33,353 results · Most relevant
Pedro 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.
When 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.
Viren 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.
Engineers 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.
Review 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.
The 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.
Greg 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.
Automattic 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.
When 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.
Mickey 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.
Select 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.
The host recommends finding the thing you have been holding back in order to stay safe in the crowd, listing possibilities such as your perspective, humor, art, sensitivity, goofiness, or mission, and suggests starting to express it.
Once misalignment is found, Hormozi recommends making a concrete trade — decrease hours in an over-invested category (like career) and reallocate them to the neglected one. He argues that trying to add investment without decreasing others yields lower overall life benefit than an explicit trade, and that you should compare the incremental return of the hour lost against the overall life benefit gained.
Philipp Schmid walks through how to use the Interactions API: server-side state management (hand conversation state to the server; for a follow-up turn, provide new input plus the ID from the previous turn and the server concatenates all inputs); long-running operations as async requests (send a request, get back an ID, set up streaming or polling until generation completes — useful because video generation with Omni takes a long time and you may not want to keep the HTTP connection open); audio generation (define response modality audio plus generation config with the voice); image generation (send input plus generation config, get back the image); and tool use (define tools like Google Search, URL context, or custom functions, and the model decides on its own whether to run search or a
Dru Knox recommends setting up a control plane with three components: an issue tracker that kicks off agent work, a review system, and a way to standardize and distribute workflows.
endorsed
Dru Knox recommends standardizing and distributing workflows via a skills registry or a shared GitHub repo where skills that improve agent quality are pushed.
endorsed
Dru Knox recommends moving all work into an issue tracker so every task starts as an issue that gets sent to a headless agent running in a sandbox.
endorsed
Dru Knox recommends setting up a control plane with three components: issue tracking (kick off agent work from tracked issues), review (GitHub PR review is probably the easiest), and workflow distribution (standardize and distribute workflows, playbooks, and skills via a skills registry or shared GitHub repo).
To create and manage guidelines, navigate to the file menu of any Figma file that's published as a library, select 'Library', then 'Manage guidelines'. Upload files that contain context for your library in the guidelines management panel, then click 'Apply changes' so the uploaded guideline files are referenced anytime someone uses Figma's agent with your library attached.
Include guidance on how to use components and their variants with clear do's, don'ts, and rationale. Also include common mistakes or anti-patterns, and unwritten team knowledge or taste preferences that the agent needs to know.
Choose sources → to get a library of your own and a daily brief.