37,617 results · Most relevant
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.
The presenters recommend seeding a set of production traces (with scores) into your Langfuse instance to have more data to analyze, and using the production traces you find interesting — especially the problematic ones — to build up a dataset for your offline improvement process to make a better application.
The hosts describe a hypothetical starting sequence for someone starting tomorrow: take your repository and use the Langfuse skill to get set up with tracing so you really know what's happening, review traces manually to understand what people are doing, then get into the motion of building out the traces and eval setup for production traces and optimizing offline.
hypothetical framing by speakers
During contact exchange, keep the conversation going with no awkward silences — figure out where her friends are and what she'll be up to while solidifying plans for a potential meetup. Don't just get a quiet, silent phone number and nervously eject; stay in the interaction, solidify the plans, and end on a high note.
When she's leaving soon and going out that night, close by proposing a plan that fits her reality: mention you might be going out later and could meet up after dinner, or she and her friends could come party. The close should fit her archetype and her weekend reality.
Coach Kyle advises steering the conversation into a slightly more intentful, flirtatious direction gradually — for example, saying 'I like [her ethnicity] people, I think' instead of 'I like you, you like me' — and asking probes like 'did you have a good experience or bad experience with [ethnicity]?'
Laurie Voss recommends exporting your failing traces from AX along with their explanations and handing the whole batch to Claude Code, Cursor, or another coding agent as context. He calls this one of the highest-leverage things you can do once you have evals running, and notes the Arize Skills plugin works well because you don't have to know how to call the API — you can just tell Claude Code to pull down some traces, see what's wrong, and make the application better, and it works.
To debug voice agents you need to see the conversation beyond just the transcript: audio, transcript, and trace all in one place. View the session as a whole — multiple back-and-forth turns from the user in the same trace view — and replay the whole conversation: the session ID stitches every turn into a timeline with every WebSocket event tagged by speaker. Play audio directly from the trace in the UI with no external tooling or exports. Replaying calls lets you see who spoke when, when the agent paused, where it got cut off, where the user got cut off, and what tools the agent called. With a session view you can scrub the audio and find failure surfaces within the tools and what the agent is doing.
Replace a sales-led onboarding process with an AI-driven self-service experience. The user types in their business name, and the AI automatically crawls the web to find and fix issues, pulling in competitor data and showing a competitive landscape. This transforms the customer journey from a manual, sales-dependent process to an automated, AI-powered one.
Inspect for economic buyer access early in the deal cycle by pulling call data from Gong and CRM enrichment tools like Clay to verify contact with the decision-maker, not just the rep's claim. Build a mechanism to inspect how contact was made with the economic buyer (direct vs. indirect connection) to get deeper deal intelligence.
When inspecting pipeline, measure the window within which deals convert and exclude deals outside that window from coverage ratio to avoid diluting your view of real coverage.
Mark (host) recommends picking a metric you can actually move during the pilot, not a downstream metric with too many variables. Shaun Crimmins agrees, advising to pick a metric the buyer cares about that ties back to broader business impact (revenue or cost), move it during the pilot, then present the extrapolated annual value to the business champion. Don't try to tie the pilot metric directly to revenue or risk in the initial kickoff; start with the operational metric the buyer cares about and connect it to business impact later.
Choose sources → to get a library of your own and a daily brief.