Tutorials Intermediate
Gemini Spark Agents: One API Call, One Cloud Sandbox
The Managed Agents API behind Gemini Spark: build a persistent cloud agent in Python.
9 min read·Kodetra Technologies
YesterdayGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
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
2d ago
Tutorials Intermediate
Qwen3.8-Max Tool Calling: A Python Agent Loop
Build a working tool-calling agent on Alibaba's new Qwen3.8-Max using the OpenAI-compatible API.
9 min read·Kodetra Technologies
2d ago
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
3d ago
Tutorials Intermediate
DeepSeek V4-Flash Tool Loop: A Coding Agent for Cents
Build an autonomous file-editing coding agent on DeepSeek V4-Flash's tool-calling API for pennies.
9 min read·Kodetra Technologies
3d ago
Tutorials Intermediate
Auto-Route Claude Refusals by Category on Opus 5
Auto-recover from Claude safety refusals on Opus 5 with one line of code: fallbacks='default'.
8 min read·Kodetra Technologies
8d ago
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
9d ago
Tutorials Advanced
Swap Tools Mid-Chat on Claude Opus 5, Keep the Cache
Add or drop Claude Opus 5 tools between turns without invalidating your prompt cache.
12 min read·Kodetra Technologies
10d ago
Tutorials Intermediate
Opus 5 Effort Router: Auto-Pick Cost vs Capability
Route each task to the right Claude Opus 5 effort level and cut your token bill.
7 min read·Kodetra Technologies
11d ago
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
17d ago
Tutorials Intermediate
Kimi K3 Reasoning Effort: Stream Thoughts, Cut Cost
Tune Kimi K3's low/high/max reasoning effort and stream reasoning_content to control token cost.
9 min read·Kodetra Technologies
17d ago
Tutorials Intermediate
Kimi K3 Dynamic Tool Loading: Inject Tools On Demand
Load tools just-in-time in Kimi K3's agent loop to shrink prompts and sharpen tool choice.
8 min read·Kodetra Technologies
17d agoPage 1 of 9