Doubleword
    Back to home

    Workbooks

    Real examples with real costs. Each workbook links to runnable code.

    Example What It Does Cost Key Insight
    Async Agents Deep research with recursive agent trees $0.34 for 47 agents Async SLA enables multi-round agentic workflows
    Synthetic Data Generation Generate training data with quality filtering $3.21 for 10K samples 3-stage pipeline in 3 hours, not 3 days
    Data Processing Pipelines Clean and enrich messy records $0.80 for 50K records LLM-powered normalization at pipeline scale
    Embeddings Semantic search over document corpus $0.03 for 1.6M tokens 70% cheaper than OpenAI for same quality
    Async Evals Grade LLM outputs with a frontier judge model $0.50 for 817 answers + judgements Rigorous evals as a background batch, not a hot-path cost
    LangSmith Evals at Scale Run LangSmith LLM-as-judge evals via Doubleword's batch API $8.82 for 10K evals 97% cheaper than GPT-5.5 real-time, zero 429 errors
    Bug Detection Ensemble Classify security vulnerabilities $0.40 for 4,642 samples Run twice for calibration, still under $1
    Dataset Labelling Build company datasets via search + LLM $1.05 for 188 companies 100% recall vs Gartner Magic Quadrant
    Structured Extraction Extract fields from scanned receipts $0.12 for 626 receipts Qwen3-30B beats GPT-5.2 at 1/12th cost
    Image Summarization Caption images for social media $0.10 for 1,000 images Vision batch makes captioning automatic
    AI Personal Assistants Always-on agents with background inference $0.80 for ~4M tokens/mo Background tasks at 4x lower cost than real-time
    Asynchronous Event Listeners Process events asynchronously at scale $0.15 for 10K events Decouple event handling from request paths
    ETL & Pipeline Sanitization Sanitize and transform data in ETL pipelines $0.50 for 100K records LLM-powered sanitization catches what regex misses
    Deep Research Recursive research agents over the web $0.34 for 47 agents Async SLA enables multi-round deep research
    Long Running Agents Agents that run for hours, not seconds $1.20 for 8h run Background inference unlocks long-horizon agents
    OpenClaw Open-source computer-use agent at batch cost $0.60 for 1K actions Computer use without real-time premiums