AI Agent Guides & Workflow Tutorials

Practical, step-by-step instructions for getting real recurring work done with an AI assistant - without touching code, servers, or workflow builders.

  1. 61
    Guide No Endpoints Found for OpenAI Batch Models

    OpenRouter removed 35 OpenAI :batch model IDs on Aug 26, 2026. Why you get no endpoints found for openai batch, and three ways to keep the 50% off.

    August 28, 2026 · 9 min read
  2. 62
    Guide ChatGPT Ads India: Who Sees Them, How to Stop

    ChatGPT ads India rollout: OpenAI now shows sponsored units to Free and Go users. Who sees ads, who stays ad-free, and the two ways to switch them off.

    August 28, 2026 · 9 min read
  3. 63
    Guide What Is GLM-5.3-Flash? Specs and Price

    GLM-5.3-Flash is Z.ai's first natively multimodal model: 320B total and 18B active, MIT weights, and a ninth of GLM-5.3's price. Specs, scores, costs.

    August 27, 2026 · 11 min read
  4. 64
    Guide How Lindy AI Memory Works With Files & Skills

    How Lindy AI memory works next to files and skills, what belongs in each layer, and how to word a correction so it survives the next scheduled run.

    August 27, 2026 · 8 min read
  5. 65
    Guide Kimi K2.5 Deprecated: Every Date That Matters

    Kimi K2.5 deprecated on five platforms, on five different dates. Moonshot sunsets Aug 31, 2026; Azure holds to 2027. What breaks, when, and where to move.

    August 25, 2026 · 9 min read
  6. 66
    Guide AI Document Automation: What Really Needs AI?

    Learn how AI document automation uses OCR, IDP, rules, document generation, human review, and agents, and how to choose the right layer for each step.

    August 24, 2026 · 10 min read
  7. 67
    Guide AI Business Process Automation, Step by Step

    Learn how AI business process automation improves workflows by removing waste, keeping rules where they fit, and using AI only where interpretation is needed.

    August 24, 2026 · 12 min read
  8. 68
    Guide AI Token Consumption: Count It, Then Cut It

    Learn what AI token consumption includes across prompts, files, tools, retries, and model calls, and how to reduce cost without weakening the result.

    August 24, 2026 · 10 min read
  9. 69
    Guide Ox Alpha Was GLM-5.3-Flash

    Ox Alpha, the free stealth model on OpenRouter, was Z.ai's GLM-5.3-Flash. The confirmation, the 3.94T tokens it pulled, and who guessed right.

    August 24, 2026 · 9 min read
  10. 70
    Guide Qwen 3.8 27B Overthinking: Turn Down xhigh

    Qwen 3.8 27B overthinking comes from one shipped default, reasoning_effort=xhigh. Here is what it costs and the exact settings that turn it down.

    August 24, 2026 · 9 min read