Chris Lema

Founder of & & #Cigar Smoker

[Chris Lema @chrislema]

No one is self-made. Tons of people open doors, make introductions, come alongside and help.

Be a door-opener.
Be an introducer.
Come alongside others.
Help.

[Chris Lema @chrislema]

What I've noticed:

When your agents are killing it, under your direction of course, the right music, loud enough thru those speakers, will make you put your arms up in the air.

[Derrick Reimer @derrickreimer]

My friend Daniel just relaunched his design studio. He's the creative behind the @SavvyCal branding. If you're looking to add a human touch to your brand with hand-drawn illustrations (no slop), he's taking new clients! https://t.co/ZePvPbtZ79

[Chris Lema @chrislema]

@OriSilver Followed

[Jason Cohen @asmartbear]

100% free and open; no email required.

1. Determine your pricing strategy
2. Figure out why they’re compelled to buy
3. What to build next to justify raising prices

https://t.co/0zrP29UUmD

[Mastra @mastra]

Mastra is built to work with whatever stack you're already running.

Check out all 80+ integrations at https://t.co/8vH9uYEVwq.

[Jason Cohen @asmartbear]

New Smart Bear Live E03 just dropped!

Restarting growth at Podsqueeze after being stuck at €16K/mo for two years.

Cohost @thecraighewitt (Castos) and I workshop it with @wbetiago and @JOAOTHA:

https://t.co/6QJIqSkvWU

[Chris Lema @chrislema]

If you haven't tried Grok Bot, you really should....
https://t.co/wmFZ5L6kHS

[Chris Lema @chrislema]

@sarcasmically happy birthday!

[Mark Ajzenstadt @mardehaym]

A PE operating partner asked us to build production AI agents inside a portfolio company's billing system, processing real healthcare claims under HIPAA.

Two people hand-wrote every rule in their claims engine across 300+ denial codes and payer logic that changes quarterly.

Four months later, seven production agents handle it with zero patient data exposure.

First month, we didn't touch a model. We mapped their data: where it sits and what's missing, so agents reason from structured facts instead of guessing.

I've watched teams skip this step across dozens of engagements. They bolt a model onto the product, watch it hallucinate over unstructured inputs, and decide AI isn't ready for their industry. The data work is what makes it ready.

We built an enrichment layer that assembles 34 dynamic variables per claim before any LLM sees it, pre-computed and versioned so the agent receives ranked facts instead of searching for context.

Every agent follows one pattern: pre-compute context, strip all patient data before the model sees it, validate output against a strict schema, let deterministic code accept or reject the action. If the output falls outside the allowlist, the system fails closed.

Seven agents, each locked to a single workflow like denied claim follow-up or billing reconciliation, each running its own enrichment payload.

Then we built the eval harness.

Every agent runs against a curated test suite before any update reaches production. When a model provider ships a new version or payer logic changes, the harness catches regression before a single live claim is affected. The flagship agent reconciles denials to the penny: 59 out of 60 on the eval set.

Most teams launch an agent and hope it keeps working. We launch one and prove it does on every deployment.

We route calls across two model providers. Swapping one changes nothing in the output because the eval harness verifies it.

Model integration was the shortest line item in the four-month build.

The operating partner now benchmarks the rest of the portfolio against this system.

That's the line between a portfolio company running AI and one still running demos.

[Jason Cohen @asmartbear]

After more than a year of labor, my book 𝘏𝘪𝘥𝘥𝘦𝘯 𝘔𝘶𝘭𝘵𝘪𝘱𝘭𝘪𝘦𝘳𝘴 has launched!

It's all my best ideas -- and best writing -- on how to grow your company with your existing budget and team.

And yes, I read the audiobook myself. :-)

𝗕𝘂𝘆 𝗱𝗶𝗿𝗲𝗰𝘁: You can buy cheaper bundles directly from me -- Kindle and Audiobook, or those plus the physical book -- from https://t.co/lCg1KKVoGS

𝗕𝘂𝘆 𝗼𝗻 𝗔𝗺𝗮𝘇𝗼𝗻: It is available in paperback, Kindle, and Audible: https://t.co/MCgkHGIvXe

𝗙𝗿𝗲𝗲 𝗔𝗜 𝘀𝗸𝗶𝗹𝗹𝘀: Skills that implement the ideas in the book as well as articles, more added all the time, at https://t.co/tn3Zh8rsNq

I'm so proud of this and grateful to the many people who helped along the way, reading early drafts, challenging my ideas, and encouraging me to do it, and the 750 people who preordered the book, trusting that it would be worth it.

All your feedback and ideas are welcome, as usual!

(P.S. You know this already, but 𝗹𝗲𝗮𝘃𝗶𝗻𝗴 𝗿𝗲𝘃𝗶𝗲𝘄𝘀 and 𝘁𝗲𝗹𝗹𝗶𝗻𝗴 𝘆𝗼𝘂𝗿 𝗳𝗿𝗶𝗲𝗻𝗱𝘀 is extremely appreciated!)

[Chris Lema @chrislema]

@learnwithmattc Absolutely. It’s very telling. I’m just highlighting that what it IS saying isn’t also what it ISNT saying. :)

[Chris Lema @chrislema]

“When should you use guards, guides and scoring with AI?”

That’s was the question I got the other day. “Oh,” I replied, “Only when I’m awake or my agents are awake.”

In other words, always.

Guides, guardrails, evals, scoring. All of it helps keep you AI locked in. But it’s an art. Because too much doesn’t give it an ability to do its own thing, not enough allows it to game the whole process.

[Chris Lema @chrislema]

@CasJam Should you get some people early access to test this? Haha :)

[Brian Casel @CasJam]

I built it. This is https://t.co/8oMY1D2jul

Email marketing you own. Your list. Your flows. Your emails. Just plug in a sender (Resend, Postmark, or SES). Manage it all in the UI or with agents.

Opening soon.

[Andy Peatling @apeatling]

Redesign an existing site (WordPress or otherwise) with @bymilesai. Use a design sandbox and leave your current site untouched until you're ready to launch. 🚀

[Chris Lema @chrislema]

@TheCraigHewitt Use /btw

[Mike Hostetler // Actors & Agents on the BEAM @mikehostetler]

This aligns with my experience

I can prompt an LLM to reduce, trim and consolidate but it takes 3x-4x the tokens and still needs Human intervention

[Chris Lema @chrislema]

@bgardner @wpengine Sounds like you keep WordPress for pages and content but use BigCommerce for transactions. Is that how it splits up Brian?