Tutorials Intermediate
DeepSeek V4-Flash: Fix the reasoning_content 400 Trap
Build a thinking-mode tool-calling agent on DeepSeek V4-Flash-0731 without the 400 error.
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
Gemini 3.6 Flash: Cut Agent Tokens With thinking_level
Build a token-thrifty tool-calling agent on Gemini 3.6 Flash using the new thinking_level control.
10 min read·Kodetra Technologies
13d ago
Tutorials Intermediate
GPT-5.6 Persisted Reasoning: Reuse Thinking Across Turns
Use reasoning.context to reuse GPT-5.6's chain of thought across turns and cut redundant tokens.
9 min read·Kodetra Technologies
19d ago
Machine Learning Advanced
TRACE: Train Agents on Their Own Failures With GRPO
Diagnose an agent's missing skills, then train targeted, routed LoRA adapters with GRPO.
10 min read·Kodetra Technologies
21d ago
Tutorials Intermediate
Claude Sonnet 5: Adaptive Thinking and Effort in Python
Master Sonnet 5's on-by-default thinking and the effort knob to cut cost and latency.
9 min read·Kodetra Technologies
Jul 1
Tutorials Intermediate
Migrate to Claude Sonnet 5: Effort and the Tokenizer Trap
Hands-on Python guide to Sonnet 5's adaptive thinking, effort levels, and the 30% tokenizer trap.
10 min read·Kodetra Technologies
Jul 1
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
Jun 27
Tutorials Intermediate
Gemini Thought Summaries: Audit Deep Think Reasoning
Surface, stream, and log Gemini 2.5 Pro Deep Think's reasoning chain with thought summaries.
10 min read·Kodetra Technologies
Jun 26
Tutorials Intermediate
GLM-5.2 Open Weights: Route Reasoning Effort by Task
Build a cost-aware GLM-5.2 agent that routes thinking effort per task and calls tools.
9 min read·Kodetra Technologies
Jun 19
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
Jun 15
Tutorials Intermediate
Kimi K2 Thinking: Agentic Tool Loops in Python
Build a multi-step tool-calling agent on Moonshot's open-weight Kimi K2.6 model.
8 min read·Kodetra Technologies
Jun 6
Tutorials Intermediate
MAI-Thinking-1 Hands-On: Build a Reasoning Agent
Deploy Microsoft's new reasoning model and build a tool-calling triage agent.
10 min read·Kodetra Technologies
Jun 4Page 1 of 2