Recommendation · MoneyPeter Werry recommends creating a tool that does the query and, as an argument to the tool, accepts a username, so you can fail right there if the username is not correct or malformed.
AI Engineer · Beyond RAG: Build a Relational Context Engine from Scratch — Peter Werry, Unblocked
Recommendation · BodyThe guest says the first thing to ask someone starting hybrid training is how much they can actually train. He warns that people overestimate their availability — claiming five conditioning sessions and four gym sessions while barely making it to the gym twice per week. Realistically, if someone says they'll train five times a week, it will be four; if they say four, it will be three. When planning frequency, look at the realistic range and ask what's acceptable within that range.
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Recommendation · BodyPushing top-end clean weights in the off-season is fantastic when it doesn't interfere with in-season training. If you're practicing cleans and making progress while other strength ratios are sorted, you'll get a lot of what you need — e.g., going from 0.8x to 1.1x bodyweight power clean between off-seasons is fantastic progress.
the 0.8x to 1.1x example is flagged as a possible numeric error
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Recommendation · BodyHill sprints let a non-sprinter athlete sprint all-out — open up and hit sixth gear — without tearing their hamstring. Aim for fast, long strides with a little of the front knee coming up. Some track coaches criticize high hills, saying you need a tiny gradient, but the speaker disagrees for non-sprinter athletes.
the track-coach criticism is a quoted position the speaker disagrees with
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Recommendation · MoneyThe speaker recommends pulling pre-built pipeline agents off the shelf from the GitHub Next organization's Agentix project, which has 30 or so different pipeline agents. Some do code deduplication, and others are different types of reviewers, such as a QA reviewer or one that just makes jokes.
AI Engineer · From Your Laptop to the Pipeline: Scaling Custom Agents with GitHub Copilot
Recommendation · MoneyAdd full text search to the query engine to handle cases where an exact title match returns no results.
AI Engineer · Beyond RAG: A Relational Context Engine That Cuts Token Burn — Unblocked
Recommendation · MoneyTo test the benefits of context bundles without wiring up Unblocked, use the open source simulator to create a context bundle on a task-by-task basis and run an A/B test against the same task to measure the benefit of context for your agents.
AI Engineer · Beyond RAG: A Relational Context Engine That Cuts Token Burn — Unblocked
Recommendation · MoneyAfter learning that whiteboard users typed 'group my sticky notes into common themes', Atlassian let users select cards and trigger the grouping with a button instead of a prompt; automate common prompts into buttons as one of the chat-to-UI patterns.
The Official SaaStr Podcast: SaaS | Founders | Investors · SaaStr 881: How Atlassian's Head of AI Ships AI Across 20 Products and 5 Million Users
Recommendation · MoneyAtlassian runs AI Builders Week every couple of months, a four-day program across the organization synchronized so everyone takes the same time; juniors come in and share all the new tools and techniques, and seniors come in and talk about quality control, AI slop, and how to build differentiated AI rather than generic AI.
The Official SaaStr Podcast: SaaS | Founders | Investors · SaaStr 881: How Atlassian's Head of AI Ships AI Across 20 Products and 5 Million Users
Recommendation · MoneyExpose your app's skills via MCP or a CLI so customers' external agents (e.g., coding agents) can use them across their other SaaS tools; agents on your platform need to work with the rest of the customer's world.
The Official SaaStr Podcast: SaaS | Founders | Investors · SaaStr 881: How Atlassian's Head of AI Ships AI Across 20 Products and 5 Million Users
Recommendation · MoneyTune the zero-copy retrieval flag and the spread scheduling mechanism flag as part of optimizing the data pipeline.
AI Engineer · From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model
Recommendation · MoneyMegatron data parallel ranks can call the array store directly to fetch data as needed instead of round-tripping through the head node.
AI Engineer · From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model
Recommendation · MoneyAnders Swanson notes that the agent runtime can invoke the memory layer through things like hooks, MCP, skills, or other methods.
described
AI Engineer · From Context to Memory: Your Agents Need a Real Memory Layer — Anders Swanson, Oracle
Recommendation · MoneyViren Baraiya recommends that when thinking about agents in production, do not think only about chatbots. Consider background agents and background workers: an agent that runs on a schedule (e.g., every hour) to check what is happening with your schedule and whether something new has popped up; event-driven agents that listen on various events and react to them; and agents that listen to production alert and log events to investigate what is going on.
AI Engineer · Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
Recommendation · MoneyYou can configure the system to block merging if there are any unresolved code review findings.
AI Engineer · AI Writes More PRs. Who Validates Them? — Ali-Reza Adl-Tabatabai, Sonar
Recommendation · MoneyYou can customize the AI review with your own rules, add your own custom checks, and trigger your own custom workflow automations in the validation system.
AI Engineer · AI Writes More PRs. Who Validates Them? — Ali-Reza Adl-Tabatabai, Sonar
Recommendation · MoneyWill Lyon recommends that for each execution plan, agents capture the tools called and the results of those tool calls, plus metrics like token burn and timing, as part of reasoning memory.
AI Engineer · Turning Agent Memory Into Skills That Work — Will Lyon, Neo4j
Recommendation · MoneyGarrett Galow recommends that companies wanting to enable non-engineers to ship apps distribute internal build tooling to every employee through MDM so everyone has access on day one, and build a shared skills repository where anyone can push useful skills and everyone can fetch and pull them down.
endorsed
AI Engineer · Let Anyone at Your Company Ship Internal Apps with AI — Garrett Galow, WorkOS
Recommendation · MoneyGarrett Galow recommends that companies running internal hackathons pair non-engineers with engineers and have the non-engineers do the building with hands on keyboard. The paired engineer's role is to consult, help, unblock the non-engineer with issues, and act as a sounding board for approaches.
endorsed
AI Engineer · Let Anyone at Your Company Ship Internal Apps with AI — Garrett Galow, WorkOS
Recommendation · MoneyMatt Gibiec recommends baking Blue Box into AI coding agents so issues are detected early and developers become productive.
AI Engineer · Your AI Agent Has No Nervous System — Matt Gibiec, Dynatrace