instibrain
instibrain  /  guides  /  around the model

What people build around a model, in nine short lessons.

A model alone reads text and writes text. How a model works opens it. This series is what people build around it: the context window it reads, the tools it calls, the attack it meets, the test that says it works, and the kinds of memory a company gives it. Retrieval and cost have series of their own, and the lessons link them.

No code and no mathematics. Every Try it is words to type in a Claude window.

the lessons · the words under it

Nine lessons, from the context window to the memory.

Lessons 1 and 2 are the context window and what a line in it is worth. Lessons 3 and 4 are tools and agents, lessons 5 and 6 the attack on them and what stops it. Lesson 7 says how to know it works, lesson 8 names the kinds of memory, and lesson 9 puts instibrain in these words.

  1. 1The context windowEverything the model reads in one call, in order; the middle counts least, and a full window rots.
  2. 2Priming and sycophancySix things decide what a line in the window is worth; the first lines set the tone, and a push with no new fact bends it.
  3. 3Tools and the agent loopThe model writes a call, a program runs it and calls the model again; MCP brings the tools to every AI app.
  4. 4Subagents and orchestrationA task in a window of its own; code or the model picks the next step; checks around the loop.
  5. 5Prompt injectionThe model reads an order and a poisoned page the same way; six ways it arrives, and the lethal trifecta.
  6. 6What works against injectionWords in the prompt help a little; less reach, a person's yes and nowhere to send data hold.
  7. 7Evals and the golden setYour own questions with their right answers, five ways an answer lands, and a judge before it goes out.
  8. 8The kinds of memoryIdentity, procedures, knowledge, events and data: semantic, procedural and episodic memory, and the environment.
  9. 9instibrain in these wordsContext window, retrieval, agentic, structure: where each word of the series sits in one brain.
what you learned

The map: every word, in its place.

The context window is what the model reads. Tools let it act, checks keep it safe, a test says it works, and the kinds of memory say what goes in. Retrieval is in RAG; what a token costs is in AI hygiene.

WhereThe wordsLesson
The context windowcontext, lost in the middle, context rot, compaction, context engineering, progressive disclosure1
A line's worthinstruction hierarchy, hard and soft constraint, priming, sentiment, sycophancy2
Toolstool use, function calling, tool result, agent loop, MCP3
Orchestrationsubagent, workflow, agentic, guardrails, sandbox, human in the loop4
The attackprompt injection, jailbreak, tool poisoning, memory poisoning, exfiltration, lethal trifecta5
The defenceleast privilege, allowlist, taint tracking, defence in depth, red teaming6
The testbenchmark, golden set, abstention, hallucination, grounding, regression, live judge7
Memoryworking memory, semantic memory, procedural memory, episodic memory, environment8
The stackcontext window, retrieval, agentic search, structure, curation, long context9