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
Jun 25Guides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
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
Jun 16
Tutorials Intermediate
Gemini 3.5 Flash: Combine Search, Code & Functions
Mix Google Search, code execution, and custom functions in one Gemini 3.5 Flash request.
10 min read·Kodetra Technologies
Jun 8
Tutorials Intermediate
Agent Harness in Python: Give LLMs Shell and File Access
Build a safe local agent harness with shell, files, approvals, and logs in Python.
10 min read·Kodetra Technologies
Jun 3
Tutorials Intermediate
Gemini Code Execution: Build a Self-Fixing Analyst
Use Gemini 3.5 Flash code execution to write Python that fixes itself in a loop.
10 min read·Kodetra Technologies
May 28
Tutorials Intermediate
Gemini Managed Agents: One Call to a Cloud Sandbox
Spin up a sandboxed AI agent that writes, runs, and ships code with one Gemini API call.
9 min read·Kodetra Technologies
May 26
Tutorials Intermediate
Pydantic AI 1.85: Type-Safe Agents That Survive Crashes
Type-safe AI agents in Python with durable execution, retries, and validated outputs.
4 min read·Kodetra Technologies
Apr 28