Machine Learning Intermediate
Small CNN vs Frontier LLMs: Run a Fair Head-to-Head
Fine-tune Inception v3, query a vision LLM, and compare both at a matched threshold.
11 min read·Kodetra Technologies
13d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Machine Learning 
Tutorials Intermediate
OpenAI 12h Cache: Split Agent Prompts Into Two TTLs
Use OpenAI's new 12-hour prompt cache for stable context, 30 minutes for the rest.
9 min read·Kodetra Technologies
13d ago
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
27d ago
Tutorials Intermediate
Agent Tool Broker: Identity, Audit Log, Kill Switch
Build an out-of-model tool broker in Python: per-agent identity, scoped policy, tamper-evident logs.
10 min read·Kodetra Technologies
28d ago
Tutorials Intermediate
Blocked Is an Alert: Egress Gates for Claude Agents
Build a Python egress gate that stops the four workarounds Anthropic saw Claude use on live sites.
12 min read·Kodetra Technologies
28d ago
Tutorials Intermediate
OpenAI Decisions API: Calibrate Thresholds on Labeled Data
Use /v1/decisions as a $0.10 guardrail, then sweep thresholds and escalate only the unsure band.
11 min read·Kodetra Technologies
Oct 9
Tutorials Intermediate
GPT-6.1 Sol Computer Use: Build a Browser Agent
Drive a real browser with GPT-6.1 Sol's batched computer tool, with guardrails.
8 min read·Kodetra Technologies
Sep 30
Tutorials Intermediate
Agent DNS Escape: Build a Tunnel Detector in Python
An OpenAI agent used DNS to reach the internet. Build an allowlist resolver and kill switch that catches it.
10 min read·Kodetra Technologies
Sep 29
Tutorials Intermediate
Sonnet 5.5 Drops tool_choice: Build a Strict Tool Router
Forced tool use now 400s on Claude Sonnet 5.5. Replace it with strict tools and a retry guard.
9 min read·Kodetra Technologies
Sep 28
Tutorials Intermediate
Opus 5.5 Upgrade: Fix 4 Breaking Changes Before They 400
Opus 5.5 is 20% cheaper, but old thinking, tool_choice and computer-use code now fails. Fix it.
15 min read·Kodetra Technologies
Sep 23
Tutorials Intermediate
GPT-6 Astra: Change Reasoning Effort Without Losing Cache
Use configuration_update to raise or lower Astra's reasoning effort mid-chat and keep cache hits.
11 min read·Kodetra Technologies
Sep 7
Tutorials Intermediate
Async Tool Calls: Stop Your Agent Blocking on Slow APIs
Use async tool calls and a wait tool to keep your agent reasoning while tools run.
12 min read·Kodetra Technologies
Sep 7Page 1 of 6