Intermediate

Build an Agentic Content Studio: the explanation

A working content studio, Slidesmith Studio, taken apart in illustrated modules. A user describes a topic, picks a LinkedIn carousel or 16:9 slides and a template, and three AI agents (research, content strategist, designer) write a structured deck spec in the user's brand. Code renders it, measures every slide in a headless browser, sends slides that overflow back to the designer, and exports PDF, PNG, ZIP or a single HTML file. The user never sees HTML: they click any text to edit it, switch t

22 parts7h 55mRevised

Overview

Who it is for: anyone who knows a little Python and wants to understand, rebuild or extend a real agentic application with a web front end, from beginners to working engineers. Each module says what to read first.

What you will learn

  • 22 written parts, yours for good
  • 7h 55m of reading, measured not estimated
  • Written for the intermediate level
  • Every future revision included

Curriculum

22 sections · 22 parts · 7h 55m

40 min free to read · 7h 15m with the project

01Start here1 part · 3 min
02Module 0: Project overview: a guided tour of the running app1 part · 17 min
03Module 1: The problem with making carousels by hand1 part · 20 min
04Module 2: The solution: one prompt, three agents, one spec1 part · 21 min
  • Module 2: The solution: one prompt, three agents, one spec21 min
05Module 3: Choosing the model and the infrastructure1 part · 22 min
  • Module 3: Choosing the model and the infrastructure22 min
06Module 4: High-level design1 part · 20 min
  • Module 4: High-level design20 min
07Module 5: Low-level design: data, deck spec, API and events1 part · 24 min
  • Module 5: Low-level design: data, deck spec, API and events24 min
08Module 6: Sign-in, sessions and brand onboarding1 part · 23 min
  • Module 6: Sign-in, sessions and brand onboarding23 min
09Module 7: The deck spec and the templates1 part · 25 min
  • Module 7: The deck spec and the templates25 min
10Module 8: The agent pipeline with LangGraph1 part · 23 min
  • Module 8: The agent pipeline with LangGraph23 min
11Module 9: The research agent and web search1 part · 21 min
  • Module 9: The research agent and web search21 min
12Module 10: The strategist, the designer and JSON repair1 part · 26 min
  • Module 10: The strategist, the designer and JSON repair26 min
13Module 11: Render, measure and repair in Chromium1 part · 24 min
  • Module 11: Render, measure and repair in Chromium24 min
14Module 12: Editing, redo and the editor1 part · 25 min
  • Module 12: Editing, redo and the editor25 min
15Module 13: Background jobs and live progress1 part · 24 min
  • Module 13: Background jobs and live progress24 min
16Module 14: Ideas, dashboard and insights1 part · 24 min
  • Module 14: Ideas, dashboard and insights24 min
17Module 15: Exports: PDF, PNG, ZIP and HTML1 part · 20 min
  • Module 15: Exports: PDF, PNG, ZIP and HTML20 min
18Module 16: Security: sessions, uploads, SSRF and XSS1 part · 24 min
  • Module 16: Security: sessions, uploads, SSRF and XSS24 min
19Module 17: Evaluating the agents1 part · 23 min
  • Module 17: Evaluating the agents23 min
20Module 18: The studio front end1 part · 21 min
  • Module 18: The studio front end21 min
21Module 19: Containers and the local stack1 part · 22 min
  • Module 19: Containers and the local stack22 min
22Module 20: Deploying to Google Cloud with CI/CD1 part · 23 min
  • Module 20: Deploying to Google Cloud with CI/CD23 min
Part 1 · freeBuild an Agentic Content Studio: the explanation · 3 min

A working content studio, Slidesmith Studio, taken apart in illustrated modules. A user describes a topic, picks a LinkedIn carousel or 16:9 slides and a template, and three AI agents (research, content strategist, designer) write a structured deck spec in the user's brand. Code renders it, measures every slide in a headless browser, sends slides that overflow back to the designer, and exports PDF, PNG, ZIP or a single HTML file. The user never sees HTML: they click any text to edit it, switch template or format instantly, or ask the AI to redo one slide. Everything runs on an open-weight model, qwen3.8:27b, on the user's own Mac through Ollama, or on a hosted copy of the same model in the cloud.

Who it is for: anyone who knows a little Python and wants to understand, rebuild or extend a real agentic application with a web front end, from beginners to working engineers. Each module says what to read first.

How each module is laid out

SectionAnswers
Where this fitsthe same system map in every module, with this module's parts highlighted
What it doesthe idea in one picture, then each production practice at a glance: what, why, how, when, where
Use cases and examplesthe same practice in this studio and in other industries
How it worksthe mechanism step by step, one figure per step, with real values
Code tourthe real files, short excerpts, every line explained, concept boxes for new ideas, and a "what happens when" trace
Design decisionswhat was chosen, the alternatives and why, with measured numbers, and when to choose differently
What can go wrongfailures and attacks, how the code handles each, and the test that proves it
Try it yourselfexact commands and what you should see
Check yourself, Key termsa short quiz and a glossary

Source code

The complete, runnable project as one zip: the code the modules explain, with its tests and the files to run and deploy it.

The source code download comes with buying this project.

Submit your build

When the last milestone runs, hand in the repository and three lines about it. That is what the project page will show for you, and what you can send with a job application.

Sign in to submit your build: the repository link and three lines about it.

Reviews

No reviews yet. The first comes from a reader who finishes the project.

to review this project once you have finished it.

Next to this one