Tutorials Intermediate
Build an LLM Spend Governor: Budget Caps in Python
A runnable Python governor that caps LLM spend per user and auto-downgrades models.
10 min read·Kodetra Technologies
TodayGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
Tutorials Intermediate
Stream Gemini Thinking: Build a Show-Your-Work CLI
Stream Gemini's thought summaries live, control reasoning effort, and track thinking-token cost.
8 min read·Kodetra Technologies
3d ago
Tutorials Intermediate
Code Mode for MCP: Let Claude Write Code to Call Tools
Cut MCP agent context up to 99% by exposing tools as a code API the model calls in code.
9 min read·Kodetra Technologies
4d ago
Tutorials Intermediate
Mercury 2 dLLM: Reasoning at 1000 Tokens Per Second
Build real-time agents on the first reasoning diffusion LLM: OpenAI-compatible, 1000 tok/s.
8 min read·Kodetra Technologies
11d ago
Tutorials Intermediate
Loop Engineering: From Prompts to Verified Agent Loops
Build a plan-act-verify agent loop with an external check, retry budget, and clear stop rules.
9 min read·Kodetra Technologies
12d ago
Tutorials Intermediate
Fable 5 Prompt Caching: Slash 1M-Token Codebase Costs
Reuse a huge codebase prefix across every Fable 5 call and pay ~90% less.
8 min read·Kodetra Technologies
13d ago
Tutorials Intermediate
Claude Programmatic Tool Calling: Cut Agent Token Costs
Let Claude write code that calls your tools in a loop — 20–40% fewer tokens, same accuracy.
10 min read·Kodetra Technologies
13d ago
Tutorials Intermediate
Fable 5 Effort: Cut Thinking Token Costs in Python
Claude Fable 5 always thinks. Use effort, display and max_tokens to control reasoning cost.
9 min read·Kodetra Technologies
14d ago
Tutorials Intermediate
DeepSeek V4 Pro: Cheap 1M-Token Context in Python
Use DeepSeek V4 Pro's auto KV cache to run huge-context jobs for cents.
8 min read·Kodetra Technologies
17d ago
Tutorials Intermediate
MiniMax M3: Master 1M-Token Long Context With MSA
MiniMax M3 hands-on: MSA sparse attention plus real 1M-token long context, with runnable Python.
10 min read·Kodetra Technologies
17d ago
Tutorials Intermediate
Claude Opus 4.8 Effort Levels: A Hands-On Python Guide
Tune token spend on Opus 4.8 with the effort parameter. Runnable Python, real I/O, real numbers.
7 min read·Kodetra Technologies
28d ago
Security Advanced
How to Secure an MCP Server Against Tool Poisoning
Harden MCP servers: kill tool poisoning, validate tokens, sandbox tools
9 min read·Kodetra Technologies
May 20Page 1 of 2