AI Agents
AI Basics
AI for Design
Engineering
Practice
test
Working with LLMs
#Agents
#Automation
#Context windows
#Cost
#Design systems
#Embeddings
#Evaluation
#Fine-tuning
#Prompting
#RAG
#test
#Tokens
Clear all
5 posts found
Training, fine-tuning and prompting are three different tools
04/09/2026
—
[email protected]
Teams reach for fine-tuning when they need context, and for prompting when they need behaviour. Knowing which problem ea...
The context window is a budget, not a memory
02/09/2026
—
[email protected]
Bigger context windows did not give models memory. They gave you a larger envelope to fill on every single request — and...
Why agents fail on long tasks
19/08/2026
—
[email protected]
An agent that handles five steps beautifully can fall apart at twenty. The reason is rarely reasoning — it is that the c...
Giving an agent memory without giving it amnesia
17/08/2026
—
[email protected]
Memory is not a feature you enable. It is a set of decisions about what to keep, what to summarise and what to let go —...
Prompt caching: the cheapest speedup you are not using
30/07/2026
—
[email protected]
If every request begins with the same two thousand tokens of instructions, you are paying full price to resend them. Ord...