Explore

Construct a knowledge graph from unstructured text: gather, chunk, vectorize, extract, generate

To construct a knowledge graph from unstructured text: gather data sources, chunk the data, vectorize it, extract nodes and relationships, then generate the graph. Use an LLM to extract entities and relationships from text chunks to cut down extraction time, prompting it with: 'Your task is to identify the entities and the relationships requested with the prompt from a given text. And then you must generate the output in a JSON format containing a list with JSON objects.' Then parse the LLM's entity and relationship output as JSON and generate the graph from it.

Method, not a verified protocol.

AI Engineer · RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j

Multi-phase agent pipeline: discovery, review, PRD, implementation, acceptance

The creator describes a multi-phase agent pipeline flow: a cron-scheduled discovery agent runs first, the developer reviews via slash command, a PRD-generating PM agent scopes the feature and generates a plan, Copilot implements it, and the developer returns at an acceptance phase to evaluate whether to take the code into the project.

Method, not a verified protocol.

AI Engineer · From Your Laptop to the Pipeline: Scaling Custom Agents with GitHub Copilot

Running agents in the pipeline: headless CLI one-shot prompts in CI, triggered on events or schedules

Use the agentic workflows framework to run agents as part of the repository rather than locally. Call the Copilot CLI in headless mode with the dash P command to pass a single one-shot prompt for it to go do. Run that inside a GitHub Actions runner or CI system to get an agent running in the pipeline. Trigger pipeline agents on repository events, such as updating documentation on a release, or on a weekly schedule to update context files.

Method, not a verified protocol.

AI Engineer · From Your Laptop to the Pipeline: Scaling Custom Agents with GitHub Copilot

Context-building flow: route, check skills/memory, then cache-first data selection with live fallback

The flow: a prompt comes in and gets routed to the right agent; the agent checks memory/skills; if a skill or memory match exists, use it instead of proceeding to data selection — and if the skill doesn't need external data, just generate a response and send it right back. When there is no skill or memory match, go right to data selection: first check the cache or synced data store and ask if the data is fresh and within your SLAs; if cached data is fresh enough, use the cache context; if not, call the live API. Loop through the context-building process a few times until enough context is accumulated, store a memory of whatever you just discovered or figured out, then generate the response and send it back to the client.

Method, not a verified protocol.

AI Engineer · Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge

The eval flywheel: define success, capture signals, diagnose gaps, act, repeat

A four-step loop: (1) define success from the customer's perspective; (2) capture signals — get as much instrumentation, metrics, and data as possible about what customers are doing, and talk to customers directly since data alone can be misleading; (3) diagnose gaps by collecting and categorizing all customer signals; (4) feed categorized gaps into decisions — prioritize them and ask science, engineering, and product teams to address them — then repeat the loop continuously.

Method, not a verified protocol.

AI Engineer · Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab

Playing the animation and applying ease-in, ease-out

Mickey demonstrates pressing the space bar to play the animation, selecting between two keyframes to see the easing of the interpolation in the properties panel, and dragging the Bezier handles to turn linear easing into an ease-in, ease-out. He explains ease-in, ease-out makes movement start from a stop, gain speed, then slow down, so the movement looks more realistic.

Method, not a verified protocol.

Figma · Figma for Edu: Prototyping with animations in Figma

Nest animations as components inside frames, as many levels deep as you want

You can nest animations as a component by placing an animated component inside another frame, and you can nest animations as many levels deep as you want; a frame containing an animation can be extracted from its parent and used on its own.

Method, not a verified protocol.

Figma · Figma for Edu: Prototyping with animations in Figma

Rank your ten life priorities and audit whether effort matches the ranking

Order the ten life elements (community, romance, parenting, family, recreation, friends, career, physical health, spiritual health, personal growth) for yourself. Then check whether your actual effort allocation matches your stated ranking — if a priority is ranked #2 but gets 2/10 effort, it's misaligned. Identify which ranked priority is off and act on the gap immediately.

Method, not a verified protocol.

Alex Hormozi · It took me 37 years to realize what I'll tell you in 18 minutes.

Shoulder-safe pull-up technique

A locally coherent method for pull-ups: (1) at a dead hang, pull down first to depress the scapula, then pull up — that's the ready position; (2) on the way down, maintain tension throughout the scapula and shoulder girdle so you don't fall back into the traction-stress position; (3) treat every rep a little slower on the way down and don't avoid full extension at the elbow. Letting the shoulders ride up at the bottom undoes the stable position and reintroduces traction stress.

Method, not a verified protocol.

ATHLEAN-X™ · 7 Exercises That Are Making Your Shoulder WORSE

Shoulder-safe overhead press setup

A locally coherent method for overhead pressing: (1) keep pressing overhead but do it better; (2) narrow the hand positioning on the barbell to bring the elbows from out to the side to more in front of the body and into the scapular plane, which also adds a bit more triceps contribution and helps you get overhead in a more free and mobile position; (3) with dumbbells, bring the elbows in to about 45 degrees rather than flaring them out to the side; (4) press one dumbbell at a time and lean slightly under the pressing dumbbell so the wrist is supported by the elbow and the elbow by the shoulder, creating a stacked joint for more stability; (5) slow the pressing speed, which combined with joint stacking regains shoulder stability and makes the pain go away.

Method, not a verified protocol.

ATHLEAN-X™ · 7 Exercises That Are Making Your Shoulder WORSE

Correct dip setup and execution

A locally coherent method for shoulder-safe dips: (1) set up by pushing down and engaging the serratus with the chest out rather than sinking down; (2) pull the shoulders down away from the ears to create greater distance between ears and shoulders, the same as with the pull-up; (3) control depth to about 90 degrees at the elbow rather than going all the way down, since going deeper pitches the shoulder more forward and stresses the anterior capsule; (4) at the top, push high rather than letting the shoulders drift back up, and finish with a 'dip plus' by pushing through with an extra plus at the end of the ascent. Getting the chest out allows a better stretch without going too deep.

Method, not a verified protocol.

ATHLEAN-X™ · 7 Exercises That Are Making Your Shoulder WORSE

Cold approach to insta-date: the full arc

A complete method for a daytime cold approach: stop the woman and get her attention, deliver a slow relaxed opener with a smile, carry the conversation playfully, then around the 2.5-minute mark assess her availability and lead her to a nearby coffee spot.

Method, not a verified protocol.

Coach Kyle · From Hi to Coffee Date (LIVE DEMO)

Structure long-running Codex tasks with goals, milestones, and audits

Gabriel Chua's method for long-running tasks: use the define goal skill from the OpenAI skills repo to define a goal, but don't create one goal — create a series of goals in a goals.markdown file you can inspect; have Codex create a progress-dashboard.html so you can see what's happening during a multi-hour run; rather than one thread doing all the work, have Codex spawn new threads at milestones; and at different milestones have it run code review and a goal audit that checks whether it is deviating from goals.markdown, nudging the main thread back or prompting a plan rethink. He notes GOAL is one of the primitives that is incredibly powerful if used in the right way.

endorsed

Method, not a verified protocol.

AI Engineer · Cooking with Codex — Charlie Guo & Gabriel Chua, OpenAI

Revealing the job: four questions and a job statement

Kent walks through a method for revealing the job to be done: ask who is this for (attendees and whoever mans the door), when does this problem happen (when people are getting into a workshop), what progress do they want (just get in to the workshop), and what do they do currently (a QR code scan, a blocking request). Then write the job statement in the form 'When [situation], help me make progress so I can [desired outcome],' often adding 'without [something]' — e.g., 'When there's a workshop going on at 10110, help me get into the workshop quickly so that I can learn about product engineering without missing the first 20 minutes.'

Method, not a verified protocol.

AI Engineer · Build the Right Thing: Product Engineering (Part 2) — Kent C. Dodds, EpicProduct.engineer

Turn feature requests into job statements via why-questions

When a feature request comes in, ask 'what are you trying to solve?' as your first question back to the requester. Ask 'why' repeatedly to dig past the requested feature and find the underlying problem. Ask 'who is this for?', 'when does this problem happen?', 'what progress do they want?', and 'what do they do currently?' to reveal what the job is. When writing a job statement, add 'without [undesired outcome]' to capture what the user wants to avoid. Example job statement: 'When there's a workshop going on at 10110, help me get into the workshop quickly so that I can learn about product engineering without missing the first 20 minutes.' The job statement has nothing to do with the requested feature (facial recognition). Getting down to the why-why-why and turning that into a jobstatement

Method, not a verified protocol.

AI Engineer · Build the Right Thing: Product Engineering (Part 2) — Kent C. Dodds, EpicProduct.engineer

Open coding then axial coding of agent traces

First pass: read each trace and write down what you see in natural language ('vague recommendation', 'made up a number', 'wrong ticker') without pre-categorizing. Second pass: group similar open codes into categories (axial coding). Each root cause points to a different fix — if you don't know the cause, you can't pick the right remedy.

Method, not a verified protocol.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Run faithfulness evals by attaching research context from traces

The speaker described running faithfulness evals in code (rather than the UI) when using the SDK: extract the research context — the output of the first research step — from the traces, attach it to all spans as context for the judge, then run the faithfulness evaluator, which asks whether, based on that same information, the agent did a good job writing the report. This puts the judge on a level playing field with the agent, unlike correctness evals for live-search agents.

Method, not a verified protocol.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Run online evals on sampled production traffic

You're not done when the dev experiment passes — you're done when the agent keeps performing on unseen production traffic. Run your evaluators (ticker check, faithfulness, actionability) automatically on incoming production traces, at trace level so the evaluator sees the full tree, and sample 10% or 1% of traffic for directional signal without an expensive LLM judge on every instance.

Method, not a verified protocol.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Split labeled data into a dev set and a held-out test set to verify the judge generalizes

Laurie Voss recommends splitting labeled data into a development set (about 75%) used to iterate on the eval until the judge agrees with you, and a held-out test set (about 25%) used to verify the judge gets expected scores. Holding out a test set shows the judge is generalizing to new examples instead of just fitting the specific data set, and he warns not to overfit the evaluator to the golden data set — the same principle as train/test splits in machine learning.

Method, not a verified protocol.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Four parts of a custom rubric: role, criteria, data labeling, output choices

The speaker recommends four parts for a custom rubric: define the judge's role, spell out explicit pass and fail criteria, label the data with XML tags, and define the output choices outside the prompt itself.

Method, not a verified protocol.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI