Have models write structured data instead of doing math
Hassan 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.
34,197 results · Most relevant
Hassan 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.
Aamir Shakir recommends first making search really good before scaling up your model or data.
Snyder 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.
Sofia 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.
The first stage of building a personal brand is to do something epic — in terms of volume or a quality outcome — before anything else.
Find big moments and big external goals that you can drive towards — things that scare you and where you actually have real stakes — as belt moments.
Before deploying an agent system, Jarmak recommends explicitly identifying what level of risk you are willing to accept.
Jarmak recommends optimizing for as much observability and as realistic environments as possible where the system will be deployed, so the values you measure can actually be trusted.
Gary Vaynerchuk says that if he were starting today with no audience, money, reputation, or resources, he would make content on the internet about things he knows — for him, that would mean talking about business.
GaryVee says small business owners should ask whether each piece of content is selfish (asking for the sale) or generous (building connection), claiming that selfish content — like only posting listing photos and 'buy from me' messages — is why most businesses struggle with social media.
Alex advises focusing on only one thing when driving traffic to an offer because you don't have the luxury of time — make one bet. He chooses summer camp over season pass as the one bet because summer will make more sense. He also notes the business has one shot at getting the summer camp offer right.
Find an approach to continuously mine for signals where AI agents are going wrong, so failures don't happen again. Manual log review is not feasible at scale with increasing automation and longer traces, so scalable approaches like LLM-as-a-judge are needed, with occasional manual inspection of eval outputs.
Don't fully automate an agent with no human oversight and ask it to 'fix everything' — that produces slop, low quality, and unsatisfied customers. But also don't go the full manual way: don't instrument everything yourself or try to catch all failure modes and review all data yourself, since that can be automated. Find the ideal balance: bring your taste and domain experts in to build datasets and curate the problem and direction, work with your coding agent to automate instrumenting, failure-mode finding, and evals (e.g., 20 experiments instead of one), and gradually automate the eval loop over time. Avoid ending up in the bottom-left corner (full manual); be the tasteful AI engineer.
Pamela Fox recommends setting up bulk automated evaluations that can be reliably run and compared before putting an agent into production, with lots of test cases, and making it easy to add more test cases to the eval suite.
The faster you can multi-thread and get to power, the better — more often than not. Multi-thread laterally, not just up: get two marketing managers on the next call instead of one — double the quantity of people you call. You might have to multi-thread across before you multi-thread up — that's the more conservative path. Don't stick with an unconvinced champion for 20 steps waiting for them to be convinced — you may delay the board send, but still go get other allies in the deal cycle.
Test each agentic feature individually against cases where the outcome you care about actually happened, to check whether the system could have correctly predicted it.
Overfitting to a known evaluation set is dangerous because the algorithm likely won't succeed in the future; backtest with a holdout set, and verify performance beyond publicly visible sets since knowing the existing set enables overfitting.
The speakers recommend building up the tools that fit your own application and giving them to the models — no generic tool works for every application — and note evals will wildly differ by domain (interior design vs speed-critical businesses), with value in building them with your team.
Laurie Voss notes that before writing requirements down, different people on your team can have different ideas of what a good agent does. He advises writing down exactly what makes a report actionable: it makes a specific recommendation, names concrete risks, and looks forward not just back. A report that is factually true but lacks a concrete recommendation is not actionable.
Laurie Voss advises reading a dozen or more traces end to end before writing a single eval, because without traces a failing agent just produces mysterious output and you can't see the failing tool call. He also suggests pointing your coding agent at the traces to look for weird things, since coding agents are aces at reading traces.
Choose sources → to get a library of your own and a daily brief.