foundr.companyby Perea

foundr.study — full features

Drop in any source. Get an agent-led course that ends in a working artifact. Skim, learn, or build — your call. MCP-first so the course meets you in your IDE.

Pricing

Free via X. Solo at indie prices. Pro when you scale.

Same pricing model across the whole foundr.* family. No per-seat math. No enterprise quote theater.

What you get

Every feature, grouped by who it's for.

Core

  • Ingest PDF, GitHub repo URL, docs URL, raw text, YouTube transcript
  • Auto-generated lesson plan with learning objectives per module
  • Inline quizzes (MCQ + open-ended) with Socratic feedback
  • Code labs — runnable sandbox per lab, agent watches you work
  • Progress tracking + resume-where-you-left-off
  • Source citations on every claim (anti-hallucination)
  • Adaptive depth toggle — skim (10min) / learn (30min) / build (2hr)
  • Final artifact — deployable repo, blog post, or working script

Agentic-first (MCP + token)

  • study_create(source, depth) — spin up a course from any URL or file
  • study_advance(course_id) — agent walks the learner to the next lesson
  • study_check(course_id, response) — agent grades + adapts the next step
  • study_artifact(course_id) — emit the final buildable artifact
  • study_library(scope) — list a founder's (or team's) courses

Solo-founder-shaped

  • "Fits a 30-min lunch" preset — every course compresses to one sitting
  • Learn-then-build pairing — no theory without a ship target
  • No certificates, no streaks, no gamified shame
  • Public share links — show what you learned, not a badge
  • Pause / resume across foundr.* tabs (state lives in Founder World)

Agentic-first

The MCP surface your agents call.

Add it once to Claude, Cursor, or any MCP host. Your bearer token unlocks every tier — no dashboard required.

# Install the server (one line, one time)
claude mcp add --transport http foundr-study https://foundr-study.foundr.company/api/mcp

Why this differs

The angles the incumbents won't ship.

  • 01

    Agent-led code labs, not just chat. Every lesson ends in a runnable artifact the agent built with you.

  • 02

    Ingest a GitHub repo, not just PDFs. Directly addresses "learn this framework I just pulled."

  • 03

    Adaptive depth — skim / learn / build. Explicit user-selected gear, not one tutor style.

  • 04

    Every course ends in a working artifact. The artifact IS the assessment — no certificates.

  • 05

    MCP-first. Learn inside your dev loop, not in a separate tab.

Competitive landscape

Who's already here, and what they leave on the table.

Honest comparison. We do not pretend the space is empty.

Pick a source. Start learning.

Quote-tweet @perea_ai. Drop in one PDF or repo. Your first agent-led course is ready in 60 seconds — and ends with a working artifact.