Playbooks
Tutorials
Long-form guides optimized for engineers shipping GenAI features responsibly.
11 min read
Route Tickets with TypeSafe Jev
Start TypeSafe Jev: waitlist key, jev-latest, Choice/Score/Noul, a first System One POST, and why this is not JSON-mode GPT.
10 min read
Call Gemini 3.8 Flash in the Gemini API
Start with Gemini 3.8 Flash: model code gemini-3.8-flash, 1M context, thinking levels, intro pricing, and when to use Live or Antigravity instead.
12 min read
Start a Gemini 3.8 Live Voice Session
Stand up Gemini 3.8 Live on the Live API: pick gemini-3.8-live or Extended Thinking, connect with the GenAI SDK, stream PCM, and migrate off 3.1 Flash Live.
12 min read
Build a RAG Pipeline with Citations
Build a retrieval-augmented generation pipeline that returns answers with citations: ingest, chunk, retrieve, generate, and evaluate using official LangChain, LlamaIndex, or OpenAI file-search docs.
9 min read
Pick a Coding Agent: Codex, Claude Code, or Antigravity
Choose among OpenAI Codex, Claude Code, and Google Antigravity using official product jobs, then open the matching comparison page.
11 min read
Build a Voice Session with GPT-Live-1
Stand up an OpenAI GPT-Live-1 session: full-duplex voice, $0.05/min billing, backend delegation, and when to use Gemini 3.8 Live or ASR instead.
10 min read
Use ChatGPT Sites from a Prompt
Turn a ChatGPT prompt or local project into a hosted website with Sites: @Sites, save vs deploy, sharing, D1/R2, and public-beta limits.
11 min read
Evaluate Sarvam 105B for Indic Language RAG
Build a practical evaluation loop for Indic and code-mixed RAG with Sarvam 105B: corpus design, chat API checks, 30B routing, and comparison against your quality bar.
9 min read
Choose Daybreak Blue or Red: GPT-5.6 Sol vs GPT-5.6-Cyber
A decision checklist for OpenAI Daybreak Blue (GPT-5.6 Sol) versus Daybreak Red (GPT-5.6-Cyber): access tiers, approved scope, governance, and when not to escalate.
14 min read
Local Coding Model Bake-off: Muse Glimmer 30B vs Qwen3.6-27B
Run a fair local bake-off between Muse Glimmer 30B and Qwen3.6-27B for coding agents: hardware envelopes, shared tasks, safety gates, and when to pick each model.
12 min read
Build a Local Agent with Muse Glimmer 30B
Go beyond loading weights: design a local Muse Glimmer agent with tool permissions, failure recovery, multimodal inputs, and a safety checklist—after you can run the GGUF.
10 min read
Run Muse Glimmer 30B Locally with llama.cpp
Download Meta's official Muse Glimmer GGUF artifacts, choose a 24 GB or 32 GB quantization, add image input, and validate a local agent safely.
10 min read
Run Stable Diffusion XL with Diffusers
Run the SDXL 1.0 base checkpoint with Diffusers, run the optional two-stage refiner, manage constrained GPU memory, and benchmark the exact pipeline safely.
10 min read
Amazon Bedrock Converse API with Boto3
Build a production-ready Amazon Bedrock chat integration with Converse and ConverseStream, IAM permissions, model IDs, retries, and observability.
11 min read
Build Indian-Language LLM Apps with Sarvam AI
A practical guide to choosing Sarvam 30B vs Sarvam 105B, handling code-mixed Indian-language input, and evaluating Sarvam LLMs for production apps.
10 min read
Structured Outputs vs JSON Mode in Production
When to use Structured Outputs instead of JSON mode, when TypeSafe Jev is a different job, and how to validate schema-constrained responses in production.
10 min read
Computer-Use Agent Sandboxing Checklist
A production checklist for running computer-use agents in isolated desktops or browsers with safer permissions and approval gates.
8 min read
Prompt Caching for Agent Workflows
How to use prompt caching to reduce latency and cost when agents reuse long system prompts, tools, documents, and examples.
10 min read
A2A vs MCP for Agent Integrations
A clear comparison of Agent2Agent (A2A) and Model Context Protocol (MCP), including when to use each in multi-agent systems.
9 min read
Claude XML Tags for Long-Context Prompts
How to use Claude XML tags to structure instructions, examples, documents, sources, and user input in long-context prompts.
11 min read
Agentjacking Defense Checklist for AI Agents
A practical checklist for defending AI agents against agentjacking, indirect prompt injection, unsafe tool calls, and computer-use hijacking.
12 min read
Synthetic Data Generation for Classifier Fine-Tunes in Legal AI Applications
This tutorial provides a comprehensive guide to generating synthetic data for training classifiers in legal AI applications, focusing on improving model performance and reducing bias. Prerequisites include knowledge of machine learning and legal domain concepts.
16 min read
Quantization Impact on Retrieval Quality in Financial Services
This tutorial examines the effects of quantization on retrieval quality in financial data systems. Prerequisites include knowledge of machine learning and data retrieval concepts.
18 min read
Hybrid Search: BM25 + Dense Re-Ranking for Academic Research
This tutorial explores the integration of BM25 and dense re-ranking for enhancing academic search engines. Familiarity with information retrieval concepts is required.