Use agentic search for complex qualitative multi-hop queries
Aamir Shakir recommends using agentic search for complex qualitative queries, which runs multiple queries to support multi-hop reasoning.
33,794 results · Most relevant
Aamir Shakir recommends using agentic search for complex qualitative queries, which runs multiple queries to support multi-hop reasoning.
Kumar recommends keeping tools like AlphaSense or Yipit but bringing them into an internal platform that learns from analysts' habits and is programmed specifically for each individual analyst and their model pattern. The goal is to bring all the tools different analysts use into one platform and up-level the existing spend, increasing the value of data subscriptions by continuously learning from all the different types of data and model updates, leveraging the MCPs and APIs these companies offer. He adds that as AI adoption increases, especially at smaller fundamental shops, having one unified layer doing many different tasks across analysts will be really valuable.
Arcolano recommends getting to 30+ runs of using skills per engineer per week, which yields a 30% bump in PR throughput holding other factors constant — a bigger effect than model choice. Skill use includes cursor rules, harness customization, and tricks of the trade that must be learned.
Measure what the finished job cost and how long it took, including retrieval, tool calls, and retries. If a person must fix the report before use, count that human work in the cost of producing the acceptable report. Include all the failed attempts in the cost of producing the acceptable report. Measure the cost of reports that users can actually use.
Chris Dreyer obsesses about personal injury law — he has books over his shoulder on personal injury lawyer marketing and personal injury lawyer intake. He hosts a Personal Injury Lawyer Mastermind podcast with 450-something episodes, runs a newsletter with several thousand subscribers, and is launching a print magazine and conference (PEMCON). He advises building an ecosystem of niche content to understand who your customer is, what their problems are, and how you can provide more value.
Gary Vaynerchuk's prescription (advice to Amber, generalized to the audience): make organic social media content over and over and over again, in as many different ways as possible, across Facebook, Instagram, TikTok, YouTube Shorts, and LinkedIn, using different thumbnails and different hooks — with complete insane psycho discipline.
Consequential creator advice requires independent verification before Today can promote it.
GaryVee identifies hyper-local Facebook ads targeted to a 10-mile radius of a physical location as the biggest opportunity for a local business to drive foot traffic and increase average receipt size.
The guest's formula for winning on Snapchat Spotlight is to first win organically, then post-produce the content with performance elements that match the most native elements of what is currently working on Snap.
The guest recommends subtly interjecting performance DNA (CTA, offer) into organic creative that won on brand, then running ads against it; performance creative derived from organic winners outperforms randomly generated A/B test variants, and A/B testing with AI-generated content variants is cute but inferior to organic-first validation.
Alex Hormozi advises Paul that the first thing to do in a cash crisis is generate cash. He proposes selling the baddest offer imaginable for a season pass to the list, because if you don't, there won't be a season for customers to come home to. He also says to hammer the email list with the offer because it's now or never, and to take as much cash as possible from the offer and drive it back into ads, then feed it through again.
Exa's snapshot feature lets you backtest your model and see how well it improves predictions; Exa itself is not involved in the prediction — it's just a valid, straightforward way to use version data to backtest your system.
Figure out how many of your agents can find access to production or can find some way around your current limits — this next week. Verify whether your agents are sandboxed, in managed workspaces, or running wild on people's actual computers. When reviewing AI incident stories, ask yourself: what is stopping any of this from happening to me, and are these actions ones my agents have permissions to take?
Frontier AI labs should publicly disclose whether their models have been used to attack standardized and deployed cryptography — the key question is the status of actually attacking standardized and deployed crypto, and labs should be asked what they've done trying to use their models on basic cryptography questions.
After the first 30 seconds, most interactions fizzle because men run out of things to say or panic eject. Instead, keep talking while slightly switching topic: bounce to a new yet relevant topic (e.g., from tattoo experience to her travel between cities, then to work). Staying on one topic like tattoos for five minutes lets it die and she'll politely end the conversation.
endorsed
Hormozi recommends doing a giveaway at the event: a year of scans, branded as a year of integrated health. He frames it as 'this is what we do for our VIP — enter here, and in the meantime go get a scan right now' so a line forms, and notes it's not a pressure sale. He also recommends giving away the $20K thing because you get to talk about it to everybody.
Hormozi identifies the attraction offer used as a giveaway as the big lever for getting referrals. Every time clients have their treatment, ask them who they want to bring; every single time they have a meeting, ask who they're bringing with them. Then peel off the referrals and run the sales process because they're going to be warm anyways.
The host advises focusing on the single acquisition channel with the best LTV-to-CAC ratio and doing far more of it rather than diversifying. For this business that's LinkedIn: stick with it rather than adding Facebook because there's already a proven process there. Sales reps should start every day by maxing out platform outreach limits, cloning exactly the founder's outreach, sending as many DMs as the platform allows. If the team executes the same outreach twice a day every day, productivity will go up, and since outreach is the constraint it's a good use of the founder's time.
Ross Hudgens recommends that the core simple way to influence AI visibility is to look at the source URLs that AI answers cite, and aim to be positively mentioned on as many of those as possible — or replace those source URLs by creating the content yourself.
Javier Garza recommends registering for the free Snyk tier and connecting it to your GitHub to run AI BOM scans on your private repos, running the AI BOM CLI tool on a GitHub repo to generate a CycloneDX-format inventory of all AI components (LLMs, MCP clients, MCP servers, datasets), putting the AI BOM into a central database so you can query everything a GitHub repo does, and using the AI BOM graphical user interface tool to create an inventory of all AI tools and check which ones have security issues.
The presenters recommend tagging agent traces with a 'user disagreement' score when the user pushes back on the agent's answer and an 'all caps frustration' score to capture frustration signals from production behavior, then filtering observations for traces where user disagreement is true to find interactions worth working on.
Choose sources → to get a library of your own and a daily brief.