Tutorials Gemini 3.8 Live: Build a Multilingual Voice Agent
Build a real-time voice agent with Gemini 3.8 Live Extended Thinking.
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials Build a real-time voice agent with Gemini 3.8 Live Extended Thinking.
Tutorials Opus 5.5 moved agent narration into thinking blocks. Stream it back with display updates and nudges.
Tutorials Opus 5.5 is 20% cheaper, but old thinking, tool_choice and computer-use code now fails. Fix it.
Tutorials Qwen keeps reasoning across every turn by default. Exploit it, or pay for it.
Tutorials Preflight your configs for gemini-3.7-flash: 5 breaking changes, a validator, real cost math.
Tutorials Build a thinking-mode tool-calling agent on DeepSeek V4-Flash-0731 without the 400 error.
Tutorials Route each task to the right Claude Opus 5 effort level and cut your token bill.
Tutorials Build a token-thrifty tool-calling agent on Gemini 3.6 Flash using the new thinking_level control.
Tutorials Use reasoning.context to reuse GPT-5.6's chain of thought across turns and cut redundant tokens.
Tutorials Master Sonnet 5's on-by-default thinking and the effort knob to cut cost and latency.
Tutorials Hands-on Python guide to Sonnet 5's adaptive thinking, effort levels, and the 30% tokenizer trap.
Tutorials Stream Gemini's thought summaries live, control reasoning effort, and track thinking-token cost.