Method · MoneyIn the live demo, Dean runs 'flash dev', which launches a FastAPI localhost so he can toy around with his function; executing it provisions a serverless endpoint that appears in the RunPod console. He views the container logs to see the worker testing health checks and running the job. The demo's first function talks to Torch to get what kind of GPU you have, and it ran on an NVIDIA GeForce RTX 4090, showing GPU RAM and GPU count in the result. When he cancels the flash dev session, it deprovisions the endpoint so it doesn't lie around.
The GPU model comes from a live demo and the source flags a possible numeric error.
Method, not a verified protocol.
AI Engineer · AI Apps in a Flash: Ship to GPUs Without Docker — Dean Quiñanola, Runpod
Recommendation · MoneyForrester recommends that developers try to have all the guardrails at their application layer, while acknowledging things might get missed. He further recommends running guardrails at the infrastructure layer for every agent running in the cluster, providing an added level of protection against a broad sweep of everything coming in and out.
None stated.
AI Engineer · Build a Platform and Watch It Burn — Michael Forrester, Accenture & Whitney Lee, Datadog
Recommendation · MoneyAfter every run, go through all of the errors and mistakes and check whether there have been inference issues. You can detect an inference issue if the model output contains repeated characters, and detect a tokenizer or inference server issue if prompt template tokens leak into the actual response.
AI Engineer · From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Recommendation · MoneyManually reviewing all production agent traces to find issues is infeasible — the speaker says he couldn't go through all of them, but Claude, Cursor, or Codex can. One of the biggest superpowers you can give coding agents is the ability to analyze traces and find the actual issues for you; Claude was able to look at actual traces and understand what the real issues are today in the live production agent.
AI Engineer · Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI
Recommendation · MoneyShipping based on vibes — manually checking input and output to verify correctness — is a common starting approach, but you can't really ship on the feeling that 'it's correct': you won't know where things are broken in production. Set up actual evals to find out where things are breaking and how to directly fix them, and build evaluations to continuously monitor the use cases you test against.
AI Engineer · Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI
Recommendation · MoneyManually reviewing all production agent traces is not feasible at scale, so give coding agents like Claude, Cursor, or Codex access to production traces so they can automatically review them and identify issues you cannot find manually.
AI Engineer · Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI
Method · MoneyNyah Macklin explains how to enable GenAI capabilities (Generative AI Assistance and Aura Agent toggles) in the Neo4j organization, open the instance in query mode, create an agent from scratch tied to the Aura instance, and name and describe it for the GraphRAG Fundamentals course.
Method, not a verified protocol.
AI Engineer · RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j
Method · MoneyA step-by-step workshop walkthrough: create a vector index in the Aura console, connect the Neo4j instance, generate a knowledge graph, then create and configure a GraphRAG agent tied to that instance.
Method, not a verified protocol.
AI Engineer · RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j
Method · MoneyNyah Macklin shows how to find the workshop solutions, run the knowledge graph structured builder (e.g., via VS Code), watch it populate the Aura instance live, and then query the graph with Cypher to inspect nodes and relationships.
Method, not a verified protocol.
AI Engineer · RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j
Recommendation · MoneyCreate a space where weird things can grow and where obsessed small groups can happen, be on alert to catch it, and funnel it forward. The best ideas get started in very small groups of people who are just obsessed and usually very curious about something and just won't stop. Sometimes it's less about the idea and more about who the interesting people are and their side projects — create chemistry around those. Build an environment and nurture both ideas and the people that can thrive there.
Lenny's Podcast · Why every company now needs to think and operate like a lab team | Josh Woodward (VP Google Labs)
Recommendation · MoneyEven if you don't use Aperture, Remy highly recommends starting to consider and look at an AI gateway. Gateways are good beyond just avoiding having three different providers configured or switching between them, and are great for understanding what agents are doing — even for individuals. Many people run their usage behind an AI gateway as individuals just to see what their agents are doing, e.g. people running something like OpenClaw on their tailnet in the background that did something it wasn't supposed to do. Using an AI or LLM gateway is important not just for lock-in prevention but for experimentation and understanding as a whole.
AI Engineer · An AI Future Without the Lock-In — Remy Guercio, Tailscale
Recommendation · MoneyRemy advises organizations against consolidating on one vendor (or maybe two) to get a handle on AI spending. In the 'panic zone' of having spent a lot without knowing how, consolidating feels natural, but with only two frontier models and their stack ecosystems, certain things become untenable and AI usage can't expand across the company.
AI Engineer · An AI Future Without the Lock-In — Remy Guercio, Tailscale
Recommendation · MoneyHide metadata fields like tenant ID from the LLM and validate output to prevent leaking internals. If the LLM outputs a hidden metadata field, wipe it out and inject your own metadata field underneath. Hidden fields in the schema, like ID or metadata fields, can leak internals if not sanitized.
AI Engineer · Beyond RAG: Build a Relational Context Engine from Scratch — Peter Werry, Unblocked
Recommendation · BodyAttack acceleration first when working on sprint technique, because in most sports the max speed phase won't express much difference. Unless you're a winger getting big open breaks covering 40-50 meters, max speed matters less. Getting good at acceleration is the low-hanging fruit and big bang for your buck for most athletes.
Garage Strength · How To Get Strong and Still Be Athletic w/ Sika Strength
Method · MoneyAn ordered deployment workflow: update the application manifest to concatenate tasks so 'spin build' compiles, composes, and builds the MCP server within the Spin developer experience; run 'spin akamai deploy', which composes the server, asks for a name, and interacts with the service registry; the Wasm file and manifest are turned into OCI layers and uploaded; every service region must confirm receipt and capability, the workload is instantiated once, and an internal health check runs; once all regions return HTTP 200, a generic subdomain is rolled so the MCP server is on the public internet. The demo achieved global distribution in roughly 60 seconds.
Method, not a verified protocol.
AI Engineer · Zero Cold Starts: Serverless AI Agents on Akamai Functions — Thorsten Hans
Method · MoneyA demonstrated end-to-end workflow: install WASMCP from github.com/wasmcp/wasmcp, scaffold with 'wasmcp new' (Rust, TypeScript, or Python templates), npm install, define tool schemas in an array with precise descriptions for humans and LLMs, implement a call-tool dispatcher that validates incoming arguments, compile with 'make' to tools.wasm, compose with 'wasmcp compose', test locally via 'npx @modelcontextprotocol/inspector' against localhost:3000, then deploy with 'spin build' combined with 'spin akamai deploy' (allowing terminal access to the service registry).
live-demo walkthrough; exact commands as shown on screen
Method, not a verified protocol.
AI Engineer · Zero Cold Starts: Serverless AI Agents on Akamai Functions — Thorsten Hans
Method · MoneyA demonstrated agent workflow: create a new Spin app from a TypeScript template, bring in Vercel AI SDK dependencies, point the agent at an Ollama LLM running on a Linode instance with a dedicated GPU, define the agent's tools in the Spin app configuration, give it an identity and intent instruction, register tools with step-count constraints, generate and return the response in the HTTP handler, then deploy with 'spin aka deploy' and point clients at the agent.
live-demo walkthrough; LLM-on-Linode detail is the host's own setup
Commercial context: The creator presents this as their own offering and directs viewers to get it.
Method, not a verified protocol.
AI Engineer · Zero Cold Starts: Serverless AI Agents on Akamai Functions — Thorsten Hans
Method · MoneyA locally coherent, ordered workflow demonstrated in the talk: install WASMCP from github.com/wasmcp/wasmcp to get a CLI; scaffold a new MCP server with 'wasmcp new' choosing Rust, TypeScript, or Python and a template; run 'npm install' for the TypeScript project; express the input schema and list tools in a simple array with precise descriptions so humans and LLMs know how to handle them (the example tool validates arguments and returns concatenated input); compile with 'make' to produce a tools WebAssembly component; run 'wasmcp compose' to pull all necessary components and compose a full-fledged MCP server (authentication was skipped for the demo); run it locally with 'spin up -f server.wasm' on localhost:3000; verify with 'npx @modelcontextprotocol/inspector' by connecting and listing.
Method, not a verified protocol.
AI Engineer · Zero Cold Starts: Serverless AI Agents on Akamai Functions — Thorsten Hans
Recommendation · MoneyPatterson recommends pre-configuring cloud environments so agents can start developing immediately without downloading dependencies from potentially contaminated registries. When an agent is put on a fresh box and told to run a project, it will read the contents and start downloading things from unknown sources — and any registry it grabs from could be contaminated.
AI Engineer · The Lethal Trifecta Is Already on Your Laptops — Michael Patterson, Coder
Recommendation · MoneyThe speaker advises writing a custom agent if you have a specific task, review, compliance, or regulatory requirement that needs custom tools or checks. When building custom agents, you can control which model the agent uses and the instructions you give it.
Also discussed by Aaron Levie on The a16z Show (unclassified source — not counted until classified). Not counted as independent sources.
AI Engineer · From Your Laptop to the Pipeline: Scaling Custom Agents with GitHub Copilot