--- title: "Agent Building Tips from the Frontlines" newsletter: "MLOps Community" date: 2025-08-07 source: https://aaif.live/newsletters/mlopscommunity/2025-08-07-agent-building-tips-from-the-frontlines --- # Agent Building Tips from the Frontlines *Plus, bottlenecks slowing down your AI agent, building a connected knowledge graph, Hidden Gems, and ML Confessions.* *MLOps Community — Agentic AI Foundation, 2025-08-07* In a week that included the release of Opus 4.1, Genie 3, and gpt-oss, shout-out to Médéric [https://www.linkedin.com/in/fmind-dev/] for dropping the most epic one [https://go.mlops.community/medintro]. ## 9 Commandments for Building AI Agents With the look comes certain expectations. I’m still working on the whole water/wine thing, but in the meantime, I thought we could use some commandments for building AI agents. I talked with Paul and Dmitri about what actually makes agents useful in production. Dynamic planning helps agents adapt mid-task, but risks going in circles. Memory is also key - not just user preferences, but remembering how to complete tasks well. That feeds back into agent reasoning and model training. To scale this, they’ve focused on letting non-engineers build agents with internal tools. That’s led to new design tradeoffs, like: * Choosing tools: Agents may need to weigh cost, accuracy, and speed before selecting one. * Execution shortcuts: Logged “successful paths” help agents skip repetitive steps. The 10th commandment? Click below to listen. Video [https://go.mlops.community/ppad7aug] || Spotify [https://go.mlops.community/spad7aug] || Apple [https://go.mlops.community/apad7aug] [https://go.mlops.community/apad7aug](https://go.mlops.community/apad7aug) [https://go.mlops.community/ppad7aug](https://go.mlops.community/ppad7aug) [https://go.mlops.community/spad7aug](https://go.mlops.community/spad7aug) ## Hidden Gems ## The Hidden Bottlenecks Slowing Down AI Agents Top tip from this episode: label your data for the price of a pizza by hosting labeling parties. Some more conventional advice did come up too, as we talked build vs buy across evals, orchestration, and observability. Evals are often bottlenecked by dataset creation, not tooling. For orchestration, building in-house gave more control and reliability than most off-the-shelf options. Observability was a clear case where simple and familiar beat specialized: * Datadog handles both agents and infra, keeping everything unified. * Custom event streaming enables reruns, so no need for separate replay tools. * Fewer vendors means less friction, especially around compliance. The best tip? Grab yourself a pizza and click below to listen. Video [https://go.mlops.community/ppab7aug] || Spotify [https://go.mlops.community/spab7aug] || Apple [https://go.mlops.community/apab7aug] [https://go.mlops.community/apab7aug](https://go.mlops.community/apab7aug) [https://go.mlops.community/ppab7aug](https://go.mlops.community/ppab7aug) [https://go.mlops.community/spab7aug](https://go.mlops.community/spab7aug) ## Job of the Week [https://go.mlops.community/jobus7aug](https://go.mlops.community/jobus7aug) ## Automating Knowledge Graph Creation with Gemini and ApertureDB - Part 2 So many tabs open, so many bookmarks, and you still can’t find what you need. To save you hunting, here’s part one [https://go.mlops.community/blog31jul] - helpfully all about finding and organizing things. Part 2 walks through how to extract relationships between entities using Gemini 2.5 Flash, then build a connected knowledge graph in ApertureDB. It covers relationship parsing with structured prompts and Pydantic models, batch-inserting links, and visualizing everything with PyVis and NetworkX. They also show how to link entities back to the source document: * Each entity is connected to the original PDF blob * This enables grounded retrieval workflows * The same pattern works for images, audio, or video too Click below to connect with this source document. Read it here [https://go.mlops.community/blog7aug] [part one](https://go.mlops.community/blog31jul) [https://go.mlops.community/MLConfess](https://go.mlops.community/MLConfess) In AI tooling, forward compatibility is the new technical debt. If you’re not betting on what gets commoditized next, you’re building yourself into a corner. Are you betting, or betting your corner will hold? Working on something tricky or planning ahead? Here’s how we can help - just hit reply: * Custom workshops tailored to your company’s needs * Hiring? I know some quality folks looking for a new adventure * Want to connect with someone tackling similar problems? I can introduce you Thanks for reading, catch you next time! --- Source: https://aaif.live/newsletters/mlopscommunity/2025-08-07-agent-building-tips-from-the-frontlines