Iteration Layer

For Agents

Guides, tutorials, and real-world workflows for composable document and image processing.

Treat the LLM as a Document Worker, Not the Workflow Owner

LLMs are useful inside document workflows, but they should not own intake, state, validation, generated outputs, or customer-facing decisions.

9 min read

MCP vs REST APIs: When Agents Should Call Tools and When Your Code Should

A practical guide to choosing MCP or REST APIs for AI workflows, production pipelines, prototyping, authentication, and operational control.

9 min read

RAG from Public Documentation Websites: Robots.txt, Terms, Retention, and Attribution

Public docs are tempting RAG sources. Before you ingest them, review robots.txt, terms, source attribution, retention, and update strategy.

16 min read

Building AI Agents That Process Documents: MCP, Structured I/O, and Confidence Routing

Build an AI agent pipeline that extracts document data, evaluates confidence scores, and routes to report generation or human review — using MCP and composable APIs.

12 min read

Document-to-Markdown for RAG: Preparing Documents for Your AI Knowledge Base

Why markdown is the ideal format for LLM ingestion, how to preserve tables and layouts from PDFs, and how to build a document ingestion pipeline for RAG.

21 min read

Read Any Document From Claude Code or Cursor — PDF, DOCX, Scans, Images via MCP

Use MCP to convert PDFs, scanned documents, Word files, and images to readable markdown directly from Claude Code or Cursor without custom preprocessing code.

7 min read

One Conversation, One Composable Content Pipeline

When document extraction, image processing, and generation are MCP tools in your AI assistant, the workflow changes fundamentally.

8 min read

Process Images From Your Coding Session — Smart Crop, Convert, Compress via MCP

Use MCP to resize, smart crop, convert, and compress images directly from Claude Code or Cursor. Chain supported operations without leaving your editor.

7 min read

Compose Branded Graphics from Your AI Assistant — No Design Tools Required

Use MCP to compose layered images, social cards, and branded graphics directly from Claude Code or Cursor. Describe the layout, get the image.

9 min read

Chain Document Extraction, Image Processing, and Generation in a Single Claude Code Session

Use MCP to chain Iteration Layer APIs inside Claude Code or Cursor — extract data from documents, process images, and generate new outputs in one conversation.

9 min read

Parse Documents Inside Claude and Cursor with MCP — No Code Required

Use MCP to parse invoices, contracts, and receipts directly from Claude Desktop or Cursor. No code, no server, no pipeline.

9 min read

Generate PDFs and Word Documents Inside Claude Code and Cursor with MCP

Use MCP to generate PDFs, DOCX, EPUB, and PPTX documents directly from Claude Code or Cursor. No templates, no code, no pipeline.

9 min read