glossary
Plain-English definitions of every term in the Frenchie docs and marketing pages. Useful if MCP, sync vs async, or skill packs are new to you — and useful for your agent if it's asked "what does X mean?"
Model Context Protocol — the open standard for how AI agents discover and call external tools. Frenchie ships as an MCP server so any MCP-compatible agent (Claude Code, Cursor, Codex, Antigravity, Claude Desktop, and others) can call OCR, transcription, Office/spreadsheet extraction, and image generation through one consistent interface.
A program that exposes a set of tools and resources to an AI agent over the Model Context Protocol. Frenchie runs in two modes: a local stdio MCP server installed via npx for desktop agents, and an HTTP MCP endpoint at mcp.getfrenchie.dev for hosted/web agents.
Frenchie's structured workflow for AI-assisted product development from requirement to release. It helps agents and humans work through requirements, test cases, implementation plans, reviews, security checks, release-check output, and cleanup with shared artifacts.
A workflow where important decisions and outputs are written to durable files instead of staying only in chat. Frenchie Method stores feature artifacts under .frenchie/docs/feature/[feature-name]/ so another agent, teammate, or later session can continue from the same trail.
A workflow where agent implementation happens in isolated git worktrees by default. This keeps parallel tasks separate, preserves the user's main checkout, and makes setup, review, and cleanup explicit.
A Frenchie Method readiness step that reports what is ready, risky, missing, and worth double-checking before release. It does not merge or release; release actions require an explicit user request and approval.
The repeatable path an AI agent follows with a human and a repository: clarify the requirement, write artifacts, define tests, plan, implement, verify, review, and prepare release readiness without hiding decisions in chat.
The Frenchie Method rule that test cases come before implementation plans. Acceptance criteria define what must be true; test cases define how the team proves it before the agent plans or edits code.
MCP transport where the agent spawns the server as a local subprocess and communicates over stdin/stdout JSON-RPC. Frenchie's primary integration path. Auto-saves results to .frenchie/<name>/ next to the source file because the server runs on the same machine.
MCP transport where the agent calls a remote HTTP endpoint. Frenchie's hosted/web fallback at mcp.getfrenchie.dev — used when the agent can't spawn local binaries (Lovable, Manus, Claude.ai, ChatGPT.com). Requires the upload → reference flow because the server has no access to local files.
Optical Character Recognition — converting PDFs and images into machine-readable text. Frenchie returns clean Markdown with table structure preserved and figures pulled out as separate PNG files. 1 credit per page. Supported formats: PDF, PNG, JPG, WebP.
Converting audio or video into text. Frenchie returns Markdown transcripts with paragraph structure. 2 credits per minute. Supported formats: MP3, M4A, WAV, MP4, MOV, WebM. 50+ languages including Thai, Japanese, Chinese, Arabic, French, Spanish.
A focused file-reading layer that turns a source file into Markdown without deciding what the content means. In Frenchie, extractors cover Office and spreadsheet files for agent workflows while the agent handles summarization, analysis, field extraction, or follow-up writing.
Frenchie's MCP tool for extracting DOCX, XLSX, CSV, TSV, and PPTX files into Markdown. It is built for agent handoffs: file in, Markdown out, no long-term file storage, no RAG layer, and no document-intelligence dashboard.
Producing an image file from a text prompt. Frenchie generates one image per call through Frenchie Kit. 20 credits per image. Output formats: PNG (default), JPEG, WebP. Sizes: 1024x1024, 1536x1024, 1024x1536, or auto. Rate limit: 50 images per hour, 250 per day per user.
A free installable bundle that teaches an agent how to use Frenchie's MCP tools. Ships slash commands like /ocr, /transcribe, /generate-image, and /frenchie-status. Distributed via the @lab94/frenchie npm package — install with `npx @lab94/frenchie install`.
Frenchie's routing for small jobs that complete inline — typically OCR on short PDFs and short audio transcription. The MCP tool call returns the result in one response, no polling. Anything large enough to take more than a few seconds is routed to the async path automatically.
Frenchie's routing for jobs too large to complete inline — long audio, big PDFs. The MCP tool returns a job ID immediately; the agent polls with `get_job_result` (or waits for a smart-wait window of up to 90 seconds). Lets your agent keep working on other things while the job runs.
Frenchie's billing unit. $1 buys 100 credits. 1 credit per OCR page, 2 credits per transcription minute, 20 credits per generated image. 100 free credits on signup, no card required. Credits don't expire and refund automatically when a job fails.
Frenchie deletes processed files immediately and expires the result payload 30 minutes after first delivery. By design — Frenchie is a processing utility, not a storage product. Agents that need to revisit a result should save the Markdown locally before the window closes.
Every Frenchie capability returns the same envelope: `{ status, jobId, creditsUsed, resultExpiresAt, result: { kind: 'markdown' | 'image', ... } }`. Agents branch on `result.kind` instead of guessing per-tool output shape. Introduced in v0.4.0 alongside image generation.
An agent with first-class auto-install support: the `npx @lab94/frenchie install` command auto-detects the agent and writes the right MCP config. Currently: Claude Code, Cursor, Codex, Antigravity, and Claude Desktop. Other MCP clients work too via `--agent <name>`.
