Recommendation · MoneyHormozi advises going where the reps are — like going where the fish are if you're fishing, since what you're fishing for is skills and network. Concretely: politics, go to D.C.; finance, go to New York; influencer/media, go to L.A. He stresses moving before you have strings tying you down, and calls geographical flexibility wildly underrated and a competitive advantage. Only once you're established — 'once you become Joe Rogan' — can you move to Austin and do whatever you want.
Alex Hormozi · My honest advice to someone who wants to get rich.
Recommendation · MoneyImplement a 'bring a friend' referral process: every time a customer comes in for a treatment, ask who they're bringing with them. Hormozi says this referral ask at every meeting will do the majority of the work on the demand-gen side and is the CS onboarding playbook, and that the marginal cost of a referral is nothing so even converting a third is worth it.
Alex Hormozi · $100M Worth of Marketing Knowledge in 32 Minutes | Scale or Fail
Method · MoneyRun a weekly event with a big giveaway (a year of scans), give every attendee a scan while a VSL plays, then book in-person close meetings right after the event, with a Zoom fallback. The scan takes about 20 minutes, which is used to sell while the prospect watches the scan results, and a 5-7 minute wait is baked in before the close.
Method, not a verified protocol.
Alex Hormozi · $100M Worth of Marketing Knowledge in 32 Minutes | Scale or Fail
Method · MoneyHormozi lays out the event sales flow: have people watch a VSL and set an appointment for later that day for a close; run scan plus VSL at the same time so people understand what's going on while being sold the whole time; right after the scan plus VSL, have the close meetings. The scan itself takes 20 minutes, which can serve as the baked-in wait. V1 test is scan plus VSL straight to close; V2 is scan plus VSL, then an appointment as the next meeting, then VSL before the appointment and close.
Method, not a verified protocol.
Alex Hormozi · $100M Worth of Marketing Knowledge in 32 Minutes | Scale or Fail
Recommendation · MoneyThe host advises costing out true delivery costs at different service levels and multiplying by 5-10x to set the price, with 5x as the minimum because costs may run over.
Alex Hormozi · How to Get Rich for Service-Based Businesses (Thank Me Later)
Recommendation · MoneyThe host recommends adding a price lock guarantee: the quoted price holds as long as the client doesn't change anything. At higher price points, condition it on headcount not changing by more than 20% and no venue change. Verbally confirm scope boundaries (no venue change, no headcount change over 20%, no added services like AV, no date change) so the scope is confined; if the client breaks the constraints, have a different conversation and true up the price at the end. Frame it as a choice between being nickel-and-dimed on every change or one price that holds.
Alex Hormozi · How to Get Rich for Service-Based Businesses (Thank Me Later)
Method · MoneyFor B2B events where the audience is the customer, the host recommends a separate approach: do whatever it takes to get those events because the client fronts the cost of gathering 500-1,000 of your ICP; get a booth; secure a speaking slot (even 15 minutes); in the slot, present about 20 mistakes event planning buyers make, each with proof of one person saying you're awesome at that thing; offer the slides via a QR code on screen; the opt-in asks whether they run events and how many per year, which becomes a lead list; the CTA is simply 'do you want the slides?' rather than a pitch. Even closing 1% of the room yields ~15 clients, a 50% business increase.
conversion figures are the host's estimates
Method, not a verified protocol.
Alex Hormozi · How to Get Rich for Service-Based Businesses (Thank Me Later)
Method · MoneyCreate a custom tool called Dispatch Analysis to tell the head of research agent to spin off multiple sessions that will be coordinated for a custom harness. Build a custom orchestration harness in the server that delegates work for each ticker into a different session, then aggregates the results and gives a bunch of scores when all done. The main agent decides at some point: 'hey, I want to spin up 10 different sessions to do work' — using the custom tool to build the custom orchestration harness.
Method, not a verified protocol.
AI Engineer · Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic
Method · MoneyLeverage sub-agents to do the bulk of the work: spin up a financial expert analysis agent (extractor) and a risk evaluator analysis. Kick off a sub-agent to verify that the defined outcome is being met: it looks at the rubric, analyzes all the work done in the session and the artifacts created, and decides whether the scorecard was delivered, the numbers are well defined, and the memory update was correct. When sub-agents finish their work, they let the main agent know what was asked of them; the main agent then wakes up, gets that information, files everything it needs to do, and creates the deliverable.
Method, not a verified protocol.
AI Engineer · Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic
Method · MoneyTell the agent: 'Here is an outcome. I want you to analyze NVIDIA's most recent quarterly filings. You're going to use Edgar identities. This is where your Edgar identities are. You have memory. So check if you've already done analysis previously and make sure that you use that instead of refiling and researching things that you already know.' Request two deliverables: write a note in memory for that specific company, and write a scorecard in a well-defined structured output saved in a specific file location. Send a user-defined outcome with a specific rubric, max iterations, and a description of the task at hand any time a session is started for a specific ticker.
Method, not a verified protocol.
AI Engineer · Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic
Recommendation · MoneyIn a real production application, use vaults for credential injection instead of injecting secrets in the prompt. With vaults, you define a secret to inject in an environment variable but put a placeholder instead of the real secret; when Claude does work and wants to use that environment variable, it injects the placeholder value, and at egress the host swaps it for the real value — only on the host domains that you specified as allowed for that secret.
AI Engineer · Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic
Method · MoneyKevin's team asked a coding agent to write 1,000 tests across 10 domains to cast a wide net and see what failures were caught. The 1,000 figure was arbitrary, not a meaningful target. They anticipated the run would take a few hours and be token-heavy, planned credential management accordingly, and let the agent figure out triage questions like whether a failure was a service issue or an MCP layer issue.
Method, not a verified protocol.
AI Engineer · https://www.youtube.com/watch?v=k72eLcYpVys
Recommendation · MoneyKevin recommends fuzz-testing your agent sandbox — asking it to complete a thousand workflows and seeing what results you get — as a very strong way to surface failure modes that are innocuous to humans. He adds: test your agents locally, but also fuzz test them with a wide set of domain tests remotely if you're looking to host agents on sandboxes.
AI Engineer · https://www.youtube.com/watch?v=k72eLcYpVys
Method · MoneyAn ordered fix-and-verify loop: (1) when potential coding issues come up in review, run an agent skill to resolve them — copy and paste the agent prompt meant to fix the suggestions, for each issue presented; (2) choose between reviewing each issue individually (to plan fixes hands-on with your agent) or auto-fixing all issues, which triggers verification, makes commits, and posts a summary of changes back to the PR; (3) after fixing PR findings, rerun the verification command rather than stopping at the local run — prompt your agent to run verification regardless of whether it decides to on its own, because the code has changed and a fix can introduce new issues; (4) make sure you've run all commands for the branch and identified what was deferred before declaring done.
Method, not a verified protocol.
AI Engineer · How to Build Quality Gates into Agentic Coding Workflows — Nnenna Ndukwe, Qodo AI
Method · MoneyAn ordered planning sequence: (1) after agents are verified and good to go, switch into plan mode; (2) use the repo-local workshop planning skill to turn the hands-on task in the README into a high-level implementation plan and a build-session execution plan, using separate high-level and execution-focused planning templates; (3) the plan must include an implementation skill handoff naming the first implementation skill and the test-driven development prompt to be chained next; (4) include skill routing so all skills the agent should kick off during implementation are planned ahead; (5) ensure the agent knows every step of the code-change process and determine the test plan; (6) if the agent doesn't prompt you to choose which workflow to implement, make that clear in the prompt.
Method, not a verified protocol.
AI Engineer · How to Build Quality Gates into Agentic Coding Workflows — Nnenna Ndukwe, Qodo AI
Recommendation · MoneyJavier Garza recommends that whenever you use an MCP tool you really check the code before accepting it, because accepting can trigger malicious behavior. When checking MCP code manually is impractical because servers are long, his recommendation is to use a tool that checks for malware. He also recommends not trusting projects no matter how many GitHub stars they have, and running a security scan on them, noting Snyk has a free one you can use on open-source projects.
AI Engineer · AI Security Engineer Foundations + Certificate — Javier Garza, Snyk
Recommendation · MoneyJavier Garza recommends redefining threat modeling scope for AI to include LLM models, prompt templates and system prompts, context windows, memory stores, and endpoints/APIs the agent can access — not just databases, credentials, tokens, and infrastructure.
AI Engineer · AI Security Engineer Foundations + Certificate — Javier Garza, Snyk
Recommendation · MoneyJavier Garza recommends storing secrets securely and granting AI agents access only to the resources they need, when they need them, and minimizing the access an AI agent has to reduce attack surface. He also warns that agentic tool tokens need to be stored in a way that they cannot be leaked, and that giving a local AI agent like OpenClaw access to everything lets it do things it is not supposed to do when it goes wrong.
AI Engineer · AI Security Engineer Foundations + Certificate — Javier Garza, Snyk
Recommendation · MoneyWhenever you use an MCP tool, really check the code — it's very important. Since reading is hard because most MCP servers are very long, use a tool that checks for malware and other issues in the code itself (Snyk has one; there are many others from other companies).
AI Engineer · AI Security Engineer Foundations + Certificate — Javier Garza, Snyk
Method · MoneyUse AI itself to help threat model: ask an agent to create the threat model for the app you are designing, generate attack scenarios and abuse cases, simulate attacks such as prompt injections so you can address the attack vectors, and have it suggest mitigations and security controls. Automatic threat enumeration from a data flow diagram is part of this.
Method, not a verified protocol.
AI Engineer · AI Security Engineer Foundations + Certificate — Javier Garza, Snyk
