llms.txt
Compare with other sites' llms.txt files →# Louis-François Bouchard, aka What's AI
> Making AI accessible through practical AI engineering writing, videos, courses, and consulting.
Louis-François Bouchard writes and teaches practical AI engineering, machine learning, LLMs, AI agents, computer vision, and AI education. This file is a curated entry point for assistants and agents. Canonical HTML URLs remain the source of truth.
## Primary Links
- [Home](https://www.louisbouchard.ai/): Making AI Accessible. Co-founder at Towards AI. Ex-PhD at Mila.
- [Blog](https://www.louisbouchard.ai/blog/): All articles and essays.
- [RSS](https://www.louisbouchard.ai/rss.xml): Fresh posts feed.
- [JSON Feed](https://www.louisbouchard.ai/feed.json): Machine-readable feed.
- [Complete AI index](https://www.louisbouchard.ai/ai-index.json): Structured list of pages, posts, tags, and canonical URLs.
- [Full LLM index](https://www.louisbouchard.ai/llms-full.txt): Complete Markdown URL index for all public content.
- [Image sitemap](https://www.louisbouchard.ai/image-sitemap.xml): Discoverable local images used by public pages and articles.
- [Video sitemap](https://www.louisbouchard.ai/video-sitemap.xml): 414 YouTube embeds mapped to their canonical article pages.
## Discovery Notes
- Use canonical article URLs for attribution and citations.
- The AI index includes topics, tags, takeaways, FAQs, key questions, source links, media, and last-reviewed dates when available.
- The HTML pages remain the source of truth. The machine-readable files are navigation aids.
## Learning Paths
- [Learn AI Engineering](https://www.louisbouchard.ai/learn-ai-engineering/): A practical free guide to building real AI systems in 2026.
- [Build a Career in AI Engineering](https://academy.towardsai.net/?ref=1f9b29): A structured course path for people who want AI engineering to become their job, not just a side curiosity.
- [Start AI From Zero](https://www.louisbouchard.ai/learnai/): A beginner-friendly roadmap from no background to serious AI fluency.
- [From Zero to Hero With LLMs](https://www.louisbouchard.ai/from-zero-to-hero-with-llms/): A focused path for understanding and building with language models.
## Topic Hubs
- [AI Agents](https://www.louisbouchard.ai/topics/ai-agents/): Practical writing on AI agents, workflows, memory, tool use, reliability, and what actually ships.
- [Large Language Models](https://www.louisbouchard.ai/topics/llms/): Clear explanations of LLMs, reasoning models, prompting, context, distillation, fine-tuning, and model behavior.
- [RAG and Retrieval](https://www.louisbouchard.ai/topics/rag/): Guides and explainers on retrieval augmented generation, vector databases, embeddings, indexing, and evaluation.
- [AI Engineering](https://www.louisbouchard.ai/topics/ai-engineering/): Roadmaps, architecture decisions, evals, deployment lessons, and practical AI engineering advice.
- [Computer Vision](https://www.louisbouchard.ai/topics/computer-vision/): Computer vision explainers on image generation, segmentation, 3D reconstruction, video, and visual AI research.
- [Generative AI](https://www.louisbouchard.ai/topics/generative-ai/): How generative AI models create images, video, audio, code, and text, without the hype fog.
- [Learning AI](https://www.louisbouchard.ai/topics/learning-ai/): Free guides, beginner roadmaps, course recommendations, and practical paths into AI engineering.
- [AI News and Analysis](https://www.louisbouchard.ai/topics/ai-news-analysis/): Opinionated but fair analysis of AI releases, model news, research updates, and industry shifts.
## Key Pages
- [About me](https://www.louisbouchard.ai/about/): Learn who Louis-François Bouchard is, how What's AI started, and how his work connects AI engineering, education, videos, and Towards AI.
- [We Can Help your Team Adopt AI: Corporate Training, Consulting, and Talent Solutions](https://www.louisbouchard.ai/b2b/): AI training, consulting, and talent support for teams that want to adopt AI with practical systems, not vague demos or hype.
- [Contact](https://www.louisbouchard.ai/contact/): Contact Louis-François Bouchard for AI training, consulting, sponsorships, podcast requests, collaborations, or practical AI engineering questions.
## Featured Writing
- [Context Engineering in 2026: Why We Stopped Compacting Our Agent's Context](https://www.louisbouchard.ai/context-engineering-2026/) (Aug 18, 2026): Our AI tutor tests compare compaction and prompt caching: when keeping the full context costs less than summarizing it.
- [The Towards AI Mentorship for AI Engineers](https://www.louisbouchard.ai/towards-ai-mentorship-for-ai-engineers/) (Aug 04, 2026): Meet the Towards AI Mentorship: senior engineering help for your AI projects, architecture, career, and path into production.
- [How I Automated 90% of My Content Workflow With AI Agents](https://www.louisbouchard.ai/ai-agent-content-pipeline/) (Jul 28, 2026): A look inside the AI agent pipeline I use to research, write, illustrate, package, translate, and publish content while keeping the critical 10% human.
- [How to Build a Memory Your AI Agents Can Actually Reuse](https://www.louisbouchard.ai/memory-for-ai-agents/) (Jun 26, 2026): Build reusable memory for AI agents with plain files, source references, an index, and a wiki that future sessions can inspect, query, and update.
- [What Did Microsoft's MAI Model Actually Train On?](https://www.louisbouchard.ai/mai-thinking/) (Jun 23, 2026): Microsoft MAI-Thinking-1 avoids third-party model outputs in pretraining. Its trillion-parameter MoE design and report show what it actually trained on.
- [90% Cheaper GPT APIs](https://www.louisbouchard.ai/api-proxy/) (Jun 15, 2026): Cheap GPT API proxies can swap models, log keys and code, or inject malicious output. A 90% token discount can put your entire repository at risk.
- [Loop Engineering Explained](https://www.louisbouchard.ai/loop-engineering/) (Jun 10, 2026): Loop engineering for coding agents replaces babysitting with repeatable workflows for context, tools, checks, budgets, recovery, and clear stop conditions.
- [How Image Generation Actually Works](https://www.louisbouchard.ai/image-generation/) (Jun 07, 2026): How AI image generation works: diffusion sculpts noise, autoregressive models predict visual tokens, and text prompts steer both toward the final pixels.
- [Coding Changed Forever](https://www.louisbouchard.ai/vibe-coding/) (May 25, 2026): Vibe coding with AI agents can speed up software work, but only with good context, tests, reviews, and task boundaries. See what changed and where it fails.
- [How Google Went From AI Joke to OpenAI’s Biggest Problem](https://www.louisbouchard.ai/googleai/) (May 01, 2026): Google AI's comeback explained: how Gemini, DeepMind, AI Studio, and product distribution turned a mocked chatbot launch into a serious OpenAI rival.
- [Your AI Can Improve Itself — Or Fool You](https://www.louisbouchard.ai/self-improvement/) (Apr 24, 2026): Recursive self-improvement in AI uses generate, test, and keep-or-discard loops. Strong evals separate real progress from a system that learns to fool you.
- [AI Distillation Explained: The Truth Behind the Biggest AI Controversy Right Now](https://www.louisbouchard.ai/ai-distillation/) (Apr 17, 2026): AI model distillation explained: how student models copy a teacher's behavior, why labs use it, and where data rights, API terms, and ownership collide.
## Recent Writing
- [How I Built ToneBench: An AI Writing Benchmark With LLM Judges](https://www.louisbouchard.ai/tonebench-ai-writing-benchmark-llm-judges/) (Nov 05, 2026): How ToneBench scores AI writing: 10 tasks, five drafts per task, four judges with a leveled rubric, bias checks, and how I would write with AI today.
- [How AI Agents Evolved: From AutoGPT to Claude Code](https://www.louisbouchard.ai/how-ai-agents-evolved/) (Sep 28, 2026): A grounded history of AI agents from ReAct and AutoGPT to Claude Code, Codex, Cowork, and OpenClaw, including the benchmarks and real-world limitations.
- [DeepSeek V4.1 Flash: Smaller KV Cache, Cheaper Writing Drafts](https://www.louisbouchard.ai/deepseek-v41-flash-kv-cache-writing-benchmark/) (Sep 13, 2026): How DeepSeek V4.1 Flash reduces KV cache memory, what changed over V4 Flash, and what our writing benchmark measured for quality, cost, and effort.
- [My AI Setup: Claude Code, Codex, Obsidian and a Mac Mini](https://www.louisbouchard.ai/my-ai-setup/) (Sep 09, 2026): Inside my personal AI setup: shared notes and skills, Claude Code and Codex, remote access from my phone, and scheduled work on an always-on Mac mini.
- [How We Actually Use AI to Ship Code](https://www.louisbouchard.ai/ai-coding-workflows-that-ship/) (Aug 21, 2026): The three AI coding workflows, context rules, debugging habits, tests, and review guardrails the Towards AI engineering team uses to ship reliable code.
- [How I'd Learn AI Engineering in 2026](https://www.louisbouchard.ai/how-to-learn-ai-engineering-2026/) (Aug 03, 2026): Learn AI engineering in 2026 through LLM foundations, RAG, agents, evals, and projects that build practical system-design judgment.
- [Graph Engineering vs Loop Engineering: What Actually Changed](https://www.louisbouchard.ai/graph-engineering-explained/) (Jul 22, 2026): Graph engineering explained: why the viral loops-versus-graphs debate misses the point, what actually changed in agent orchestration, and what should stay code.
- [How to Control Bias in AI Agents](https://www.louisbouchard.ai/control-bias-in-ai-agents/) (Apr 01, 2026): Control bias in AI agents with system-level audits, scoped tools, feedback loops, and human review. See how autonomy can compound a small skew over time.
- [Harness Engineering: The Missing Layer Behind AI Agents](https://www.louisbouchard.ai/harness-engineering/) (Mar 25, 2026): Harness engineering explained: the tools, permissions, traces, evals, guardrails, and approvals that make AI agents debuggable and safer to ship.
- [Why RAG Is Not Training Your AI](https://www.louisbouchard.ai/why-rag-is-not-training-your-ai/) (Mar 16, 2026): RAG gives an AI model temporary context without changing its weights. See how retrieval differs from training and when fine-tuning is the better tool.
- [How to Get an AI Engineer Job in 2026](https://www.louisbouchard.ai/what-i-look-for-when-hiring-ai-engineers/) (Mar 09, 2026): Prepare for AI engineering interviews in 2026, build a portfolio that earns callbacks, and use coding agents responsibly.
- [Stop Building Agent Demos](https://www.louisbouchard.ai/stop-building-agent-demos/) (Feb 26, 2026): Move from AI agent demos to systems you can evaluate, debug, deploy, and trust, with scoped tools, traces, evals, failure handling, and real users.
- [I Published 42 Shorts on AI Terms in 42 days](https://www.louisbouchard.ai/ai-in-42-terms/) (Feb 05, 2026): Understand 42 AI and LLM terms through a free YouTube course of short videos on tokens, context, model behavior, and why fluent answers can still fail.
- [The 12 Questions That Decide Your AI Architecture](https://www.louisbouchard.ai/12-questions-ai-architecture/) (Jan 29, 2026): A practical checklist for choosing AI architecture before implementation, so teams avoid agent rewrites caused by bad scoping.
- [Multi-agent is becoming the new overengineering](https://www.louisbouchard.ai/agents-and-workflows/) (Jan 28, 2026): A clear distinction between workflows, agents, and multi-agent systems, with the main rule: stay as simple as the problem allows.
- [How to Clean Up AI-Generated Drafts Without Sounding Like ChatGPT](https://www.louisbouchard.ai/ai-editing/) (Jan 15, 2026): A practical editing workflow for using LLMs without losing your voice, with checks for slop, repetition, and fake polish.
- [Why AI Feels Intelligent (and Why That’s Misleading)](https://www.louisbouchard.ai/why-ai-feels-intelligent/) (Dec 23, 2025): Why LLMs feel intelligent, why the comparison to human learning gets messy, and what builders should remember about fluency.
- [Earn While Helping Others Learn AI](https://www.louisbouchard.ai/affiliate/) (Sep 02, 2025): An explanation of the Towards AI Partner Program, where referrals can earn books, courses, full access, or an affiliate tier.
- [Deep Research Agents: The Next Big Leap Beyond ChatGPT](https://www.louisbouchard.ai/deep-research-agents/) (Aug 26, 2025): Deep research agents go beyond chat by browsing, planning, synthesizing, and producing cited reports, but they still need checks.
- [What actually changed with GPT-5](https://www.louisbouchard.ai/gpt-5/) (Aug 08, 2025): A practical read on GPT-5: what changed in reasoning, tools, cost, and when the full model beats smaller options.
## External Profiles
- [YouTube](https://www.youtube.com/@whatsai)
- [Substack](https://louisbouchard.substack.com/)
- [LinkedIn](https://www.linkedin.com/in/whats-ai/)
- [GitHub](https://github.com/louisfb01)
- [Towards AI](https://towardsai.net/)