Alexey Grigorev ✓
@Al_Grigor · Build and ship together: · joined 20 Jan 2020
Founder @DataTalksClub | Teaching engineers to build production AI systems | AI agents, LLMs, ML, data engineering | 100,000+ learners
29 670Followers
431Following
8 029Posts total
36.5KViews on collected posts
Latest posts
Looking for new posts…
I hope I'll be able to do the same with .claude soon too https://t.co/1grVEyOi0A
893 views · 7 likes
· 0 reposts · 0 replies
Open on X →
I built a Django to-do app in one prompt.
Cost: less than $1.
Here's what the coding agent did:
1. Created the project structure
- Generated Django project and app
- Set up settings and URLs
- Configured Tailwind CSS for styling
2. Built the data model
- Created a Todo model
1.1K views · 21 likes
· 4 reposts · 8 replies
Open on X →
Jev is a new kind of model that doesn't generate text. It only makes decisions.
You send it a state (text or JSON) plus a set of typed questions, and it returns structured JSON with probability distributions.
I replaced my gpt-4o-mini setup for routing tasks to my 3 agents and
1.2K views · 23 likes
· 1 reposts · 6 replies
Open on X →
@Al_Grigor i am currently working on enterprise data analysis agent, pretty interesting.
https://t.co/QjpgQfMaJ7
282 views · 1 likes
· 0 reposts · 0 replies
Open on X →
If you found this post helpful, follow me for more content like this.
I publish a weekly newsletter where I share practical insights on data and AI.
It focuses on projects I'm working on + interesting tools and resources I've recently tried: https://t.co/oh7DBWuGEE
793 views · 4 likes
· 0 reposts · 1 replies
Open on X →
So you follow one evolving system, practice on separate mini-projects, explore other examples, and build something of your own in parallel.
That is the core of Buildcamp.
The course starts in less than 5 days. You can sign up for the course here: https://t.co/REMfPMnikB https:/
1.1K views · 6 likes
· 1 reposts · 0 replies
Open on X →
Optional projects:
8. FAQ Assistant: Add search integrations and turn it into a support chatbot.
9. YouTube Transcript Summarizer: A system that extracts summaries and chapter structure from YouTube videos using structured output.
10. PDF Book Processor: Similar tasks often ht
1.2K views · 4 likes
· 0 reposts · 1 replies
Open on X →
Homework projects:
3. Document processing with AI. You download books, extract PDF text, chunk documents, and build a full RAG pipeline.
4. Wikipedia Agent. You implement search and page-fetching tools and build an agent using a framework of your choice.
5. Testing and https:/
1.1K views · 4 likes
· 0 reposts · 1 replies
Open on X →
2. Capstone project
Your own AI application, built step by step during the course, from first RAG version to a more complete system with tools, testing, monitoring, evaluation, and deployment. https://t.co/6dYwGSnjWZ
1.3K views · 7 likes
· 1 reposts · 1 replies
Open on X →
1. A running example project
A Documentation Agent that evolves throughout the course. It starts as a RAG system and gradually becomes an agent that is tested, monitored, and evaluated. https://t.co/62CSPLgE4j
1.5K views · 7 likes
· 0 reposts · 2 replies
Open on X →
AI Engineering Buildcamp is project-driven.
You learn AI engineering by building.
15 projects you can build during the course 👇🏼
(You get lifetime access to the course if you sign up) https://t.co/VUDgEMhMLG
24.2K views · 371 likes
· 74 reposts · 9 replies
Open on X →
Against accounts of the same size
4 posts from the last 90 days, next to the 10K–100K follower range. right around the median for its follower range.
Median views1 130this account924median for 10K–100K
Reach, %3.81%this account3.62%median for 10K–100K
Engagement, %1.69%this account1.52%median for 10K–100K
| Metric | This account | Median for 10K–100K | Ratio |
|---|---|---|---|
| Median views per post | 1 130 | 924 | 1.22× |
| Reach (views ÷ followers) | 3.81% | 3.62% | 1.05× |
| Engagement rate | 1.69% | 1.52% | 1.11× |
Others in this range → Compare with another account → How these benchmarks are built →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
24.2K9 Apr
1.5K
1.3K
1.1K
1.2K
1.1K
793
28210 Apr
1.2K18 Sep
1.8K
1.1K19 Sep
893
Last 12 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
1.87%9 Apr
0.61%
0.68%
0.45%
0.42%
0.63%
0.63%
0.35%10 Apr
2.59%18 Sep
0.33%
3.00%19 Sep
0.78%
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.
What the audience does
Likes41.4%460 in total
Reposts7.3%81 in total
Replies2.6%29 in total
Quotes0.1%1 in total
Bookmarks48.6%540 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Similar accounts
Upendrra Rai ✓
@UpendrraRai
59.3K followers
· 29.6K posts
Faisal Karim Kundi ✓
@fkkundi
59.3K followers
· 13.8K posts
Emilia Mars ✓
@emiliamarsx
59.3K followers
· 2.9K posts
Jack McDaniels ✓
@jackwmcdaniels
59.3K followers
· 2.3K posts
Devon ☀️ ✓
@devonzuegel
59.3K followers
· 18.2K posts
Epic Wallpapers ✓
@Epicartworks
59.3K followers
· 12K posts
ʌиıʍʌ ✓
@anima_marina
59.3K followers
· 17.9K posts
曹操说 ✓
@wildwall1984
59.3K followers
· 12.2K posts