Creator perspective · MoneyJim Clark notes that in an hour of agent work, the agent might need his Git signing keys for only about two minutes of that time. When committing, the agent needs the Git commit tree, the ability to make the commit, and signing keys — but nothing else. He would like the sandbox an agent runs a task in to be modeled after the intent of what the task is doing: if the agent is not making a commit, commit signing keys should not be inside that sandbox. If agents know the intent of what you're trying to do, use that intent to model the capabilities you give them.
AI Engineer · How Many Credentials Should Your AI Agent Have? Zero. — Jim Clark, Docker
Principle · MoneyKeep judge output choices simple — binary is best, two clear labels. Numeric scales like 1–5 are tempting but LLMs are bad at them because they can't distinguish a three from a four. If you really need more categories, use a partial result like a 0.5 score, but by default go for zero or one. Under the hood the judge is given a tool it calls with correct or incorrect, so you don't need to specify output in the prompt.
AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI
Principle · MoneyIn the demo, the correctness eval scored zero on every row — it completely failed. The correctness eval failed because it judges against the LLM's training data, while the agent used live web search for current 2026 stock prices the judge couldn't possibly know. Don't use a correctness eval when your agent uses live data beyond the judge model's training cutoff — it will complain about information from the future it couldn't know. Instead, use a faithfulness eval when your agent uses live data, because the judge actually has context and is on a level playing field with the agent.
AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI
Creator perspective · MoneyKnow which of your evals are guardrails (ship blockers) and which are North Star metrics (aspirational), because it changes how you act on results and set up production monitors. Some evals are guardrails and ship blockers: if an agent hallucinates a stock price, that is a hard fail — don't ship. A guardrail regression should page someone in the middle of the night. A North Star metric dip is something you look at in a weekly report.
AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI
Creator perspective · MoneyDon't build a single 'God evaluator' that checks accuracy, tone, completeness, policy compliance, and formatting all in one prompt — it is a nightmare to calibrate. A God evaluator that fails makes it impossible to know which of its five dimensions failed. Having a God evaluator emit 15 different labels becomes too complicated to judge or score by. Split evaluation into one evaluator per dimension instead of one mega evaluator; the combination gives a richer picture than any single eval.
AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI
Principle · MoneyThe next step after knowing what's wrong is code evals — no model configuration, no API calls, just Python. A code evaluator is a simple Python function that returns an evaluation result with a label and a score; it needs no LLM and no API call and returns instantly. Code evaluators are completely deterministic functions that take input and output and decide whether the output is good according to some definition of good — anything with grading logic that always gives the same answer for the same input can be a code evaluator. A code eval doesn't have to be a simple string operation — the grading logic just has to be deterministic; it can query a database or hit an API. Use simple deterministic code evaluators as the first line of defense in your evaluation stack (Swiss cheese model).
AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI
Principle · MoneyTreat renewal as a commercial milestone where you present accumulated value evidence and ask for more (years, business units, products). Never ask for more money at renewal if you've only met the account cold — e.g., second meeting in eight months — without demonstrated value; that's like a stranger knocking on the door selling old brooms.
30 Minutes to President's Club | No-Nonsense Sales · #604 - Upsell & Expansion Masterclass: 7 Lever to Grow Any Account
Principle · BodyThe single governing rule: the moment the kettlebell hits the floor, the challenge is over. Resting is allowed only by holding the bell (goblet hold or clean position), never setting it down.
iamariankanani · https://www.instagram.com/reel/Dcbq4SHSbew/
Principle · MoneyThe four key things that impact valuation for a B2B SaaS business, in order, are growth, ARR/revenue, churn, and profit. Founders should optimize them in this order.
MicroConf · When to Sell Your SaaS Business: How to Get a 5x Better Offer
Creator perspective · MoneyTara Seshan states that the core of the PM role has always been about asking the most essential question about your product: what determines whether it works or not. Many trappings of the job (execution on time, writing docs, presentations) have fallen away, and the hypothesis definition and testing loop has become the most important thing at the company. Everyone (EMs, engineers, data scientists, designers) now focuses on this.
Lenny's Podcast · AI’s third era: the rise of persistent AI coworkers | Tara Seshan (OpenAI’s product lead)
Recommendation · MoneyLakshya A. Agrawal advises bringing actionable side information and surfacing as much domain-specific information as possible to optimizers, because optimizers of the future will be able to work with it.
AI Engineer · Beating RL With Reflection: GEPA and Optimize Anything — Lakshya A. Agrawal, GEPA
Recommendation · MoneyLakshya A. Agrawal advises using a language model or agent to reflect on the entire rollout trace — what worked and what did not — instead of relying only on a zero-or-one reward signal.
AI Engineer · Beating RL With Reflection: GEPA and Optimize Anything — Lakshya A. Agrawal, GEPA
Recommendation · MoneyRoman Ugarte recommends delegating day-to-day work tasks to AI bots to focus on higher-leverage activities, and delegating completely — trusting the bot to finish without oversight rather than partially supervising. He argues that when you only 90% trust a teammate you still carry the mental load, so the aim is 100% trust to truly delegate.
Lenny's Podcast · How we built Grok Bot in a month | Roman Ugarte (SpaceXAI)
Recommendation · BodyThe creator advises prioritizing the face pull before leaving the gym, an exercise most people relegate to last or skip entirely, because what you do after your workout determines whether it was great or a missed opportunity.
ATHLEAN-X™ · Do This AFTER Every Workout (NON NEGOTIABLE!)
Recommendation · MoneyHassan El Mghari recommends having an expert human in the loop when building AI agents in specialized spaces, because domain expertise catches what engineering checks miss.
AI Engineer · Right Answer, Wrong Reasons: AI Forecasts Costco - Hassan El Mghari & Omar El Mghari, Together AI
Recommendation · MoneyHassan El Mghari recommends having models write structured data (like formulas in JSON) instead of having them do the math and do everything all at once.
AI Engineer · Right Answer, Wrong Reasons: AI Forecasts Costco - Hassan El Mghari & Omar El Mghari, Together AI
Recommendation · MoneyAamir Shakir recommends first making search really good before scaling up your model or data.
AI Engineer · Better Search Took This AI Agent From 36% to 98% Accuracy - Aamir Shakir, Mixedbread
Recommendation · MoneySnyder recommends that founders be the ones doing the selling, especially in a startup during zero-to-one product discovery. For non-founders doing zero-to-one work, he recommends focusing on trying to sell the thing and learning through selling. Getting lost in zero-to-one work is a real risk that selling-focused learning protects against.
Lenny's Podcast · How to find product-market fit (but, actually) | Rob Snyder (Author, The Power of Pull)
Recommendation · MoneySofia Jakovcevic recommends closing the loop between what coding agents produce in the IDE and what is actually happening in the observability backend, by connecting coding harnesses and coding agents with what is actually happening in the production database. This gives agents full understanding of what changes are actually making.
AI Engineer · Your Agent Fix Just Broke Something Else - Sofia Jakovcevic, Arize AI
Recommendation · MoneyThe first stage of building a personal brand is to do something epic — in terms of volume or a quality outcome — before anything else.
Alex Hormozi · How I Would Build a Personal Brand in 2027 (If I Had to Start Over)