Tutorials 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.
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials Use OpenAI's new 12-hour prompt cache for stable context, 30 minutes for the rest.
Tutorials TanStack AI hit 1.0. Build an agent whose refund tool pauses for approval, edits and denials.
Tutorials Use Argon's background long decode to generate 1M tokens of output, with cost math.
Tutorials Build an out-of-model tool broker in Python: per-agent identity, scoped policy, tamper-evident logs.
Tutorials Build a Python egress gate that stops the four workarounds Anthropic saw Claude use on live sites.
Tutorials Use /v1/decisions as a $0.10 guardrail, then sweep thresholds and escalate only the unsure band.
Tutorials Build an effort-routing tool-loop client for Beam's OpenAI-compatible API and size the self-host bill.
Tutorials Run a durable Codex-powered agent in OpenAI's hosted sandbox with a custom tool and file outputs.
Tutorials Drive a real browser with GPT-6.1 Sol's batched computer tool, with guardrails.
Tutorials An OpenAI agent used DNS to reach the internet. Build an allowlist resolver and kill switch that catches it.
Tutorials Forced tool use now 400s on Claude Sonnet 5.5. Replace it with strict tools and a retry guard.
Tutorials Build a store=false Grok 4.7 tool agent that keeps its reasoning, hits cache, and escalates effort.