LAI #135: The Useful Part of Graph Engineering Is Not the Graph

Graph engineering, the latest buzzword for orchestrating multiple agent loops, forces teams to formalize processes but was already covered by Anthropic in 2024, according to Louis-François Bouchard, Co-founder of Towards AI. Bouchard warns that forcing structured outputs like JSON can reduce model accuracy, especially on reasoning-heavy tasks, and advises measuring answer quality separately from parse rates. A community-built toolkit, review-toolkit, adds two reviewer agents to Claude Code for plan and code review before merging.

Good morning, AI enthusiasts The AI discourse has a new buzzword this week, and for once, the underlying idea is worth your time, even if Anthropic already wrote about it in 2024. We’re also tackling a tradeoff most teams don’t measure: forcing structured outputs can make your model’s answers worse, and a 100% parse rate won’t tell you. We also cover: Let’s get into it I made a video on loop engineering a few weeks ago, and apparently it died before some of you even got a chance to watch it. We now have Graph engineering, basically, this week’s name for connecting several agent loops into one orchestrated system. I am glad we are talking about it, but Anthropic’s Building Effective Agents post from 2024 covers each of these concepts already. We are talking about it now because drawing the graph forces you to think about the process and set it up once and for good. Graph engineering is this week’s name for taking orchestration a bit more seriously now that we have access to models like 5.6 and Fable. So today, in What’s AI, I am diving into what graph engineering actually is and which part deserves your attention. Read the full article here https://www.louisbouchard.ai/graph-engineering-explained/ , or if you prefer watching, check the video on YouTube https://www.youtube.com/watch?v=MDHcmWmvqvo . Structured Outputs make responses easier to plug into software, but they also change how the model generates its answer. When we first wrote the lesson ‘Structuring Your Data’ for our Full Stack AI Engineering https://towardsai.com/academy/full-stack-ai-engineering/?utm source=Newsletter&utm medium=email&utm id=AItips course, the main problem was getting models to return JSON your application could reliably parse. As structured outputs became standard across newer reasoning models and smaller models used in production, another problem became harder to ignore: the schema can be perfectly valid while the answer inside it gets worse. This is especially important on tasks that already stretch the model’s reasoning. Requiring it to solve the problem within a rigid schema can reduce accuracy, particularly when the schema is complex, or the model has little capacity to spare. Before adding a schema, run the task in free form and record the quality of the answers. Then introduce the smallest schema your application needs and repeat the same evaluation. Measure answer quality and schema validity separately. A 100% parse rate only tells you that your software can read the response. It does not tell you whether the response is correct. When structure reduces accuracy, simplify the schema. For tasks where the final formatting is deterministic, let the model work through the problem freely and package its answer into the required structure in code. — Louis-François Bouchard, Towards AI Co-founder & Head of Community Dr zoe88 https://discord.com/channels/702624558536065165/983037843532308500/1528335297396342894 just built review-toolkit, a small toolkit that gives Claude Code two “reviewer” agents. One reviews your plan before you write any code, and one reviews your code before it merges. The repo ships with a test suite of planted flaws, and both reviews are allowed to say: “nothing to fix”. Try it out on GitHub https://github.com/mahmoudmoe84/review-toolkit and support a fellow community member. Share your feedback, questions, and if it catches something for you in the thread https://discord.com/channels/702624558536065165/983037843532308500/1528335297396342894 Anthropic leads at 21%, but 18% of you don’t want to work at any of these companies; you want to build your own. Nearly 1 in 5 picked founder over every major lab on the list. NVIDIA takes third at 16%, which makes sense if you’re thinking long-term; betting on the infrastructure layer is a different kind of bet than betting on any one model provider. Also, 5% of you said Towards AI; we see you, and we appreciate it. As we mentioned last week, the deployment pods do hire from this community first. For those who picked founder: are you already building something, or is that the plan once you feel ready? And for those who picked a lab, what’s the pull? The research, the product, or just wanting to be where the biggest models get made? Let me know in the thread https://discord.com/channels/702624558536065165/833660976196354079/1528376599534243940 The Learn AI Together Discord community is flooding with collaboration opportunities. If you are excited to dive into applied AI, want a study partner, or even want to find a partner for your passion project, join the collaboration channel https://discord.gg/rj6m9AF7eC Keep an eye on this section, too — we share cool opportunities every week 1. Jadexrose https://discord.com/channels/702624558536065165/784477688551178240/1529065786503598221 is recruiting for AI engineering roles at startups and is looking for someone to discuss AI engineering concepts, do some mock interviews, and build stuff. If this sounds like it would help you as well, connect with them in the thread https://discord.com/channels/702624558536065165/784477688551178240/1529065786503598221 2. Divyanshijoshi https://discord.com/channels/702624558536065165/998978160605540454/1528289413950476370 is currently looking for people to work together on AI research, especially in interdisciplinary fields with a focus on machine unlearning, LLM bias mitigation, and studying bugs in software engineering. If this sounds interesting, reach out to her in the thread https://discord.com/channels/702624558536065165/998978160605540454/1528289413950476370 3. Mikieldus https://discord.com/channels/702624558536065165/998978160605540454/1529526317073170624 is looking for a team to develop his project. If you want to work on projects and need more details, write to him in the thread https://discord.com/channels/702624558536065165/998978160605540454/1529526317073170624 Meme shared by bigbuxchungus https://discord.com/channels/702624558536065165/830572933197201459/1528122460455571626 Hypothesis Testing Is Just a Courtroom With Worse Snacks https://pub.towardsai.net/hypothesis-testing-p-values-explained-simply-dba502312edb?sharedUserId=tai-tech by Kamrun Nahar https://iknahar.medium.com/?source=post page---byline--dba502312edb--------------------------------------- A journalist named John Bohannon convinced the world that chocolate helps you lose weight. He didn’t fake a single number. The study was real, the p-value was real, and that’s exactly the problem. This article uses that story to explain why p-values fool people, traces hypothesis testing back to Fisher’s tea-tasting experiment, and walks through null hypotheses, significance levels, Type I and II errors, power, and confidence intervals with runnable Python code throughout. 1. Building a Multi-Agent Support Ticket Triage With LangGraph https://pub.towardsai.net/building-a-multi-agent-support-ticket-triage-with-langgraph-963a5b2081fb?sk=2d2e94d8a158f1fd69f00869bb3dbb51 by Sarah Lea https://medium.com/@schuerch sarah?source=post page---byline--963a5b2081fb--------------------------------------- If you’ve been looking for a clean starting point for multi-agent systems, this is it. A classifier assigns category and priority, a router directs traffic, a responder drafts replies, and urgent tickets escalate to a human. One factory function lets the same graph run locally on Llama3 or through GPT-4o-mini, no architecture changes needed. 2. DPO Fine-Tuning from First Principles in Python https://pub.towardsai.net/dpo-fine-tuning-from-first-principles-in-python-0ef188377cb0?sk=ac780e9ae20466e88358ab89e4599628 by Armin Norouzi, Ph.D https://arminnorouzi.medium.com/?source=post page---byline--0ef188377cb0--------------------------------------- Most DPO tutorials start at the loss function. This one starts at why the loss function works. The author derives everything from Bradley-Terry preferences through the reparametrization that eliminates the reward model entirely, then implements it in pure NumPy with analytical gradients. A beta sweep at the end shows how temperature controls KL drift in practice. 3. I Built a Team of AI Agents That Manage Themselves — Here’s the Orchestrator Pattern Behind It https://pub.towardsai.net/i-built-a-team-of-ai-agents-that-manage-themselves-heres-the-orchestrator-pattern-behind-it-cdc815b56036?sk=f47391701ef06c9a61a5c3d48391328d by Sai Insights https://medium.com/@sai-insights?source=post page---byline--cdc815b56036--------------------------------------- An orchestrator decomposes a question into subtasks, runs specialist workers in parallel over a shared blackboard, and a critic flags low-confidence answers for capped retries. What makes this useful: a free demo mode verifies every code path without API costs, and a live Claude mode lets you run it for real. The full execution logs are included so you can see exactly what happens at each step. 4. Langfuse from Zero to Production: Tracing, Prompt Versioning, and Evals in One Stack https://pub.towardsai.net/langfuse-from-zero-to-production-tracing-prompt-versioning-and-evals-in-one-stack-67584889982c?sk=874236679cd086ed7e0da418f433ee5f by Harish Ramkumar https://medium.com/@ramkumar.harish?source=post page---byline--67584889982c--------------------------------------- If you want LLMOps without handing your data to a third party, this is the walkthrough. The author sets up Postgres, ClickHouse, Redis, and MinIO via Docker Compose, instruments a RAG pipeline with nested traces, adds versioned prompts with one-click rollback, and wires up LLM-as-judge scoring. A CI quality gate at the end turns every prompt change into a testable, reversible release. If you are interested in publishing with Towards AI, check our guidelines and sign up https://contribute.towardsai.net/ . We will publish your work to our network if it meets our editorial policies and standards. LAI 135: The Useful Part of Graph Engineering Is Not the Graph https://pub.towardsai.net/lai-135-the-useful-part-of-graph-engineering-is-not-the-graph-969868925865 was originally published in Towards AI https://pub.towardsai.net on Medium, where people are continuing the conversation by highlighting and responding to this story.