Tutorials Intermediate
Gemini 4 Argon Long Decode: 200K Tokens, One Request
Use Argon's background long decode to generate 1M tokens of output, with cost math.
9 min read·Kodetra Technologies
8d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
Tutorials Intermediate
Mistral Large 4 Preview: Canary-Test Silent Model Updates
Mistral Large 4's preview can change without notice. Build a Python canary suite that catches it.
11 min read·Kodetra Technologies
15d ago
Tutorials Intermediate
OpenAI Agents API: Run a Data Audit in a Cloud Sandbox
Run a durable Codex-powered agent in OpenAI's hosted sandbox with a custom tool and file outputs.
14 min read·Kodetra Technologies
21d ago
Tutorials Intermediate
GPT-6 Luna First, Sol on Demand: A Python Cascade
Send GPT-6 requests to Luna, validate the JSON, and pay Sol prices only when the checks fail.
13 min read·Kodetra Technologies
28d ago
Tutorials Intermediate
DeepSeek V4-Flash KV Cache: Cut Input Costs 50x
Structure prompts so DeepSeek's disk cache hits, and pay ~50x less on repeated input tokens.
9 min read·Kodetra Technologies
Aug 5
Tutorials Intermediate
Guaranteed JSON From Claude: Structured Outputs in Python
Force Claude to return schema-valid JSON every time, no parsing errors and no retries.
9 min read·Kodetra Technologies
Jul 29
Tutorials Intermediate
Kimi K3 Partial Mode: Prefill Replies to Force Output
Prefill Kimi K3's assistant turn to lock output shape, force clean JSON, and steer tone.
9 min read·Kodetra Technologies
Jul 21
Tutorials Intermediate
Kimi K3 Vision: Extract Structured Data From PDFs in Python
Use Kimi K3's native vision and JSON schema output to turn messy PDF pages into clean, typed data.
9 min read·Kodetra Technologies
Jul 18
Tutorials Intermediate
Prompt Cache Retention: Cut OpenAI Bills Up to 90%
Structure prompts, set prompt_cache_retention, and read cached_tokens to slash GPT-5.6 input costs.
8 min read·Kodetra Technologies
Jul 11
Machine Learning Advanced
Read an LLM's Mind: Probe Hidden Thoughts Like J-Space
Train a linear probe on hidden activations and steer output, the method behind Anthropic's J-Lens.
9 min read·Kodetra Technologies
Jul 7
Tutorials Intermediate
Pydantic AI: Type-Safe Agents You Can Unit Test
Build agents with typed deps, validated output, and offline tests using Pydantic AI.
9 min read·Kodetra Technologies
Jun 24
Tutorials Intermediate
Claude Opus 4.8 Fast Mode: 2.5x Faster Output in Python
Use speed:"fast" on Claude Opus 4.8 for up to 2.5x faster output, with a safe rate-limit fallback.
9 min read·Kodetra Technologies
Jun 10Page 1 of 2