opening date
- seedance 2.0 makes their reel before they have a photo
- the postcard lands before their google listing even exists

the entire process is automated. even the NFC +postcards are ordered through an api

reply "FABLE" + RT and i'll send you a free guide so you can build this too (must be following so i can DM you)

[Rawghu Writes @Raw_ghav]

@FynCas EDIT

[Cas.Fyn @FynCas]

built a Claude skill that lets me copy any viral video ad — with my own product dropped in.

Show it one viral ad → it clones the whole style.

Backgrounds, typography, zooms, cut rhythm, pacing. Swaps in your product, your face, your voice.

8 scene changes in 9 seconds. Never opened a timeline.

One skill file. Raw clip + reference video in → finished ad out.

Comment "EDIT" and I'll DM it 👇

[Rawghu Writes @Raw_ghav]

@raph_guilhem Skill

[Rawghu Writes @Raw_ghav]

@FynCas Claude

[Cas.Fyn @FynCas]

Claude = 550 videos/day

Fully realistic UGC ads, cinematic lighting, natural human motion, clean pacing, powered by AI agents.

UGC cost: $1
Production time: minutes
Scale: instant

One AI engine that creates, tests, and scales short-form ads automatically, nonstop.

RT & Comment ''Claude'' and I’ll DM you the full workflow.

(Must be following)

[Aakash Gupta @aakashgupta]

She literally showed how she uses adversarial agents in Claude Code to win hackathons and ship features:

2:47 - How she won her hackathon
4:30 - The 5-layer Claude stack
7:17 - Which model to actually use
9:55 - Chat vs Desktop vs Chrome
14:43 - Cowork automations
26:18 - Skills that beat prompts
34:28 - The AI chief of staff build
59:24 - MCPs every PM needs
1:02:16 - Claude Design is here
1:08:53 - Adversarial agents, live
1:13:01 - The new AI builder role
1:15:57 - The 2026 AI PM interview
1:29:06 - Self-improving product loop

[Rawghu Writes @Raw_ghav]

@georgesttock EDIT

[Atlas @crptAtlas]

GITHUB JUST KILLED THE WORST PART OF VIBE CODING

they shipped a free tool called Spec Kit and it already crossed 120,000 stars

the fix is stupidly simple

instead of tossing vague prompts at an agent and praying it doesn't wreck your project

Spec Kit makes the AI write a full structured spec before it touches a single line of code

it works through the problem first

figures out what you want to build

asks about the gaps

lays out the project

then it starts coding

you get fewer insane bugs, cleaner output and results you can predict

the flow looks like this:

/constitution for your rules and standards
/specify for what you want to build
/clarify for the open questions before you start
/plan for architecture and stack
/tasks for the ordered work
/implement to run it

it plugs into Claude Code, Cursor, Copilot, Codex, Gemini CLI and 25+ other agents

120,000 stars, 10,000 forks, open source, shipped by GitHub itself

learning to drive agents like this is most of what separates people getting hired as AI engineers from everyone still fighting their prompts

[kaize @0x_kaize]

Loop engineering - the reading list

In 2026 agents stopped being about smarter prompts and started being about longer runs.

Everyone needs to stop writing stupid prompts and start learning Loop engineering.

The real question isn't "what do i type". It's "how does my agent keep going for 40 minutes without falling over".

1. Can it recover from a failed step?
2. Can it control spend?
3. Does it know when to stop?

All of it comes back to loop design:

[ READING LIST ]

1. Addy Osmani - Loop engineering:
https://t.co/kzIbYW8wLG

2. Firecrawl - Loop engineering:
https://t.co/8UhKcZvbw9

3. Oracle - What is the AI agent loop:
https://t.co/Jg5ic7dxJc

4. OpenAI - Harness engineering:
https://t.co/7i34jS1Qk9

5. Martin Fowler - Harness engineering for coding agent users: https://t.co/1QvsIHGbXa

6. From React to loop engineering - Agentic loops:
https://t.co/WERkgRXWsy

7. Mem0 - Loop engineering for ai agents, memory-first:
https://t.co/mJxzguwX7z

[ OPEN SOURCE WORTH READING ]

1. Codex CLI: https://t.co/TCbo5tNb3b
2. Openhands: https://t.co/KgPJOHgLK4
3. Pydanticai: https://t.co/6Dd1Hu9Etj
4. OpenAI Agents SDK: https://t.co/JobwcV75dH

[ WHAT TO STUDY ]

- How the loop runs?
- How the loop stops?
- How the loop verifies?
- How the loop recovers?
- How the loop is debugged?

[ THE POINT ]

- Prompt decides how the agent starts.
- Context decides what the agent sees.
- Loop decides how far the agent gets.

Scheme:
Think -> Act -> Observe -> Verify -> Evolve -> Repeat

[ START HERE ]

Before you touch anything above - read my Article first -It's the entry point.

[Rahul @sairahul1]

https://t.co/uRsQBBhTcH

[Rahul @sairahul1]

This is the best site on the internet to learn harness engineering.

Free. Completely.

Most AI engineers have never heard the term.

https://t.co/bwDbTTYsjM

Bookmark this site.

Then read this setup ↓

[Rawghu Writes @Raw_ghav]

@rom1trs Motion

[Alex Prompter @alex_prompter]

There are layers of working with AI. Prompt engineering. Context engineering. Harness engineering. Loop engineering.

Layer 1 is prompt engineering. What you type into the chat window. How you word the instruction, what you ask for, what you tell it to avoid. This is where everyone starts. It matters, but few people go further.

Layer 2 is context engineering. Everything the model sees before your prompt. System instructions, reference files, conversation history, examples of good output. A mediocre prompt with great context beats a great prompt with no context every time.

Layer 3 is harness engineering. The code around the model. Tool routing, verification steps, retry logic, structured outputs. This is what makes AI reliable instead of just impressive. When the model checks its own work before returning it to you, that's the harness.

Layer 4 is loop engineering. The system runs itself. You set a goal and a stop condition. The loop prompts the model, checks the output, adjusts, and repeats without you. This is where you stop being the bottleneck entirely.

Each layer wraps the one before it. Better prompts help, but without context the model guesses. Context helps, but without a harness the output is inconsistent. A harness helps, but without a loop you're still manually triggering every run.

Full setup guide for all 4 layers using Fable 5 below.

[DAN KOE @thedankoe]

https://t.co/gN9cBK7feV

[Juned Khatri | Engineer Turned Recruiter 🇮🇳 @hijunedkhatri]

How to actually land a remote job in 30 days.

I've made 320+ hires.
Most candidates apply on job boards and wait.

Here's what actually moves the needle.

Step 1.
Pull companies hiring across these boards
- Wellfound
- Remote OK
- We Work Remotely
- FlexJobs
- Jobgether
- Remotive
- Working Nomads
- Jobspresso
- JustRemote
- Underdog
- Built In
- Remote co
- Skip The Drive
- Virtual Vocations

Step 2.
Verify the posting is genuine before you spend time on it. Check multiple signals.

Same role posted on the company's own careers page
Same role posted on LinkedIn
Same role also live on Wellfound
Company page on LinkedIn shows recent hiring activity, not just one stray post
Job description matches across platforms, not copy pasted from 6 months ago
More signals lining up, more real the role is.

Step 3.
Find the email of the CTO, engineering manager, or founder using Apollo.

Step 4.
Email 2 people directly. Keep it short, mention the specific role, attach your resume.

Step 5.
Follow up once after 4-5 days. Low key, just a bump, not a chase.

Step 6.
Do this for 10 companies a day, every day, for 30 days.
That's 300 companies you've reached out to directly. Not 300 applications sitting in some ATS queue.

I've seen people land offers doing exactly this while everyone else was still refreshing job boards and waiting for a response.

Happy to answer questions if you're stuck on any of this. Happy Job Hunting :)

[Rawghu Writes @Raw_ghav]

@mikefutia SCRAPE

[Rawghu Writes @Raw_ghav]

@shivsakhuja Goose