Recommendation · MoneyBe violently yourself with all of your idiosyncrasies, quirks, and atypical ways of behaving, and accept them as obviously different — in so doing they make you exceptional. X factor typically comes from a level of agency of self-acceptance: stars like Dolly Parton and Joe Rogan are willing to accept themselves as they were and just say, this is what I'm into. By accepting yourself as you are, people either admire that level of courage or see a part of themselves in you.
Alex Hormozi · If I Started A Personal Brand In 2026, I'd Do This - Dolly Parton
RecommendationAnthropic's advice for building agent evals is to get high-quality data to evaluate over, iterating on your data and making sure the problem is set up correctly. They warned that garbage in, garbage out: ill-defined eval ideas can yield 100% scores that mean nothing about performance. They suggested looking at historical sessions and their results, then scoring them, as a good way to build an eval dataset. They noted Claude Code is pretty good at building an eval for you, and that while this is not an out-of-the-box solution, it is generally the advice that has worked.
AI Engineer · Claude Managed Agents Q&A: Evals, CI/CD and Multi-Tenancy (Part 4 of 4) — Anthropic
Recommendation · MoneyUse boundaries and separate dev, staging, and production environments as in the normal software lifecycle. AI agents should never touch production directly — only through monitored CI/CD pipelines with safety controls in place.
AI Engineer · AI Security Engineer Foundations + Certificate — Javier Garza, Snyk
Recommendation · MoneyAlways put a human in the loop for approvals for things like deployment to production or dangerous operations such as deleting a database or making a user root.
Also discussed by The a16z Show (unclassified source — not counted until classified). Not counted as independent sources.
AI Engineer · AI Security Engineer Foundations + Certificate — Javier Garza, Snyk
Recommendation · MoneyThe hosts advise maintaining evaluation criteria over time so evaluators don't over-index or stop providing meaningful information, and maintaining the evaluation dataset because initial assumptions about user behavior will miss unaccounted-for edge cases; they emphasize dataset maintenance as the most important part of continuously improving an agent.
AI Engineer · Continuously Improving Agents with Langfuse — Annabell Schäfer & Lotte Verheyden, ClickHouse
Recommendation · MoneyWolfram Ravenwolf recommends inspecting and controlling the system prompt because it is a very important evaluation factor. Telling an agent 'you are a helpful assistant' vs 'you are an autonomous agent' produces very different benchmark results.
AI Engineer · From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Recommendation · MoneyWolfram Ravenwolf recommends an isolated sandbox for each task, which is super important, because otherwise you would change your own system with every evaluation run and results would be even more random.
AI Engineer · From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Recommendation · MoneyWhen choosing a model, you want a very high ceiling, a very stable average, and a very high solid base. When two models have almost the same average score, pick the one with the higher solid base. Also look at worst and best scores in addition to averages, and check what percentage of benchmarks a model can solve at all and how consistently.
AI Engineer · From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Recommendation · MoneyWolfram Ravenwolf recommends running agents in a sandbox instead of locally on your own system, because running locally causes interference between runs and corrupts results. Docker is a very common option, and cloud sandbox providers exist when Docker is hard to parallelize on your system.
AI Engineer · From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Recommendation · MoneyUse both graph and vector approaches together rather than choosing one over the other. Graph is not going to completely replace the vector layer; the recommendation is to add graph on top of vector and use the benefits of both. A mnemonic for remembering retrievers: they are like a golden retriever that fetches the necessary information.
AI Engineer · RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j
Recommendation · MoneyUsing both is actually the key: use both graph and vector rather than replacing the vector layer with a graph. Vector-only RAG and vector-only databases fall short on tasks requiring node traversal and historical context.
AI Engineer · RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j
Recommendation · MoneyJosh Woodward stresses getting outside the building and showing people prototypes as the way to evaluate product-market fit, rather than relying on internal debate.
Lenny's Podcast · Why every company now needs to think and operate like a lab team | Josh Woodward (VP Google Labs)
Recommendation · MoneyJosh Woodward advises that finding product-market fit is a numbers game: you have to take a lot of shots, throw yourself out there, and try to live in the future a little bit to chase it. He acknowledges that sometimes you get excited and build a product that's just not good — that's part of the game.
Lenny's Podcast · Why every company now needs to think and operate like a lab team | Josh Woodward (VP Google Labs)
Recommendation · MoneyPatterson's third pillar of agentic security: restrict what the agent can access with tightly sculpted credentials and restricted permissions. He warns that teams generally give agents access to everything because 'it needs access to do the work,' violating least-privilege principles, and that assuming AI won't make human mistakes leads to over-permissive access even though AI is exploitable by the same vulnerabilities.
AI Engineer · The Lethal Trifecta Is Already on Your Laptops — Michael Patterson, Coder
Recommendation · SocialThe host urges viewers to develop the courage to be ridiculed, presenting it as one of the core traits of charisma drawn from Trump and Mamdani, and encouraging people to learn it from both regardless of whether they love or hate them.
Charisma on Command · The 3 Traits That Make You Impossible to Ignore
RecommendationThe best guidelines come from watching what the agent makes, noticing where it needs more direction, and tightening things up as you go. When the agent produces off-system output, tighten the guidelines rather than adding instructions to each prompt.
Figma · Teach Figma's agent your design system | Add guidelines to your Figma library
Recommendation · MindHormozi's culminating advice: play your own games of your own design, where if you were to win, you would be happy with the W, and the price it came at was one you were willing to pay.
Alex Hormozi · a video to watch if you're ambitious and in your 20s or 30s
Recommendation · MoneyAnish Acharya advises founders to start shipping and let their moat develop over time rather than trying to design it upfront. He pairs this with the script 'Moats are most often discovered, not designed,' warning against overthinking upfront strategy.
Lenny's Podcast · Why companies are becoming a series of loops | Anish Acharya (a16z)
Recommendation · MoneyAnish Acharya distinguishes between merely using AI and reorganizing your entire company around AI, recommending the latter. He suggests asking: if AI were infinitely intelligent and astonishingly cheap, how would you reorganize the company? He also says to give the average employee more credit for embracing AI tools, citing a 'Jedi Academy' concept where everyone at a company, including mechanics, is taught to use the new tools.
Lenny's Podcast · Why companies are becoming a series of loops | Anish Acharya (a16z)
Recommendation · SocialWhen an interaction is going well, move it forward by asking when she's free rather than staying in small talk; many guys get into good interactions but fail to do this, wasting momentum.
Coach Kyle · From Hi to Coffee Date (LIVE DEMO)