Explore

Store skills by meaning via embeddings, not plain text

The most important thing when storing skills is capturing the meaning of the sentences and what the skill means itself, rather than having it as text. Storing a skill as plain text in a file on the file system limits agent interaction to keyword or regular-expression word search; regular expression matching (like grep) is inefficient for huge files, and if the file system grows linearly, the performance of regular expression matching decreases quadratically, so it doesn't scale with file size. Pre-computing embeddings of a skill captures hidden meaning between tokens that text descriptions alone do not; embeddings are typically 384 minimum to a thousand-plus dimensions and make skills much more discoverable by semantic search.

speaker's argument; dimension figures are approximate

AI Engineer · Memory-Aware Agent Harnesses for Anti-Money Laundering — Nacho Martinez, Oracle

Single agents struggle researching long ticker lists; flows split work across isolated scan agents

A single agent struggles when it tries to research each ticker on a list by itself. With flows, split up the list of tickers and pass each ticker to a scan agent, giving each scan agent an isolated context where all it cares about is its one ticker, so it isn't influenced by other tickers or search results. After the scan phase completes, pass results to the next phase (review), which is its own isolated context.

AI Engineer · Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic

Tiered evaluation benchmarks reveal true generalization

Design ML evaluation benchmarks with multiple difficulty tiers that vary chemical similarity — from shared building blocks, to shared hub only, to completely different libraries — to reveal true generalization. In the Kaggle competition, the winner performed okay on shared-building-block splits, saw some boosts on shared-hub splits, but no one beat chance on the completely different library split. Models that win on chemically similar test splits may fail completely on distribution shift — three of the top five entries were the noisy tutorial notebook.

Latent.Space · Lab-in-the-Loop at Compute Speed — Ian Quigley, Leash Bio

One trifecta capability is usually fine; two is risky; all three is never acceptable

Having any one of the lethal trifecta capabilities is usually fine, because realistically your AI tool won't be very useful if it can't have access to any of these things — though even one can lead to disaster if you're not careful and the rest of your infrastructure has a lot of issues. Having two together is risky and not something Jiang would recommend, especially in a regulated industry like banking or financial services. Giving agents access to all three at the same time is never acceptable — not for a prototype, not just for one sprint, not for just one repository — because that combination of vulnerability is an open door to compromise your whole organization.

AI Engineer · Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder

Zero-trust approval: agents cannot approve their own changes; approval must come from someone else

Agents cannot approve their own changes, and the engineer who prompted the agent is also not the approver. Ensure the approval comes from someone apart from the bot that was prompted by the same person. The control is making sure the change was approved and tested by someone who did not write it.

AI Engineer · Rebuilding CI for AI-Scale Commit Volume — Gautam Korlam, Sonar

Only allow commits onto the trunk if they pass CI in combination with all incoming commits

Only allow a commit onto the trunk if it passes CI in combination with all other incoming commits — this keeps the trunk green.

AI Engineer · Rebuilding CI for AI-Scale Commit Volume — Gautam Korlam, Sonar

For hypertrophy, at least one of frequency, intensity, or volume must be high

Dr. Andy Galpin states that to succeed at hypertrophy you only need to make sure the training is hard enough, and that as long as one of the three variables — frequency, intensity, or volume — is high, you will achieve hypertrophy. The only wrong combination is infrequent training combined with low intensity and low volume. This makes crafting a hypertrophy program fairly simple: you just have to make sure you do the work.

Andrew Huberman · Essentials: Optimal Protocols to Build Strength & Grow Muscles | Dr. Andy Galpin

Chaos management: adapt disrupted workouts to your goal

Dr. Andy Galpin explains that your goal (hypertrophy vs strength) determines how you manage disrupted workouts — what he calls chaos management — and that 10% to 50% of your workouts will be chaos management situations (short time, hotel, not feeling it). For hypertrophy when short on time: lower the load, lower the rest intervals, and just get to the burn and get going as much as you can to hit total volume. For strength when short on time: cut your volume in half, get the few repetitions done at high load, and just don't do very many sets that day. He gives the example of a plan that normally takes 60 minutes when you only have 35 minutes available.

Andrew Huberman · Essentials: Optimal Protocols to Build Strength & Grow Muscles | Dr. Andy Galpin

Volume targets: 10 sets minimum, 15–20 realistic, ~25 for the well-trained

Dr. Andy Galpin lays out weekly working-set volume targets per muscle group: the minimum is 10 working sets per week; a more realistic number for most people, especially intermediate or advanced, is 15 to 20; very well-trained individuals should push toward around 25. He notes that past 25 working sets per week there is not a lot of research. He illustrates how easy the minimum is: three sets of 10 done three days a week gets you to nine working sets — almost 10 — and going to the gym one day a week doing three sets of 10 across three exercises also yields nine. Hitting 10 sets per week per muscle group is fairly easy (not even counting indirect activation of secondary muscles), and hitting 20 is actually still not that hard.

Andrew Huberman · Essentials: Optimal Protocols to Build Strength & Grow Muscles | Dr. Andy Galpin

If sets aren't hard enough, rep range doesn't matter — get close to failure

Dr. Andy Galpin explains that if you're not seeing adaptations despite adequate volume, the repetitions in your sets may not be hard enough. A set of 25 that only starts getting hard at the end is not enough stimulus — and neither is a set of five or six that feels the same way. When sets aren't challenging enough, the rep range itself doesn't matter; the effort within the set is the issue. Rep range doesn't matter if you're not getting somewhat close to failure, though sets don't need to go to complete failure.

Andrew Huberman · Essentials: Optimal Protocols to Build Strength & Grow Muscles | Dr. Andy Galpin

Match kickoff tone to team performance — never fake rah-rah when reps are missing quota

When the team isn't winning, Katie Givens recommends a 'true grit' perseverance theme that acknowledges it's harder to be excited, focusing on pushing barriers out of the way rather than fake enthusiasm. She says never plan a massive celebration kickoff when reps are missing quota because reps feel the fake theme — their pay is tied to winning. In a losing locker room, run a session where reps feel heard about what's getting in their way, with an honest conversation about why. In a down economy, use a chip-on-your-shoulder 'we're gonna get this done' tone instead of a tone-deaf celebration, while still celebrating individual successes.

Presented as the guest's design philosophy from experience.

30 Minutes to President's Club | No-Nonsense Sales · #612: Sales Kickoff Masterclass: The Ultimate Planning Guide

Fold the year's first QBR into kickoff so reps leave with concrete plans

Fold the rep's first QBR of the year into kickoff itself, while the theme is fresh and reps are fired up and undistracted, so they launch into the year immediately. Teams that don't do QBRs at kickoff suffer a post-kickoff delay because reps return without proper account plans and spend time re-orienting instead of selling. Structure a QBR as: retrospective on last quarter (numbers, misses, wins, three biggest lessons learned or a start/stop/continue), then forward plan — this quarter's number, the gap, and three to five very specific goals. Make goals hyper-specific with the format 'I will make X calls by X date to X customer' — never vague goals like 'I'm just going to make some more calls.' In QBRs, have reps deliver in-depth account planning on their top three to five deals to peers —

Presented as recommended design; the delay claim is the speaker's observation.

30 Minutes to President's Club | No-Nonsense Sales · #612: Sales Kickoff Masterclass: The Ultimate Planning Guide

Limit teaching to one focused concept per day, delivered interactively by multiple voices

Limit the kickoff teaching agenda to one heavily-focused concept per day — reps won't remember material if you try to teach everything at kickoff. Put more than one person on stage during teaching moments so attendees hear different points of view and avoid enablement-person fatigue. Talking at attendees for hours is a fatal flaw: even with a room of 1,100 reps, build in interactive elements. Roughly four hours of the general session day go to the single new concept, broken into multiple sessions with breaks and lunch in between.

The four-hour allocation is the guest's described practice.

30 Minutes to President's Club | No-Nonsense Sales · #612: Sales Kickoff Masterclass: The Ultimate Planning Guide

Put customers and prospects on stage together — the prospect always converts

Put customers and prospects on stage together at kickoff: the prospect always converts when they hear a customer validate the value. Pair later-stage prospects with customers facing similar challenges and ask them hard questions. Prep panelists beforehand, ask hard questions, and use a strong moderator — a CSM paired with a rep works well because they understand different go-to-market angles. Always open the panel for Q&A; customers and prospects get excited to participate and often want to stay and mingle afterward.

'Always converts' is the guest's emphatic claim from experience, not a measured rate.

30 Minutes to President's Club | No-Nonsense Sales · #612: Sales Kickoff Masterclass: The Ultimate Planning Guide

Define straight-through processing inside a named boundary

Finance already has a useful term for no human intervention: straight-through processing. Define it as a complete end-to-end without human intervention inside a boundary you name — the boundary could end when the code is drafted, when the pull request is approved, or when the change reaches production.

None stated; presented as the host's endorsed definition.

AI Engineer · What Technical Due Diligence Finds When the Deck Says “70% Automated” — Soukaïna Abelhad

The first check is pure arithmetic: workload volume vs fully loaded human labor

The first check requires no knowledge of models; it is pure arithmetic. Put workload volume next to fully loaded human labor, counting everyone whose work exists because of AI — operators, reviewers, trainers, escalation, and rework.

None stated; presented as the host's endorsed first check.

AI Engineer · What Technical Due Diligence Finds When the Deck Says “70% Automated” — Soukaïna Abelhad

The three checks together: arithmetic, definition, and the tell

The three main checks are: one, the arithmetic — compare workload volume with fully loaded human labor; two, the definition — identify the wrong one and request the straight-through rate inside a named workflow; three, the tell — ask who defines quality, whether the expert agrees, and what bad output escapes. Always put those checks together.

None stated; the host's summary of the framework.

AI Engineer · What Technical Due Diligence Finds When the Deck Says “70% Automated” — Soukaïna Abelhad

Even surviving claims must survive the economics; compute cost per accepted autonomous task

Even when a claim survives the checks, it still has to survive the economics. Start with eligible workflow value, apply actual adoption, straight-through process success, and accepted quality; then subtract the cost of AI, human review, escalation, and rework. If the task fails, escalates, or needs rework, that belongs to the cost. The metric Soukaïna would want is cost per accepted autonomous task.

None stated; the host's endorsed economic framing.

AI Engineer · What Technical Due Diligence Finds When the Deck Says “70% Automated” — Soukaïna Abelhad

Evaluation maturity is the first credibility signal; ask who labeled ground truth and what bad output escaped

Evaluation maturity is the first credibility signal to look for. Always ask who labeled ground truth, whether the expert agrees, whether anyone measures that agreement, what the automated judge was validated against, and what bad output escaped.

None stated; presented as the host's endorsed third check.

AI Engineer · What Technical Due Diligence Finds When the Deck Says “70% Automated” — Soukaïna Abelhad

A building record must answer what changed, when it changed, and who needs to know

A record must answer what has changed: compare two walks of one space object by object and surrounding by surrounding. It must answer when it has changed: every observation carries and captures where it came from. And it must answer who needs to know about observed deltas, so stakeholders can be informed and counteract — e.g., when structure damage is found with evidence, the responsible party needs to know and counteract, and when fire extinguishers are found expired, that fact must be surfaced so it can be acted on.

None stated.

AI Engineer · Every Building Is a Balance Sheet: Spatial Memory for Real-World Assets — Jordi Spranger, Spranic