Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Building LLM Powered Features (lightning talk)
Search
Radoslav Stankov
July 19, 2025
0
15
Building LLM Powered Features (lightning talk)
Radoslav Stankov
July 19, 2025
Tweet
Share
More Decks by Radoslav Stankov
See All by Radoslav Stankov
All you need is CSS
rstankov
0
56
Ruby on Rails The Single Engineer Framework
rstankov
0
11
Rails: The Missing Parts
rstankov
1
170
The dream that turned into nightmare
rstankov
0
260
The dream that turned into nightmare (lightning)
rstankov
0
81
Ruby on Rails - The Single Engineer Framework
rstankov
0
300
Living Without Exceptions
rstankov
1
260
One engineer company with Ruby on Rails
rstankov
2
760
Eliminating noise from your code
rstankov
0
150
Featured
See All Featured
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
What's in a price? How to price your products and services
michaelherold
246
12k
Code Review Best Practice
trishagee
70
19k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
YesSQL, Process and Tooling at Scale
rocio
173
14k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
How STYLIGHT went responsive
nonsquared
100
5.7k
Music & Morning Musume
bryan
46
6.7k
Transcript
⚡lightning talk ⚡ Building LLM Powered Features " Radoslav
Stankov
None
#
Radoslav Stankov @rstankov rstankov.com
https://tips.rstankov.com
None
1.AGI 2.AI taking developers jobs 3.Vibe coding 4.How fast AI
moving 5.Agents / MCP I'm not talk about
None
LLMs are already incredible, and there is years of work
to be done to fully productize the capabilities that exist today.
None
None
None
None
None
MODEL GPU Network API
await fetch("https://api.openai.com/v1/chat/completions", { method: "POST", headers: { "Content-Type": "application/json", "Authorization":
"Bearer YOUR_OPENAI_API_KEY" }, body: JSON.stringify({ model: "gpt-4", messages: [ { role: "system", content: "You are a helpful assistant." }, { role: "user", content: "Explain what LLM is" } ], temperature: 0.7 }) });
Instructions (system prompt)
Input (user prompt)
None
None
None
Evals
None
None
None
None