34,287 results · Most relevant
After getting an Instagram, stay in the conversation, continue the interaction as if the woman is completely free, and after a couple more minutes bring up getting a coffee or a bite to eat, then lead her to an insta-date in real time.
Structure the webinar with an intro (story/origin), three points, the offer, then an FAQ section. Review all DM FAQ buckets at the end of the webinar and answer them live on screen, and keep answering questions as long as attendees are still on the webinar.
Alex Hormozi proposes a repair sales motion: use repairs as a foot-in-the-door (repair jobs are an underserved market because competitors won't show up for small jobs, which qualifies the provider for future larger jobs, and small repair jobs typically chunk up into larger replacement jobs over time). After repair jobs, route customers to an onboarding call with Amanda (salesperson) who attempts the mini-close on additional services. Have repair customers watch a VSL before their onboarding call that explains the broader benefits of the company's services. After the salesperson walks the house, reference the VSL to the customer for additional context, which edifies the salesperson and company. The mini-close script acknowledges the customer doesn't need most items but identifies what they
A two-step consultative sales process: first unsell what the customer doesn't need to gain trust, then prescribe what they do need. The speaker reports this has been one of the most effective strategies in his business because giving a raw, authentic opinion automatically builds trust, and it increases average ticket size. He recommends it for any transactional sale that can be completed in one conversation.
Consequential creator advice requires independent verification before Today can promote it.
Alex lays out a VSL structure: intro, then a promise ('in this video, I'm gonna explain X, Y, and Z'), an amazing roof outcome, and helping the viewer avoid pains they've probably dealt with in the past. Address viewer skepticism: 'you might not believe me because you just met me. And so let me just give you some proof of Angie and Daniel and so-and-so that are all around this area have houses as big or bigger than yours. So you can feel like I work with people of your caliber.' Show the plan of how the company actually delivers the promised outcome. Include an 'old way, new way' section: the way the current industry looks is this, and our special K process is X, Y, and Z — that's why it's very different than the old way of doing things. Include objections number one through N that clients
Hormozi lays out a VSL structure: open with a promise ('I'm going to show you how we transform people's mouths'), address the pain being avoided, follow with three or four proofs each matching a different patient avatar, present the big idea by contrasting the old way with the new way, pre-handle common sales-consult objections using the structure 'this is what people think, why it's wrong, what is true, and here's proof,' and close with before-and-afters and patient reactions.
Consequential creator advice requires independent verification before Today can promote it.
Break down costs per customer customization, create customer segmentation to find which customers drive the most profit, then retool messaging, marketing, VSL examples, and scripting to attract that segment — selling only to the top segment could yield 4x the money at the same volume.
The whole process involves going through six stages: (1) spec the job and split it — for Jev, splitting some 800,000 rows into 200,000 smaller specialized cases, each into typed questions; (2) decide the failure surface — run good models on a small slice of the data, with some of it manually checked, to set a baseline you can fail against; (3) run minimal bounded pilots to test architecture; (4) once something starts working, move those checks into rigs — code that runs between bounded work segments called codons; (5) codons are reused, looped independently, validated, and placed in sequence; (6) working pipelines get deployed to production where they can slowly mature.
Spec the job and split it: for Jev, that meant splitting some 800,000 rows into 200,000 smaller specialized cases, and each of those cases into typed questions.
Find an architecture that gives a solid result, use it as a baseline, then swap models and parts for faster, cheaper options, compare against known intermediates, and tighten the requirements for success each time.
Automate accounts receivable collections with an agent — it is a universal pain point that most companies still handle manually. The playbook: send the invoice to the correct finance point of contact within 10–30 minutes of the deal closing; check whether a finance contact is listed on the contract and email the line-of-business person as primary and CC the finance contact (or vice versa); if no finance contact is listed, use enrichment to look up and guess the right finance recipient (most companies have standard AP or finance inboxes); CC multiple stakeholders on every collections invoice (contract signer, deal POC, finance contact, line-of-business owner) so someone can always escalate; have the agent monitor the collections inbox daily; send a first payment-reminder touchpoint one week
Jake's site overhaul included a full rework of structure and navigation, and a review-page template: lead with a huge image, a very short intro, and a quick summary block capturing the searcher's intent; use your own brand colors so the visual pops; briefly cover pros and cons, pricing, rating score, and size and fit (fit being super important to shoe buyers); focus on attributes that matter — stability, versatility, durability, quality; include high-quality video of actually testing shoes and show your own experience wearing them to prove you're the real deal; and give readers the meat and potatoes above the fold — everything they need in their first five seconds — without assuming every reader wants to go as deep as the creator.
On a review page, the first thing readers should see is a huge image, followed by a very short intro and a quick summary of the entire post. The summary block represents the intent of the searcher: tell readers what people care about, go through the pros and cons very briefly, and include pricing, your rating score, and size and fit — size and fit being super important to anyone who actually wants to buy a shoe. The next thing readers do is qualify themselves, such as with high-quality video of the reviewer actually testing shoes, and show your own experience demonstrating that you're actually wearing the shoes you review.
Matt Ragone lays out a five-step method for building a skill: pick a workflow you repeat, teach the agent with real cases, pack it into a skill, test it on real cases, and ship it with an owner and a reviewer. None of the steps require writing code, but every one requires knowing the work really well.
The runtime authenticates with a security token service using its app client credentials or workload identity and sends the subject token containing the user's identity and access. It creates a token exchange request asking for permission to access the MCP server for that tool call — and only that tool call. Token exchange yields three pieces of info missing from the demo: the identity of the agent requesting access, the identity of the user it acts on behalf of, and the level of access the user granted the agent. Whether the token should be issued is decided using governance policy evaluated against the requested access, the target resource, the agent's identity, and the user's identity. When everything checks out, the STS issues an access token for the MCP server, keeping the user as the
Javier Garza outlines a practical AI threat modeling workflow: first discover and map the AI system structure (e.g., with an AI-generated map, converting tool JSON output into a graphical data flow diagram, or AI-aware architecture diagrams/model artifacts), then enumerate threats such as adversarial inputs and prompt injection to ensure complete coverage. He also stresses that threat models need to evolve alongside application deployments, and that threat modeling should be integrated early when designing AI-agentic workflows because it is proactive.
The core loop runs on a real agent: detect the issue (e.g., the price-filtering bug), investigate using the Arize trace tool or through Signal, fix the issue with Claude patching the fallback, then verify. Step one is detect — surface the fallback failure before a user reported it. Step two: based on that failure and evals running in your platform, investigate what's happening with real traces. In the example, Signal and the skills via Claude Code looked at traces of a user asking for the price under $30, married that to an investigation of the code path that checks the price filter, and proposed a fix. The speaker found a bug in his own price filter code by using Signal, the trace data in Arize, and the skills via Claude Code, seeing the interaction happen with a real user and then fixing
Run the full loop: use Arize skills to create a dataset of failed traces (e.g. ~25 budget-constrained search failures), run trace analysis with Claude Code to identify the bug and prepare a fix as a PR, stand up the dev agent behind an endpoint, hit it with the failure dataset, and score responses with the same judge rubric used in production. The agent can run this autonomously — collecting failures, creating a dataset, running it against a new version of itself, and preparing a report.
endorsed
With agent experiments and the agent playground, deploy the fixed agent to dev, stream dataset inputs into it, and compare side by side what the dev agent with the fix does versus what the production agent did. Look at before-fix vs after-fix results, the judge, examples and queries, and operational metrics like latency and cost — then quantify the results of the experiment.
endorsed
To get an agent to use a graph tool, don't fight the model's prior experience — lean into it by making the graph feel like what the model already uses. Rename graph query tools to 'search' (e.g., call a tool 'query graph' just 'search') so the agent uses it naturally; if you name a tool 'search', the agent will almost always do multi-keyword search into it with no training. Meet the model halfway: name the tool 'search', account for how the model will query it, and adjust the tool's behavior accordingly. Return graph results to the model in the same tool structure and response format as ripgrep, because that's what the model has been trained on.
Use saved training trajectories and a controlled intervention to explain a failure, separating equilibrium theory from observed empirical stability.
Demonstrate all 3 repaired bugs and defend why a passed gradient check is necessary but not sufficient for generalization.
Use the tractable fixture and posterior predictive results to separate approximation, sampling and model errors; justify one revised modeling assumption.
Choose sources → to get a library of your own and a daily brief.
Map each implemented component to the original paper and explain 2 reduced-model failure modes without claiming full-scale reproduction.
Use calibration and shift measurements to justify a monitoring or abstention threshold, and give an explicit confounding counterexample to causal feature-attribution claims.
Defend a causal claim or refusal using the DAG, numerical estimates and a counterexample showing why predictive model fit cannot establish identification.
