Explore intelligence

Recommendation · Social

Inject flirtatiousness early in the interaction

The coach advises injecting flirtatiousness — teasing or intent — within the first two to three minutes of an interaction rather than waiting until minute four. The student's interaction went three or four minutes with no additional teasing or intent beyond the initial open, which the coach diagnoses as lacking flirtatiousness. A flirty line like 'you could come visit me' hits harder if you've already dropped intent, push-pull, or teasing earlier in the conversation.

Coach Kyle · How to Talk to Women in Public: Real Infield Breakdown

Recommendation from Coach Kyle

Recommendation · Social

Open from a safe distance with a smile

When approaching a woman on the street, open from a safe distance so she has time to look up, acknowledge you, see you smiling, slow down, and stop before walking past. Opening too close, too quietly, and without a smile causes women to blow past you and keep walking.

Coach Kyle · How to Talk to Women in Public: Real Infield Breakdown

Recommendation from Coach Kyle

Recommendation · Money

Fix for mistake 1: empower people early by writing down principles and letting them decide

Tim's answer to the benevolent-dictator mistake is to empower people early: write down your principles and guardrails, then have the courage to let people make decisions. Make people make decisions — the earlier you start, the smaller the decisions they can begin with. If you notice you are being a benevolent dictator, stop and empower people instead.

MicroConf · Scaling a SaaS to €35M ARR: 3 Mistakes I'd Never Repeat

Recommendation from Tim van der Kasteelen

This is the speaker's personal recommendation from his own experience, not a validated method.

Method · Social

Turning a daytime approach into an instant coffee date

A step-by-step method for converting a good daytime interaction into an instant date: check her availability, lead her to a nearby coffee spot, keep the ordering phase light, then move to seated conversation.

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

Method described by Coach Kyle

Method preserved for inspection; not a verified protocol.

Method

Use side threads to unblock and monitor a long-running main thread

Gabriel Chua describes side threads: you can create one with the slash side command alongside the main thread to focus on a specific issue, and use it to give the agent targeted help (e.g., credentials for signing in) when you anticipate it needs assistance. Ask the agent in a side thread what it has done in the last hour, what it plans to do next, and whether anything can unblock it; the side thread can update the main thread with resolved information. Side threads are ephemeral and get stale, so communicate any context you want to keep back to the main thread. He also suggests asking Codex to send Slack messages — via the Slack plugin, reply to a thread with a summary of what's done, what's not, and any blockers — since blockers like authentication issues or API keys are common, and he'd

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

Method described by Gabriel Chua

Method preserved for inspection; not a verified protocol.

endorsed

Recommendation

Embed Codex into your product via AppServer

Charlie Guo recommends embedding Codex into your product using the AppServer, letting users power the product with their ChatGPT subscription and token budget.

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

Recommendation from Charlie Guo

Recommendation · Money

Go see your actual users in their real environment ('get on the truck')

Kent recommends going out and watching your actual users use your software in their real environment — his shorthand is 'get on the truck,' from a story where a boss asked an engineer whether he had ever ridden along with truck drivers using their software. Seeing users in context is humbling and reveals dozens of concrete improvements (he mentions thinking of around 30) you would never identify from your desk.

AI Engineer · Build the Right Thing: Product Engineering (Part 1) — Kent C. Dodds, EpicProduct.engineer

Recommendation from Kent C. Dodds

Method · Social

Closing sequence: implicit invitation without asking

A closing sequence where the speaker first asks what she's up to right now, then states what he was considering doing (e.g., getting coffee or tea) without asking her thoughts, creating an implicit invitation that lets her reveal availability without a direct ask.

Coach Kyle · A Realistic Approach at a Mall (Infield)

Method described by Coach Kyle

Method preserved for inspection; not a verified protocol.

Recommendation · Money

Don't turn feature requests directly into implementation

Kent advises not turning feature requests directly into implementation — including not building an app that takes a user's request, sends it to an agent, and automatically implements it, which he says would produce a terrible product with no vision, taste, or judgment. Each feature request requires your product judgment, and requests shouldn't be nailed onto the product you already have.

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

Recommendation from Kent C. Dodds

Recommendation · Money

Use a collection of all three eval types, matched to the question

Most real applications use a collection of code evals, LLM-as-a-judge, and human evaluation together. Use code evals when the answer is deterministic (format validation, length limits, forbidden phrases, required fields), LLM judges when you need semantic understanding, and keep humans in the loop for unseen failure modes and to verify judges are judging correctly.

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

Recommendation from Laurie Voss

Recommendation · Money

Read your traces and categorize what went wrong before writing a single eval

Before writing any eval, read your traces and categorize what went wrong. Figure out what to measure first. Categorize eval explanations into types of failures and count up the categories — this is called coding. If you see the same explanation across 50 different traces, you have a systematic problem, not a one-off edge case, which makes it the first thing you should fix.

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

Recommendation from Laurie Voss

Recommendation · Money

Read a dozen or more traces end-to-end before writing any evals

The speaker advised reading a dozen or more traces end-to-end — starting with the ones where something went wrong — before writing a single evaluator, asking what the input was, what the output was, and what specifically is broken.

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

Recommendation from Laurie Voss

Recommendation · Money

Use code evals for deterministic checks; LLM judges for the rest

Use a code evaluator when looking for a specific string in output (no LLM needed to check whether the ticker was mentioned). Use code evals for production-critical checks like output-is-JSON, length limits, and avoiding forbidden phrases such as 'as an AI language model'.

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

Recommendation from Laurie Voss

Method · Money

Storing and resuming agent sessions with a data pack

A demonstrated workflow: connect the MCP server to your agent and create a skill that tells it when to store memories; store the conversation in a named data pack and record incident facts as searchable memories; kill the session and resume it later from a brand-new chat window without being inside a project or enabling a special memory mode; ask the same question to verify the agent pulls prior context back out of memory. When resuming, the agent searches memory first instead of creating a new conversation, and the MCP server instructs it to create a new conversation only for storing new content.

AI Engineer · Agent Memory Is Solved. Agent Learning Isn't. — Karthik Ranganathan, Yugabyte

Method described by Karthik Ranganathan

Method preserved for inspection; not a verified protocol.

endorsed

Recommendation · Money

Get your codebase agent-ready: lightweight agents.md files as living documents

Harald Kirschner recommends getting your codebase as agent-ready — a no-brainer that everybody should already be doing. Create agents.md files that are lightweight enough and give agents a good map of the codebase — where to look at, mapping that out. These are living documents that should evolve as the agent makes mistakes and works. Teams that invested in developer experience gain a lot because good documentation and onboarding for a codebase is read by the agent as well and helps the agent as much.

AI Engineer · How VS Code Went from Monthly to Weekly Releases with AI — Harald Kirschner

Recommendation from Harald Kirschner

Recommendation · Money

Encode expert knowledge into skills, e.g. the accessibility best-practices skill

Harald Kirschner recommends creating skills that encode expert knowledge — like VS Code infusing all accessibility best practices into a skill everybody uses. Previously accessibility required one person to get pulled in or give feedback; now that skill is reviewed and maintained by the area owner of accessibility to bring that expertise into everybody's hands. Think how you can encode your expert knowledge to unlock the few users who might always be asked for this input into your skill.

AI Engineer · How VS Code Went from Monthly to Weekly Releases with AI — Harald Kirschner

Recommendation from Harald Kirschner

Recommendation · Money

Maintain your own easy-to-extend evals (VSC bench) and feed developer scenarios back in

Harald Kirschner recommends that when shipping an agentic product, it's important to have your own evals of the product always at hand and easy to extend. VSC bench is VS Code's own eval harness for their agentic product. When a GitHub issue is filed to add a new eval scenario, an agent picks it up from a template and bootstraps the scenario for you. Bring developer scenarios from issues and customer conversations back into your evals so you can start hill climbing against them. Confirm improvements offline first, then run online experimentation — a classic product lifecycle.

AI Engineer · How VS Code Went from Monthly to Weekly Releases with AI — Harald Kirschner

Recommendation from Harald Kirschner

Recommendation · Money

Pull stable authentication logic out of the model's responsibility and reuse it across operations

When the authentication workflow is stable and reusable across business operations on the same portal, pull that logic out from the responsibility of the model and reuse the same authentication mechanism for many business operations. Leaving authentication in the model's responsibility forces it to re-derive a never-changing workflow on every run, adding unnecessary steps and preventing reuse.

AI Engineer · Why 99% Accurate Browser Agents Still Fail — Derek Meegan, Browserbase

Recommendation from Derek Meegan

: none

Recommendation · Money

Give the agent a deterministic OCR verification tool to check its work in real time

Meegan recommends giving the agent an opportunity to verify its work in real time via an OCR tool that deterministically extracts entities from the document and compares them against the system of record — a deterministic mechanism so the agent knows authoritatively whether it did its job right. Deploying without such a mechanism leaves the agent unable to know whether its trajectory succeeded or failed.

AI Engineer · Why 99% Accurate Browser Agents Still Fail — Derek Meegan, Browserbase

Recommendation from Derek Meegan

: none

Recommendation · Money

Encapsulate complex multi-step operations into a single deterministic tool call

When a task involves programmatically interacting with the page — e.g., downloading a file and retrieving it from storage into the agent's runtime — encapsulate the operation into a single tool call that performs download and retrieval in one transaction, instead of the model making decisions on the fly. Leaving such decisions to the model increases steps, raising unit costs and reducing performance and maintainability.

AI Engineer · Why 99% Accurate Browser Agents Still Fail — Derek Meegan, Browserbase

Recommendation from Derek Meegan

: none