1
If you’re still feeding your LLMs with plain JSON, you’re leaving tokens, speed and budget on the table. TOON launched last week — and it’s a game changer for anyone building with LLMs
Home / LinkedIn creators / Brij Kishore Pandey
Brij Kishore Pandey
AI Architect & AI Engineer | Building Agentic Systems & Scalable AI Solutions
We read 917 of their posts. Here is what they actually do.
TechnologyEducationalAuthority hooksProfessionals
linkedin.com/in/brijpandeyji ↗737KFollowers
7.2Posts / week
971Avg likes
629Median likes
57Avg comments
9.3K likesBest post
Engagement over time
Average likes per post, by month.
1.3likes / 1K followers
That puts them in the 25th percentile of the 1,390 creators we track in the 100K to 1M follower band. Reach is not the same as resonance, and this is the ratio that separates them.
2025-03Average likes per month2026-08
Their hooks, word for word
The opening line of their best-performing posts. This is what stops the scroll.
- If you’re still feeding your LLMs with plain JSON, you’re leaving tokens, speed and budget on the table.9.3K likes
- Not all APIs are created equal.8.3K likes
- Master the core SQL commands that drive 80% of tasks. This post focuses on practical, real-world applications of SQL for maximum impact.7.8K likes
- LLM ≠ Generative AI ≠ AI Agents ≠ Agentic AI7.4K likes
- Top Generative AI Terms You Should Always Know-7.3K likes
- The AI Agents Staircase represents the structured evolution from passive AI models to fully autonomous systems.7.3K likes
Content pillars
What they post about, with a line from a real post as evidence.
- AI Architecture & Agentic Systems
Explaining the progression from LLMs to autonomous Agentic AI systems.
- Technical Cheat Sheets & Core Engineering
Breakdowns of essential SQL commands, Linux directories, and API architectures.
- Modern Data & Tooling Formats
Covering new formats like TOON and retrieval strategies for RAG.
Signature moves and voice
The repeatable moves that show up across their best posts.
- Use inequality hooks to contrast related concepts.
- Structure lists with clear directional arrows and bullet points.
- Add 'When to use' practical decision frameworks.
Tone of voiceAuthoritative, educational, and structured, breaking down complex engineering concepts into crisp, accessible technical frameworks.
What works for them
Patterns that separate their top posts from the rest.
- Contrasting buzzwords into distinct conceptual tiers drives massive technical engagement.
- High-utility foundational cheat sheets reliably generate broad professional interest.
- Actionable announcements of emerging developer tools outperform general commentary.
When they post
Every post, grouped by day of week.
Mon
830
Tue
1.1K
Wed
841
Thu
888
Fri
837
Sat
1.4K
Sun
1.1K
Posts publishedAverage likes
Best day is Saturday at 1.4K average likes. Monday is their weakest at 830.
What format works
Text, image, video or carousel, ranked by what actually lands for them.
| Format | Posts | Avg likes | |
|---|---|---|---|
| Image | 849 | 1K | |
| Carousel | 7 | 281 | |
| Text only | 22 | 264 | |
| Video | 39 | 87 |
Format fingerprint
How their posts are built, measured across every post we analysed.
Median length1,948 chars
Line breaksHigh
Bullet pointsMedium
EmojiNone
HashtagsLow
Outbound linksHigh
Reading levelGrade 3
Promo intensity1/10
Steal this
Moves you can apply to your own posts this week.
- Clarify industry confusion by mapping out overlapping technical terms.
- Pair abstract architectural concepts with clear, real-world application examples.
- Lead with high-impact cost or efficiency gains in technical hooks.
Best-performing posts
Ranked by likes, across everything we analysed.
2
Not all APIs are created equal. The architecture you choose has a direct impact on your application's scalability, performance, and long-term maintainability. It's not just about implementation—it's about alignment with your business goals and technical constraints.
3
Master the core SQL commands that drive 80% of tasks. This post focuses on practical, real-world applications of SQL for maximum impact. Fundamental SQL Commands 1. SELECT: Retrieving specific data SELECT first_name, last_name, email FROM customers; 2.
4
LLM ≠ Generative AI ≠ AI Agents ≠ Agentic AI We need to stop grouping them together. Each serves a different purpose, operates at a different level of complexity, and solves a different class of problems. Here’s the breakdown: 🔹 LLM Predicts tokens based on patterns in data. No memory.
5
Top Generative AI Terms You Should Always Know- 1. LLM (Large Language Model) What it enables: The engine behind modern AI applications - Business Impact: Powers everything from code generation to content creation - Implementation: Models like GPT-4, Claude, and Gemini 2.
Similar creators
Comparable follower counts, analysed the same way.
Stop paying $3,000 for what 2pr does in 1 minute.
free trial, no limits on requests — start growing on LinkedIn today.
Built from public LinkedIn posts, last refreshed 2026-09-03. Follower counts and engagement change over time. Brij Kishore Pandey is not affiliated with 2pr.io. Request removal.