Akash Deep Vishwakarma

Learning & Experimenting with - Java, Spring Boot, Microservices, Gen AI, Agentic AI and more...

[Puneet Patwari @system_monarch]

I'm a Principal with 12 years of experience. If I was coaching you to crack system design rounds for Sr to Staff+ AI/ML roles at companies like Meta, Google, Salesforce, Amazon, etc.

I would 100% ask you to work on these fundamentals before we would start talking about interviews.

Because AI system design is still system design.

The only difference is that now your bottlenecks are not just databases, caches, and queues.

They are tokens, context windows, retrieval quality, inference cost, hallucinations, model latency, evals, and user trust.

Here are the fundamentals I would start with:

➤ LLM Basics
↬ Tokens
↬ Context Window
↬ Prompt Design
↬ System Prompts
↬ Temperature
↬ Top-p Sampling
↬ Structured Outputs
↬ JSON Mode
↬ Function Calling
↬ Tool Calling
↬ Agents
↬ Memory
↬ Guardrails
↬ Hallucinations
↬ Model Latency
↬ Model Routing
↬ Small vs Large Models
↬ Fine-tuning vs Prompting
↬ Open-source vs Closed Models

➤ RAG & Retrieval
↬ Embeddings
↬ Vector Search
↬ Vector Databases
↬ Chunking
↬ Chunk Overlap
↬ Metadata Filtering
↬ Hybrid Search
↬ Keyword Search
↬ Semantic Search
↬ Reranking
↬ Retrieval Recall
↬ Retrieval Precision
↬ Query Rewriting
↬ Document Freshness
↬ Permission-aware Retrieval
↬ Citation Grounding
↬ Evidence Selection
↬ Context Packing
↬ Missing Information Detection

➤ AI System Architecture
↬ API Gateway
↬ Request Routing
↬ Model Gateway
↬ Prompt Service
↬ Inference Service
↬ Retrieval Service
↬ Ranking Service
↬ Feature Store
↬ Offline Pipelines
↬ Online Serving
↬ Async Processing
↬ Queueing
↬ Streaming Responses
↬ Rate Limiting
↬ Fan-out/Fan-in
↬ Batch Inference
↬ Real-time Inference
↬ Human-in-the-loop Systems
↬ Fallback Workflows

➤ Cost & Performance
↬ Token Budgeting
↬ Prompt Compression
↬ Prompt Caching
↬ Semantic Caching
↬ Response Caching
↬ Batch Requests
↬ Model Quantization
↬ Distillation
↬ Latency Budgets
↬ Cold Starts
↬ GPU Utilization
↬ Throughput
↬ Cost per Query
↬ Cost per User
↬ Model Selection
↬ Inference Scaling
↬ Backpressure
↬ Load Shedding

➤ Evaluation & Quality
↬ Offline Evals
↬ Online Evals
↬ Golden Dataset
↬ Human Review
↬ LLM-as-Judge
↬ A/B Testing
↬ Regression Testing
↬ Answer Relevance
↬ Factual Accuracy
↬ Faithfulness
↬ Groundedness
↬ Toxicity Checks
↬ Safety Checks
↬ Drift Detection
↬ Feedback Loops
↬ Confidence Scoring
↬ Escalation Criteria
↬ Quality Monitoring

➤ Reliability & Security
↬ Timeouts
↬ Retries
↬ Circuit Breakers
↬ Failover
↬ Model Fallbacks
↬ Graceful Degradation
↬ Observability
↬ Tracing
↬ Prompt Logs
↬ Token Metrics
↬ Error Budgets
↬ PII Redaction
↬ Data Privacy
↬ Access Control
↬ Prompt Injection
↬ Jailbreak Defense
↬ Audit Logs
↬ Compliance

[Scotty Matthewman @scottymatt]

this is sick https://t.co/1dKi95YO5u

[ClaudeDevs @ClaudeDevs]

We shipped four updates to Claude Managed Agents this week.

First, you can now set a budget for sessions to keep spend predictable. Sessions that hit the limit pause with a budget_reached event, you can raise the budget to resume.

[ClaudeDevs @ClaudeDevs]

New in Claude Code: your sessions can now message each other.

Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.

[Akshay Saini @akshaymarch7]

I've spent 10+ years writing production code, working at startups, Paytm, Uber, building products, managing teams, and getting multiple promotions.

One lesson my corporate life taught me:

Nobody gets promoted because they work the longest hours.

The people who create the highest impact become difficult to ignore.

Being busy and being valuable are two completely different things.

Be so good that people around can't ignore you! 🔥

[ClaudeDevs @ClaudeDevs]

MCP 2026-07-28 is live and it's the largest update to the protocol since launch.

MCP is now stateless, making it easier to deploy and scale remote servers.

https://t.co/K8KqxbUh4e

[Cursor @cursor_ai]

Today we're launching Cursor Start, a new ₹649/month plan for developers in India.

Start includes generous access to Grok 4.5 and Composer, so you can plan, build, test, and ship with agents every day.

[Anupam Haldkar  @AnupamHaldkar]

If you're preparing for the Claude Certified Architect – Foundations certification, here's the complete exam blueprint.

- Exam Guide: https://t.co/KXD0akhKlH

- Official Certification: https://t.co/tcEZ1QGvet

- Official Prep Courses: https://t.co/2k8pfTJZlK

- Community Study Guide: https://t.co/5oPVwHtmlY

- Playbook: https://t.co/OGd7Hn8SDM

[Gaurav Sen @gkcs_]

Here is the recording of my session on "Mastering RAG-based systems for software engineers"

We cover such topics in the AI Engineering Cohort, starting 1st August 2026.

Registration Link: https://t.co/6l1xVg3h9v

[Akash Deep Vishwakarma @adv2612]

@systemdesignone Playbook

[Neo Kim @systemdesignone]

I just created a playbook to help you learn AI engineering.

It gives you:

• Core concepts behind modern AI systems.
• Condensed notes to understand AI engineering stack.
• Must know techniques to build, deploy, debug & scale AI apps.

(24 hours only!)

To get it for FREE:
1. Like, Retweet & Follow @systemdesignone
2. Reply "Playbook"

Then I'll DM you the details.

[Anupam Haldkar  @AnupamHaldkar]

One accidental paste can expose an API key, access token, or other secret.

That's why I came across SecureIntent, a Chrome extension that warns you before you paste sensitive credentials into AI tools or other websites.

🔒 Runs entirely on-device
🚫 Your pasted text never leaves your browser
✂️ Can redact detected secrets before pasting
⚡ Works across popular AI chat and coding tools

If you work with AI, code, or cloud infrastructure, it's worth checking out.

🌐 https://t.co/LDujngCUOE

🧩 Chrome Extension:

https://t.co/TKivPULxhX

[Rahul @sairahul1]

must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must must read

[KingWilliam @kingwilliam_]

https://t.co/gTEzA9vLxY

[Dipanshu Kushwaha @Dipanshu_AI]

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 and read this article below

[Rahul @sairahul1]

ST£AL These 7 Claude Prompts to Learn Anything 10x Faster

1. The Feynman Technique

​Use this when a concept feels too academic, abstract, or overwhelming. It forces the AI to strip away the jargon.

​The Prompt: > "Teach me [insert topic] in simple language, as if you are explaining it to a beginner. Break it into clear, easy-to-grasp steps and provide simple examples. Afterward, ask me to explain it back to you in my own words. Evaluate my response to identify any gaps, misconceptions, or missing pieces in my understanding."

2. First Principles Breakdown

​Use this when you need to understand the underlying logic of a subject, rather than just memorizing surface-level facts.

​The Prompt: > "Act as an expert instructor. Break down [insert topic] into its most fundamental building blocks using first principles thinking. Challenge standard assumptions, explain the ‘why’ behind each concept, and rebuild the idea from the ground up so I understand the core mechanics."

3. The Active Recall Coach

​Reading creates the illusion of competence. Recalling information builds actual memory. Use this to test yourself.

​The Prompt: > "After teaching me the basics of [insert topic], quiz me with progressively challenging questions that force me to actively recall information without looking at my notes. Mix conceptual, applied, and scenario-based questions. Evaluate my answers, clearly explain any corrections, and reinforce my weak areas with targeted follow-up questions."

4. Spaced Repetition System

​Use this to ensure you do not forget what you learned today by the time next week rolls around.

​The Prompt: > "Create a spaced repetition revision schedule for mastering [insert topic]. Outline exactly what I need to review daily, weekly, and monthly based on memory retention principles. Specify review activities—like recall, practice, and testing—and tell me how to adjust the intervals based on my performance to move this information into my long-term memory."

5. Smart Knowledge Summary

​Use this when you need a cheat sheet or a high-level overview of a broad topic.

​The Prompt: > "Summarize [insert topic] using clear frameworks, mental models, and simplified structures. Highlight the key principles, patterns, and relationships within the subject. Present this information in a highly structured way that makes it easy to remember and apply to real-world situations."

6. Learning Acceleration Roadmap

​Never wonder what you should study next. Use this to create a personalized syllabus.

​The Prompt: > "Design a structured, end-to-end learning roadmap for mastering [insert skill]. Break the journey down into progressive stages, milestones, and checkpoints. Specify the key resources to study and practice tasks for each stage, and define measurable criteria so I can efficiently track my progress and always know exactly what to learn next."

7. Targeted Weakness Assessment

​Use this to find out what you do not know before it costs you in an exam or a real-world scenario.

​The Prompt: > "Ask me a series of diagnostic questions about [insert topic] to identify my weakest areas, blind spots, and misunderstandings. Adapt the difficulty of the questions based on my answers. Once we finish, explain where I went wrong and recommend specific exercises or focus areas to strengthen my overall comprehension."

[Rohit @heyrohitai]

🚨 Anthropic just showed a 27-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now.

[Raytar @Raytar]

My friend applied to 200 tech jobs in two years. No CS degree. No callbacks.

Last month Anthropic offered him $750,000.

All because of one Stanford lecture. Free on YouTube. One hour.

A professor explains how ChatGPT actually works. Not the Twitter version. The real one.

He watched it in bed. Paused it eleven times. After that hour he told me something I didn't believe. "It's embarrassingly simple."

Three days later he applied to Anthropic.

Every single question they asked him, he knew from that video.

[Akash Deep Vishwakarma @adv2612]

Learn CLAUDE in 1 HOUR 🔥

[Anuj @anujcodes_21]

Claude FULL COURSE 1 HOURS (Build & Automate Anything)

[Akash Deep Vishwakarma @adv2612]

Loop engineering is the future. Here's how you can learn it for free.

[Rahul @sairahul1]

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

Loops.

Most builders are doing this wrong:

No memory file, so every loop starts from zero.
No sub-agent split, so one agent tries to do everything.
No stop condition, so loops run forever and bill you in your sleep.

Most builders are missing at least two of the three.

Watch the video first.

Then read this - everything you need to know about Loops in 2026, in one place.

Bookmark this before it gets buried.