Advanced curriculum · practical systems
Beyond the Chatbox
A technical curriculum for building persistent, stateful, and autonomous AI systems. Transition from stateless queries to high-efficiency agentic workflows.
Five modules, each a working technique rather than a definition. If you are new to any of this, start with Phase 1 and come back — this page assumes you already know what a token is.
Procedural Memory: Agent Skills
Stop using monolithic system prompts. Agent Skills provide a modular framework for injecting procedural knowledge—how to perform specific tasks—without bloating the context window.
Progressive Disclosure
The agent doesn't load everything at once. It indexes metadata first, then loads the body only when a semantic match occurs.
Step through the three stages and watch the file on the right change:
--- name: pdf-handler description: Extracts text and tables from PDFs, fills forms, and merges files. allowed-tools: [shell, python] --- # Procedure 1. Analyze the PDF structure. 2. If encrypted, request user passphrase. 3. Utilize the Python `PyPDF2` library...
The Memory Bank
LLMs are stateless. The Memory Bank pattern creates a persistent "external brain" using hierarchical Markdown files, reducing redundant explanations by 23%.
Click a file to explore its role
Understand how temporal state is orchestrated across sessions.
Project Root
File Content Focus
Select a file from the explorer
Computational Economics
Agents resend their whole context on every step, so a long loop pays for the same tokens dozens of times. Caching the stable prefix is the single largest lever on that bill — and the one most teams never pull.
The Power of Prefix Caching
Prompt caching reduces latency by 85% and slashes input costs by 90% by storing Key-Value (KV) tensors. Success depends on placing static data at the absolute beginning of the prompt.
Cache Architecture Comparison
Compression & Model Strategy
Managing token exhaustion and choosing the right compute tier.
When to use SLMs?
- • Routine document classification
- • Tool call JSON generation
- • Local RAG embeddings
- • Edge/Mobile environments
Rolling Summary
Uses a cheaper LLM to generate prose summaries of old logs.
LOSS RATIO: MEDIUMAnchored Incremental
Maintains a structured JSON document, only updating with new facts.
LOSS RATIO: LOWKompact Proxy
Middleware that uses 8 adaptive transforms to strip syntax.
COST SAVING: 40-70%The Perfect Agent Lifecycle
Every module above, assembled into one loop. Read it as the order things happen in, not a list of features.
Initialize with cached Memory Bank files → Index metadata → Load required Skills → Run loop with incremental summarization → Externalize state to Memory Bank → End.