Recommendation · MoneyThe creator recommends instrumenting every agent running in the pipeline with Otel so you can go to a SIM or logging platform and analyze how agents run across repositories and how much they cost, including pivoting on average token use.
AI Engineer · From Your Laptop to the Pipeline: Scaling Custom Agents with GitHub Copilot
Recommendation · MoneyThe app server comes as part of the Codex CLI — it's the same binary, so if you have the CLI you can spin up the app server right now. But you should bundle the app server binary with your application so you have full control over the capabilities of the version you're building against, since the protocol regularly changes between versions.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyDominik Kundel warns against rushing to write your own system prompt: OpenAI constantly tunes the harness to keep prompts in distribution and the agent performing well, and you lose all of that by replacing base instructions. If changing instructions, start by adding developer instructions rather than changing the base instructions.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyDominik Kundel advises starting with developer instructions rather than changing base instructions when customizing the agent. Rushing to write your own system prompt loses the harness team's work keeping the prompt in distribution so the agent performs well; he says to be careful if you do write your own.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyDominik Kundel recommends the app server when building a more comprehensive client that shows the agent, or when spinning up many Codex threads at once — such as running your own eval harness — because it gives full control over the harness and avoids hand-rolling parallelization of CodexExec calls.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyThe two biggest things to look at when customizing the agent on the app server are developer instructions — appending on top of Codex's system prompt rather than replacing it, leveraging OpenAI's prompt-tuning work while customizing for your use case (this is what OpenAI does in the Codex app, since some functionality is app-specific) — and bringing tools: dynamic tools expose additional functions via MCP or by defining tools directly, and can be marked as deferred loading so Codex finds them via a tool search tool instead of polluting the context window.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyDominik Kundel recommends exposing new functions as part of your interface but marking them deferred, so you avoid polluting the context window and confusing the agent while keeping the functions available. He notes the Codex app does this so the agent can control itself, e.g. spinning up automations.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyDominik Kundel advises shipping your own version of the harness to eliminate many headaches: relying on the user's installed CLI means constantly running into breaking changes (especially with experimental features, even though OpenAI tries to minimize them), and worrying about whether users have updated to get the latest features or nudging them to update.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyDominik Kundel recommends shipping your own harness to eliminate headaches: relying on the user's installed CLI exposes you to breaking changes (especially with experimental features) and forces you to worry about whether users updated to a version with the feature you need.
AI Engineer · Building on the Codex Harness — Dominik Kundel, OpenAI
Recommendation · MoneyPedro Lopez explains that CLIs invoked by agents cannot assume a human is present to answer interactive prompts; such CLIs get stuck. Inputs should be exposed via flags, and credentials via environment variables and config files so setup can happen out of band.
AI Engineer · Designing CLIs for Agents, Not Humans — Pedro Lopez, Airbyte
Recommendation · MoneyWhen starting with a customer, be transparent about three things: show what works (state the reliability level they can trust), tell them what you're doing to improve (acknowledge known gaps you're investing time to fix), and tell them what is out of scope — if something doesn't work, say so and don't let them try it.
Commercial context: The creator presents this as their own offering and directs viewers to get it.
AI Engineer · Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab
Method · MoneyViren Baraiya walks through an SRE agent as a remediation loop: step one is a call to the LLM, whose output is the steps the agent should do; the harness then executes those steps as a deterministic workflow. The loop first understands the root cause of the problem, reacts to it, observes the output, and then runs another loop to plan the next set of steps — essentially a remediation loop that runs twice. The agent's job is to understand what's going on in the current system, plan what should happen next, and execute on those things.
Method, not a verified protocol.
AI Engineer · Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
Recommendation · MoneyEngineers should optimize for this new world by decomposing needs into their simplest chunks, which lends to understanding, simpler code surfaces, and control of code bases. Teams used to break a feature into small atomic pieces they could reason about — small enough to hold in your head.
AI Engineer · Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop — Gabriel Martinez, G2i
Recommendation · MoneyReview service boundaries, data flows, state transitions, and failure modes as the compressed review surface. Leave the main process or workflow as the reviewable surface with implementation details pushed to the leaves. Gabriel Martinez also vouches for declarative code and architecture patterns that create layers humans can actually reason about.
AI Engineer · Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop — Gabriel Martinez, G2i
Recommendation · MoneyThe answer to AI slop is conventions, standards, documented flows, small reviewable surfaces, and clear ownership boundaries and definitions of done. The more obvious the path, the less room there is for slop to hide. With proper conventions, intent is more easily dropped into place.
AI Engineer · Generation Is Cheap, Review Is Expensive: How to Stop Shipping AI Slop — Gabriel Martinez, G2i
Method · MoneyGreg created a set of policies and a skill called 'Grumpy Engineer' (internally 'Garfield') to review agent-written code. It runs a sub-agent per policy; each sub-agent either gives feedback or stands down. The loop repeats until every sub-agent stands down and validates the code, and only then does Greg read the code himself.
Method, not a verified protocol.
AI Engineer · Stop Prompting — Greg Pstrucha, Sentry
Method · MoneyAutomattic runs two-week in-person enablement programs structured as 50% facilitated learning and 50% real project work. Internal workshop hosts run sessions, participants bring real work or tools/dashboards they want to build (including new skills or MCPs), peer workflow sharing is encouraged, and project demos happen at the end of each day.
Method, not a verified protocol.
AI Engineer · How a Remote Company Builds AI Fluency — Em Shreve, Automattic
RecommendationWhen sending a prototype to Figma Make, prompt it to make the interaction into a section of a website, using the intro animation and keeping things as is, honoring the transitions.
Figma · Figma for Edu: Prototyping with animations in Figma
MethodMickey demonstrates a first animation: draw a rectangle into the frame, click the motion icon at the bottom of the toolbar to enter motion mode, move the rectangle to its starting position, move the playhead to the far left, and keyframe-stamp the position at zero seconds; then move the playhead to about 500 milliseconds and stamp another position, using the position widget over the selected rectangle to change its position for the second keyframe.
Method, not a verified protocol.
Figma · Figma for Edu: Prototyping with animations in Figma
MethodSelect the frames in prototype mode and use the Send to Figma Make option; Figma Make opens, imports the designs, and analyzes them. Prompt it to make the interaction into a section of a website, use the intro animation, keep things as is, and honor the transitions.
Method, not a verified protocol.
Figma · Figma for Edu: Prototyping with animations in Figma