AIBussin
Build useful systems with modern AI
Menu
Home
Books
Solutions
Learn
Toolkit
Prompts
Articles
About
Software Engineering
What Context Means
Beyond the Chat Box
What Remembering Means
The Measurement Instrument
Never Stand in Front of the Steamroller
The Measurement Instrument
The Context You Didn't Type
If There's Any Doubt, It's Deterministic
The RAG Baseline
The Context Window Is a Budget
From Retrieval to Persistent Understanding
Scrum Built the Training Set
More Is Not Better
Meat Proxy
Pathways Through Memory
Order Changes Meaning
The Memory Nexus
The Price of Intelligence
Not All Tokens Are Equal
Why
Intelligence in the Wrong Direction
Make the Window Bigger
Is It Still True?
Where Are the Finished Projects?
Reuse Before Recompute
One Runtime, Many Windows
What Did We Leave Unfinished?
Remove What No Longer Matters
A Revolver, Not a Foundation
What Matters Right Now?
Compression Is Loss
Consequences Nobody Wrote Down
The Smallest Useful Model Call
Let Old Context Fade
Does Better Context Change Behaviour?
One Operation, Several Model APIs
Externalize the Working Set
Token Counts Don't Add Up
When the Frame Is Wrong
Bring Back Only What You Need
A Successful Call Is Not Finished Work
Context Is a Bottleneck
The Agent Writes Its Own Context
What Did the Model Actually See?
What Should Memory Keep?
Memory Is a Context Source
Learning From Experience
Restart Is Not Resume
Tools Produce Context
Can Memory Be Trusted?
Preserve Before You Interpret
When Memory Becomes Documentation
Representation Is Part of Context
Claims, Evidence, and Decisions
Who Gets to Be Right?
The Agent Said Done. Did Anything Change?
The Remembering System
Context Goes Stale
Appendix — Building a Remembering Agent
Capability Is Not Authority
Edition History
Keep Context in the Right World
The Agent Cannot Grade Its Own Homework
Assemble for the Task
Retries Are Side Effects Too
The Context Compiler
Blind Before You Compare
What a Compilation Proves
The Models Were Different. Their Mistakes Weren't
Did It Reach the Model?
When Your Benchmark Is Too Easy
Did the Context Help?
Discovery Is Not Promotion
The Complete Context System
Replicate Before You Believe
What Should Happen Next?
One Process, End to End
Your Applied AI