35,595 results · Most relevant
GaryVee argues quantity is a secret, under-admitted ingredient in breaking through — it's at-bats at making the piece of content that changes your life — but quality must also be part of the equation, since people who make 10,000 low-quality pieces never make it. Quality is subjective while quantity is not.
GaryVee asserts that accountability is the greatest trait: the second you go into accountability for what's wrong in your relationship, work, or life — saying 'it's on me' rather than blaming the other person (the 'fun part') — things become unbelievable. He notes that blaming the other person means missing the moment of seeing what's actually wrong.
Anything that can charge money or spend money has to be confirmed — treat that as a best practice for agent workflows.
Rather than dictating every step, declare the how by composing intermediary contracts along the way. Think of these as checkpoints in a DAG: each step fulfills one contract, which triggers the next until the final contract is met. Agents stay flexible on how to achieve each intermediary.
What's different from other chat- or agent-based flows is that all runs are compared against a contract — think of it as a fresh session every time getting benchmarked against the contract you've written declaratively.
Benchmarking fresh sessions against a declarative contract gets models out of the self-confidence loop. You don't want the same model checking the thing that was done; spawning new sessions and bouncing them off a contract is a better pattern.
Dan Barrett endorses spawning new sessions and bouncing them off a contract as a better pattern than having the same model check the thing that was done, because it gets the models out of the self-confidence loop.
Sell the outcome, not the tool — the core principle of agentic SaaS.
The main strategic move in the AI era is to become the worker — start doing the work your customers currently do with your tool, rather than just selling a tool. A large portion of B2B SaaS follows the model of selling a tool that a business owner hires an employee to operate in order to produce an outcome.
Al Chen lays out that deploying on-prem AI at an air-gapped bank involves a more complicated flow, organized around three pillars: (1) the build pipeline — how banks pull images from the vendor's software into their cluster; (2) data resilience — the plan if a region fails mid-request; and (3) ensuring no sensitive information leaks out to internal bank employees or outside the bank's VPC.
described
Al Chen identifies signals that shorten time to production — having a lot of processes set up for how you pull images down from a registry, and having GPUs sourced and ready to go for running inference. Timelines get pushed out to a few months with formal security reviews, a custom LLM gateway, or RBAC configuration, and pushed even further out when there's no approval process for pulling images down to the registry or no story around sourcing and procuring GPUs. Most signals that push timelines out are less technical and more about internal human and organizational challenges and alignment.
described
Al Chen challenges the audience to look at the system prompts for their LLM judges and check the traces to see if the traces, with the judges' reasoning, contain any PII or MNPI. A system prompt for a simple judge outputs a score and explanation of how well the agent performed; a seemingly innocuous line asking the human reviewer to be able to verify the agent's work may have allowed the judge to leak unredacted PII or MNPI. Your UI can still look good while on the back end the judge's reasoning unredacts customer information.
described
Al Chen explains that compliance velocity and CVEs go hand in hand: any serious platform has a plan for addressing common vulnerabilities and exposures as the first compliance hurdle. A single CVE can be researched on the NVD, CISA, or MITRE websites, but in reality a platform has multiple images and each image has multiple CVEs, so vendors serving multiple banks must create a system and process around CVE management.
described
In regulated spaces, define hard limits — things that definitely shouldn't happen (e.g., a financial services agent should never give investment advice) — and ingrain them in the evaluation set. Even if a violation is never fully prevented, you will at least know about it when it happens.
Define functions for LLM tool calling using JSON schema, including name, description, and typed parameters. Writing that schema — types, descriptions, parameter names — is prompt engineering: the LLM decides how to call the function based on that information.
When evaluating tool calling, check whether the model calls the right tool and passes in the arguments you expect, across all the different inputs. If a model calls a tool with wrong arguments, that means there's ambiguity in your function description — go back and clarify it with explicit constraints (e.g., 'don't include me or you, just named attendees, first and last if provided').
Build agents by having the model call tools in a loop until it reaches a goal. When evaluating models with tool calling in a loop, test their efficiency — can they accomplish the same goal with fewer tool calls? Count the number of tool calls needed to reach the final answer, and look at both the final answer and how long it took to get there, since every tool call is another network request adding latency.
Backtesting matters because if you know the existing evaluation set, you can overfit it. Overfitting is very dangerous because an overfit algorithm is unlikely to be successful in the future. You need to do backtesting with a holdout set. Because you have backtesting capability, you can check for overfitting by going back into your data and constraining the companies you know something happened to (e.g., 10 companies) against 20 companies that didn't, then train and iterate on your model, and make sure it continues to perform beyond just the publicly visible sets.
Commercial context: The creator describes this as their own product.
Larry and Jerry are obsessives and purists who wanted all the flexibility and pacing of editing a movie while also getting the benefit of a live audience telling them if the joke is landing — so they invented a novel production process to get the best of both worlds. Seinfeld episodes were not live camera switched; all the real work was done in post-production editing, which allows much tighter cuts — shorter scenes, more scenes, more situational jokes per episode — and lets you tell jokes you couldn't otherwise do, like The Contest, where the joke is cutting between characters in bed, restless or sleeping like a baby.
described
In The Busboy, Larry David introduced interweaving storylines that all intersect and resolve at the end in a grand finale; Seinfeld gave each of the four characters their own storyline, creating four concurrent storylines per episode, which forces extremely efficient storytelling — no wasted words, no wasted minutes.
described
Choose sources → to get a library of your own and a daily brief.