Creator perspective · MoneyThe number one thing the team does with outbound agents is relentless competitor and lookalike tracking, and it is working — a perfect use case for outbound. Competitor tracking can be done with Muse literally for free for B2B, in two parts: feed your Muse agent your customers, or use a custom-built agent if you have one — the speaker used Muse and it was really great at this. If a company has no outbound today, it should do these two parts: load in its customers and also load in its direct competitors, or ask Muse who it thinks the competitors are.
None stated.
The Official SaaStr Podcast: SaaS | Founders | Investors · SaaStr 883: The AEO Playbook: How to Get Picked by Agents (The Agents #017)
Report · MoneyThe reviewer describes the Slashy demo as having too much text and activity, with a screen recording that plays too fast for viewers to follow what the AI agent is typing, making it hard to mentally orient around what's happening.
Y Combinator · How To Stand Out In A World Of AI Designs
Report · MoneyThe reviewer describes the Slashy social proof section, headlined 'loved by the busiest people', and notes that using investors and founders as social proof makes viewers think the product is only for investors and founders, potentially alienating general consumers.
Y Combinator · How To Stand Out In A World Of AI Designs
Report · MoneyThe reviewer states that after reading the Slashy website, he is still very confused about what the product actually does, who should use it, and why.
Y Combinator · How To Stand Out In A World Of AI Designs
Report · MoneyWells Fargo decided to examine all customer transaction data — debit card, credit card, digital, and check transactions from many different channels — to see if a foundation model could be built and fine-tuned for downstream tasks like credit scoring, fraud detection, anti-money laundering, and marketing.
AI Engineer · A Bank Trained Its Own Foundation Model to Catch Fraud — Freddy Lecue, Wells Fargo
Report · MoneyThey stepped back to identify the raw features needed — not the pre-built/post-built features for downstream tasks — to understand which raw information units matter. They ended up with thousands of raw features but tried to find the core raw information units, then let the transformer architecture figure out the relationships between those core features.
AI Engineer · A Bank Trained Its Own Foundation Model to Catch Fraud — Freddy Lecue, Wells Fargo
Report · MoneyAcross multiple comparisons — Opus vs Sonnet, switching to ChatGPT, Cursor to Claude Code, autocomplete to agentic mode — switching produces statistically meaningless change in merged PRs per engineer. Arcolano calls it 'statistically a nothing burger' and discourages relying on tool/model switching to improve output.
AI Engineer · Better AI Models Won't Fix Your Engineering Team — Nicholas Arcolano, Jellyfish
PrincipleWhen building a product or agent to detect financial discrepancies, use version search to check what information existed before the market-wide correction, including whether an SEC filing would have revealed the discrepancy in an accounting footnote, and whether less reputable vendors found information that more reputable sources missed.
AI Engineer · Version-Controlled Search: The Web as It Was — Ryan Ahern, Exa
Principle · MoneyRob Walling describes entering a fast-growing ecosystem and building a tool serving a need that didn't exist a year or two prior, with examples including premium WordPress themes in 2008 (WooThemes), Josh Pigford's Bear Metrics as a one-click Stripe analytics tool in 2013, and podcasting tools like Squadcast riding the wave leading into 2020.
Startups For the Rest of Us · Episode 854 | How to Find Startup Ideas (Sneak Peek Chapter from My New Book)
Principle · MoneyA cost-optimization pattern: begin with a very loose declaration and let an intelligent (expensive) model figure out how to reach the outcome. Once the agent produces a trace, codify (shrink-wrap) that trace into a 'how', making the process more specific and deterministic to bring cost down.
AI Engineer · Stop Telling Agents How — Dan Barrett, Raymond Weitekamp & Jose Montes de Oca, OpenProse
ReportPamela Fox demonstrates a travel planning agent built with LangChain V1, giving it tools for searching flights, hotels, checking budget, and searching activities, plus a system prompt instructing it to prefer direct flights, always check budget, and ask for activities at the end based on remaining budget. Middleware is added to log which tools are being called.
AI Engineer · The Model Swap Workshop: GPT-5.5 vs Kimi vs DeepSeek vs Mistral — Pamela Fox, Microsoft
ReportWhen NBC doubted whether Seinfeld only played in New York or was universal, Warren Littlefield had Preston Beckman commission custom audience-retention reports by metro area; the data showed no difference in retention from Cheers reruns to Seinfeld in any major metro area, which unlocked the pickup decision.
described
Acquired · Seinfeld
PrincipleThe hosts describe how Jerry and Larry had all the leverage — guaranteed production, no risk to the counterparty, multiple interested buyers — so they could essentially write the deal terms and negotiate for a large percentage of the backend/equity rather than a flat fee. And because nobody thought a one-time special would be worth much, and there was no risk, the perceived low value made counterparties agree to generous backend terms.
Acquired · Seinfeld
PrincipleThe hosts describe Jerry Seinfeld's response to lacking script-writing experience: he recruited Larry David, who had TV writing experience (Fridays, SNL). And when Jerry needed a collaborator with a specific skill, he flew back to New York three days after the meeting and sought out Larry David late at night after his sets — going to find them immediately and in person.
Acquired · Seinfeld
Report · MoneySnack can bring the application up, take it down, and run a doctor command that checks whether the database is running and the app has network connection.
AI Engineer · Teach Your Agent to Prove It's Done — Nick Nisi & Zack Proser, WorkOS
Report · MoneySnack can prove work in two ways: a prove command that checks for deterministic output, and a judge that uses a System 1 model to get a sense of whether you're going in the right direction without matching one-to-one.
AI Engineer · Teach Your Agent to Prove It's Done — Nick Nisi & Zack Proser, WorkOS
Report · MoneyLaurie Voss walks through a failure: the demo agent was told to write a report but not where to write it, so it assumed it should write to a file. It asked 'I need permission to write the financial report file. Would you like me to display the report here?' — completely unhelpful in a no-permissions environment. The agent doesn't understand it's running in a no-permissions environment where the report should go to the command line; the failure happens because the prompt is ambiguous. Sometimes the agent does just figure it out — that's the non-determinism. In the demo run it wrote a report, tried to write it to a file path on the presenter's computer, and said it couldn't work. The reason it tried to write to disk and failed is the 'don't ask' setting: it was told it would run unattended,
AI Engineer · How to Know If Your AI Agent Is Any Good: Evals With Phoenix & Claude — Laurie Voss, Arize AI
Report · MoneyLaurie Voss describes putting the two turns together so both appear in one trace: first the research turn, then the writing turn, resuming the research turn's session so the writer can see everything the researcher found. The whole thing is wrapped in traceAgent because it gives one parent span encompassing all the data; without it you'd get two sibling spans in Phoenix, which would be fine but slightly harder to read. He frames this as shaping the trace data up front to make your life easier later.
AI Engineer · How to Know If Your AI Agent Is Any Good: Evals With Phoenix & Claude — Laurie Voss, Arize AI
ReportCJ Avilla describes Claude Managed Agents as an API surface that lets Anthropic manage the agent lifecycle for you, and recommends checking it out.
AI Engineer · Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic
ReportAfter creating credentials in a vault, you pass the vault when creating the session; the platform knows, based on the vault contents and placeholder secrets at the egress layer, how to inject the correct values.
AI Engineer · Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic