Waqas Khan

EM / Tech Lead @ Point Pickup. Past: iOS @chesscom, cofounder IQFriends ( / China xlr8r / StartupBrasil), founder Half Fried Games, Gikian.

[Rubab Ai @AiWithRubab]

According to Feng Shui, the mess in your house isn't random. It's a map of where the energy is stuck in your life.

Overflowing closet =

[Jamon @jamonholmgren]

I'm just going to dump my whole agentic setup out here, because I see too many people missing giant chunks of this and it's hurting them.

Here's what I have and recommend:

0. an AGENTS.md that is a router -- it sends the agent to the right skills, docs, tools

1. a standard workflow doc/skill customized to my needs ... (grab Matt Pocock skills if you don't already have something) ... I tag this in most sessions with `@/AGENT_WORKFLOW.md` and it pulls it in.

2. self-healing docs for every system, and agents are instructed to keep them updated ... I tag the ones I know I need, or let the agent find them through AGENTS.md ... I also provide a more detailed summary in the first 7 lines of every doc, so they're easily greppable to find the right thing, and this is documented in AGENTS.md

3. agents always run the app ... the agent should always actually run the app itself, and test its work and fix issues as it goes, especially if running autonomously / asynchronously

4. end-to-end tests and instructions to write more and keep up to date, and docs on how to write tests, what to avoid, and a list of all the tests and what they test in yet another markdown doc ... write and run targeted tests during implementation, improve and commit with work

5. custom linters at precommit hooks looking for any problems you run across, with `--fix` fixing the problems automatically, OR if that's not feasible, it shells out to a cheaper LLM like Composer 2.5 or Sonnet to fix the problems -- NOT just flagging them, but actually resulting in cleaned code

6. cross-agent review at each major point: research, plan, implementation, and wrap-up. I mean codex, claude, cursor, whatever -- but it shouldn't be the same model reviewing the same code. And specific docs for agent review, what to look for, how to approach it. Also, personas -- looking at the code from different perspectives, such as maintainability, code quality, security, performance, AI smells, domains (e.g. "financial services expert" or whatever) ... and each persona also "owns" a set of system docs too and keeps them up to date

7. agent traces / worksheets that track what the agent is doing each session. if the agent fails partway through, you should be able to hand this worksheet to another agent and it could finish the job. commit this worksheet with the work so it's all connected and easy to reference later (you will reference these later!!), also have the agent apply git tags that correspond to specific worksheet names so they're easy to find

8. automatic agent feedback to you at the end of the session, added to a doc that is also committed with the work, that you periodically ingest into an interactive session and improve your workflows

9. a tools or bin folder that contains python or bash scripts that the agent has skills to make to make its job easier (for example, I have an `agent_review` bash script that lets the agent kick off agent reviews via CLI without knowing each agent's particular incantations) ... docs on how to make scripts effectively, and instructions to constantly build these out more

10. periodic agent sweeps through recent commits, looking for problems / gotchas from a higher level across commits

11. a coding conventions doc that is just for specific coding conventions you want to see in the code base, your review agents use these a lot (but a lot of this should be in linters)

12. an agent loop / night shift skill for autonomous work, that lays out how the agent is to approach this, from an orchestration standpoint

13. a task queue that is accessible to the agent (mine is just a TODOS.md, but yours might be in Linear etc, with a CLI to fetch via API)

14. a periodic false-confidence test audit skill that looks for tests that aren't actually testing what you think they're testing, and that fix those

15. visual regression tests -- take screenshots, compare via tool and with agent visual review, commit with work (git lfs useful here) or at least push into the PR

16. automatic performance benchmark tests that notice when performance degrades

17. performance profiling tools that can be used by agents for targeted benchmarking, trying new techniques, comparing outputs, and comparing profiles

18. end-of-shift full validations, including running all tests, performance, agent reviews, sweeps, everything -- when you return, it's all as pristine as it can be

If you have all this, your agentic coding experience is going to be very different than dry prompting and manually guiding it toward the right thing every time.

[Lionel Mora @lionel_mora]

Following the amazing reaction to the Marble Curriculum yesterday, we've decided to make it open source 🛰️👇

Everything a child learns in primary school. 1,590 concepts. 3,221 connections across 8 subjects, from Math and Science to Computing and Life Skills. Anchored in the US and UK curriculums, standard by standard (NGSS, Common Core, DfE).

What you will find in the repo: every concept as structured JSON with its age band and the evidence a child must show to master it. Every prerequisite link marked hard or soft, with a written rationale. It's a true DAG you can compute learning paths on. Open license, you can build whatever you want with it.

Now is a unique time in history to be building in education. Getting AI and kids education right is likely one of the hardest and most important problems to crack over the next decade and we need as many smart and creative minds behind it.

We think a common solid basis, accessible to all and that can be built upon, is critical to move fast. That's why we're making this curriculum open source.

It's not perfect but we know it's a robust basis, and we believe that sharing it openly is the fastest way to progress in this field. If you're building in education, share this around you and tell us in comments if you find this useful and if you want to contribute.

We'll keep working and investing on it @withmarbleapp. Credit goes to @guillaume_boni for building this. I just made it look pretty.

Links below 👇

[Bayyinah Institute @bayyinahinst]

The Quran says 'don't point out your own flaws.' - وَلَا تَلْمِزُوٓا۟ أَنفُسَكُمْ -  The phrasing is odd at first, but there's wisdom hidden here. (49:11)

[Movez @0xMovez]

Andrew Ng:

"100% of my tasks are now done by AI agents - hype has exceeded my expectations. Loops is next step.

in 3-6 months, everyone will be using self-improving loops. No more prompting."

In a 30-minute talk, Andrew Ng explains how to build self-improving agentic systems from scratch.

Worth more than a $500 agentic course.

[Bayyinah Institute @bayyinahinst]

When the tribe of Tamim came to Madinah, Umar and Abu Bakr argued loudly about leadership. The Prophet ﷺ sat quietly listening.

[Matt Van Horn @mvanhorn]

https://t.co/DM0CAuyprS

[H’s mom @aiishadahir]

SubhanAllah… today the Ustadh asked a question that made the entire class freeze:

“Who are you in the story of Musa and Khidr?”

Naturally, we all thought the answer was Musa. It wasn’t.

What he said next completely shattered my perspective on surah kahf

[Poonam Soni @CodeByPoonam]

Anthropic engineer revealed exactly how they build AI agents internally.

And it's not what most developers expect.

Here's what stood out 👇
→ Most agents fail from bad architecture than bad models
→ The best agents are simple. Complexity kills reliability.
→ Tool design matters more than prompt design
→ Evaluation is the hardest and most ignored part of agent development
→ Real production agents look nothing like demo agents

[Roan @RohOnChain]

Anthropic pays $750,000+ a year for engineers who can build LLM architectures from scratch. Stanford taught the entire thing in 1 hour lecture & released it for free.

Bookmark & watch this today before someone takes it down.

[NutriScience @Nutri_Science_]

I was 29kg overweight, had a huge belly, and I wanted to reach 13% body fat in 2026. I did it with these 25 rules:

Rule 1. STOP RUNNING.

[Discover @0x_Discover]

An Anthropic engineer caught my screen at a café in SF.

“Are you seriously running Claude against live markets?”

Yes.

I walked him through it.

214 trades
74% WR
+$9,437 / 19 days

Copy it:https://t.co/IPY41UFgnZ

Stack is simple:

– historical market + wallet dataset
– CLI for fast market access
– execution layer with strict filters

No predictions.

First repo:
https://t.co/VuXDNYM1tz

The model ranks wallets by exit efficiency.

Metric that matters:

captured_value / expected_value > 0.70

If a wallet can’t realize its edge — it’s noise.

Signals only trigger on repeated structure.

Second repo:
https://t.co/tvkaEEx1b7

Position sizing = Kelly.

f* = (p*b - q) / b

Most cycles: idle.

When conditions align: deploy capital.

Three trades:
+7c, +22c, +16c — all closed within hours

He looked at the repos, paused:

“We had internal experiments like this.”

There’s no secret.

Just discipline.

Markets don’t pay for being right.

They pay for exiting well.

[Allen Braden @allen_explains]

This 2-hour Stanford lecture breaks down how models like ChatGPT and Claude are actually built, clearer than what many people in top AI roles ever get exposed to.

Save this and set aside two hours today. It might end up being the most valuable thing you learn all week.

[H’s mom @aiishadahir]

In the time of the Prophet ﷺ, there was a young man and like many young people, his desires were strong. He who walked into the masjid while the Prophet ﷺ was sitting with his companions.
And he said something no one expected:

“Ya Rasulullah… allow me to commit zina.”

[الــحــديـــث @Alhdeth]

قال رسول الله ﷺ

ما أصاب أحدا قط هم ولا حزن فقال :

اللهم إني عبدك ، وابن عبدك ، وابن أمتك ، ناصيتي بيدك ، ماض في حكمك ، عدل في قضاؤك

أسألك بكل اسم هو لك سميت به نفسك ، أو علمته أحدا من خلقك ، أو أنزلته في كتابك ، أو استأثرت به في علم الغيب عندك

أن تجعل القرآن :
ربيع قلبي
ونور صدري
وجلاء حزني
وذهاب همي

إلا أذهب الله همه وحزنه وأبدله مكانه فرجا .

فقيل : يا رسول الله ، ألا نتعلمها ؟

فقال : بلى ، ينبغي لمن سمعها أن يتعلمها.

صححه الألباني في السلسلة الصحيحة 199

[Sara @piousdeenn]

Allah gave us 25 role models in Quran.

Here’s how they handled pain, pressure, success, failure, and leadership:

[Cool_Ustaaz ☪ @Cool_Ustaz]

Stop saying: « 0 Allah, make it easy for me. » Start saying this instead:

—Slide it 🛝

[H’s mom @aiishadahir]

Allah swears by TIME but not the time you think.

He doesn’t say Zaman, He says “Wal-‘Asr”

Why ‘Asr?

[𝐌𝐚𝐡𝐝𝐢 @Mahdii_365]

Before the Battle of Uhud, one of the polytheists dug a pit and sat for days digging it, saying:

"Perhaps Muhammad {pbuh} will pass by it and fall into it."

And when the Battle of Uhud came, and the Messenger {pbuh}, was in the midst of the battle, he did not see the pit, so he fell into it, and his noble face struck the stone, breaking his incisors-that is, his front teeth- and blood flowed from his noble face..

......see more 👇👇

[Sam Hogan 🇺🇸 @samhogan]

What if a codebase was actually stored in Postgres and agents directly modified files by reading/writing to the DB?

Code velocity has increased 3-5x. This will undoubtedly continue. PR review has already become a bottleneck for high output teams.

Codebase checked-out on filesystem seems like a terrible primitive when you have 10-100-1000 agents writing code.

Code is now high velocity data and should be modeled at such. Bare minimum, we need write-level atomicity and better coordination across agents, better synchronization primitives for subscribing to codebase state changes and real-time time file-level code lint/fmt/review.

The current ~20 year old paradigm of git checkout/branch/push/pr/review/rebase ended Jan 2026. We need an entirely new foundational system for writing code if we’re really going to keep pace with scale laws.