Adam Perschke

I've been thinking a lot about how infrastructure shifts in regulated sectors map to economic development. The best ED technology isn't another tool bolted onto the stack. It's an operating system: one layer where every workflow connects, and everything else (compliance, reporting, coordination, institutional knowledge) gets better because of it. I think the industry is heading in this direction. Wrote about it here.

Product engineering is changing fast. Teams used to spend weeks writing PRDs before anything tangible existed. Now the workflow is shifting: AI prototype first → feedback fast → iterate live → align → then write the PRD. Visuals are becoming the new starting point.

That’s good to know, thanks. Totally get wrestling with AI products to just do what you want the first time. Still happens to me. I’m wrestling the largest US public incentive subsidy dataset (not publicly available) of over the last 40 years and have been using Claude to analyze and extract insights for a landmark 400-page market volume. Fascinating data insights.

It turns out I need deep research reports that are higher quality than other products spit out by default (hundreds of sources, very very tight verification, etc) and I hate wrestling with AI products to do a good job. With Webhound I can just tell it exactly how much to spend and I get a great result each time.

My new deep research setup: Manus to create research prompts / exec summaries, Webhound to run$100 deep research reports (Manus uses the Webhound API), Dropbox to store all the research reports (Manus saves/ organizes reports using the Dropbox API)

@fivosaresti Agents

I co-founded an agency that’s on pace for $5,000,000 ARR. We’re going to do that by becoming the #1 "service-as-software" for GTM. Right now, we have 13 agents in our org chart. And we’re “hiring” 10 more. Here’s our plan to stay an extremely lean team: (across departments) Content Team • Competitor Research Agent • Content Ideator Agent • Interviewer Agent • Designer Agent • Repurposer Agent • Newsletter Agent • Client Track Agent GTM Team • List Building Agent • Qualification Agent • Outbound Plays Strategist Agent • Copywriter Agent Sales Team • Pre-Call Assistant Agent • CRM Assistant Agent • Email Assistant Agent • Sales Analyst Agent Project Management Team • Project Tracker Agent • Outbound Reporting Agent • LinkedIn Reporting Agent Customer Success Team • ICP Matrix Agent • Company Research Agent • Meeting Summarizer Agent • Onboarding Agent • Expansion Agent I put together a complete agents + humans org chart that maps this all out. That way, you can steal it and scale your company 3-5x leaner. If you want it... Comment "Agents" And I’ll DM it to you.

@JJEnglert GTM guide

I built the ultimate GTM Engineer AI Toolkit that handles prospect research, outreach writing, meeting prep, and more in minutes. This is a beginner-friendly walkthrough that shows you exactly how to set it up, use it at work, and personalize it to your business. It can: - Research real prospects and companies - Score accounts against your ICP - Write personalized cold outreach sequences - Generate meeting prep briefs before calls - Help you build a repeatable prospecting pipeline - All using a free toolkit + Claude Code / Codex. This is for SDRs, founders, marketers, and GTM operators who want to use AI to do more at work without buying another expensive tool. I break down the full workflow step by step in the video. 👇 Comment "GTM GUIDE" and I’ll send you the full toolkit. (make sure you're following me so I can DM you)

@boringAI @thisisgrantlee Yeah with the right prompting and design system.

@AdamPerschke @thisisgrantlee You really think it’s as good?

Two years ago, we made the biggest bet in Gamma's history. AI models were getting dramatically better, and we decided to rebuild our entire product around them. People thought we were crazy, we were a small team, pre-revenue, and we were essentially starting over. That bet took us from a few thousand users to 50+ million. From zero revenue to $100M ARR. It transformed how people create and share ideas. Now we're seeing the same kind of shift happening again. The world is going agentic and just like we went AI-first two years ago, we're now building Gamma for an agent-first world. Today we're launching the Gamma connector for Claude, in partnership with @AnthropicAI. When Claude finishes a task for you (a research summary, a project plan, meeting notes) it can now hand you a Gamma presentation built from that work. Your thinking becomes something visual, polished, and ready to share. This is our first step. We believe that as agents become the way people get work done, every agent should be able to express ideas visually. We want Gamma to be the presentation layer for the agentic world. We're just getting started.

@chrysb @openclaw How did you give it access? Web browser login, API..

I gave my @openclaw a $1K budget and access to trade stocks autonomously. she's developed a process for deep research, building theses, and managing risk. she wakes up at 6am, scans pre-market, and makes her own calls by market open. I don't approve anything. she uses our notion workspace to track every thesis, log every trade, and journal her reasoning. let's see if she can beat the s&p!

Code is cheap now. Designing, managing, and validating multi-agent systems is where the real value is.

I used Claude on Chrome to set up GA4 and Tag Manager like a Fortune 100 company, autonomously. It’s a Tier 1 digital agency in a web extension. Do an audit if you already have GA4 and Tag Manager set up. Have Claude scroll your website, your analytics setup, and let Claude fill the tracking gaps.

Claude Code + MCP + Figma has opened my eyes to the future (now) Many other capabilities across an org

@JJEnglert Writer

I built an entire content team in 21 minutes. It writes LinkedIn posts, YouTube scripts, Newsletters, and Tweets. All in my voice. Content used to be the bottleneck. Writing for multiple platforms meant either spending hours on it or hiring someone who never quite sounded like me. I spent weeks refining this system so I could show you exactly how to set it up. What's in the guide: - Setting up your personal AI writer from scratch - The folder structure that makes AI writing actually work - Using successful examples to train your AI's voice - Building and refining custom writing skills - Advanced techniques for scaling across platforms This is for creators, founders, and marketers who want to produce more content, faster, without losing their voice or hiring a team. I recorded the full walkthrough. Every step. Live. Comment "WRITER" and I'll DM you the free GitHub repo with the complete folder structure and skills. (Make sure we're connected so I can DM you)

@DallasAptGP @phil_mcalister Also interested to verify and validate. DM?

@phil_mcalister in your inbox

I downloaded Claude in Excel on Friday night and didn't stop until I hit my Claude Max limits. Multiple times. My Excel skills are average at best. But I understand real estate. I understand taxes, Opportunity Zones, depreciation, compounding, waterfalls. I know when the numbers are right and when they're wrong. So I talked Claude through building a model that had only ever existed in my head. The result: a 30-year Opportunity Zone fund model with capital recycling. One of the most complex financial structures you can build in a spreadsheet. 14 interconnected sheets. 360-month engine. 378 rows × 114 columns tracking 13 deals simultaneously, month by month. Here's what makes this hard: Dynamic deal triggering. Deals aren't hardcoded. They auto-generate when cumulative refinance proceeds hit a funding threshold. The model decides when to deploy capital based on what's actually available. 13 stacked, interdependent deals. Each has its own timeline: construction → stabilization → refi → refi 2 → exit. The timing of one deal triggers the next. Miss one link and the whole chain breaks. Multi-phase waterfall. Pref → return of capital → GP catch-up → 80/20 split. The LP/GP economics flip mid-stream. The model tracks allocations across both phases. OZ tax basis tracking. Original deferred gain. 10% basis step-up at Year 5. Deferred gain tax due Year 6. K-1 losses flowing through annually. Full exclusion of appreciation after Year 10. All tracked separately for LP and GP. Depreciation allocation differently before and after the waterfall flip. The model knows the difference. After-tax IRR. Most models stop at pre-tax returns. This one calculates true after-tax performance including K-1 loss utilization, deferred gain payments, and OZ exclusion benefits. 8 automated validation checks. All passing. I built it in a weekend by having a conversation.

Cool to see AI evaluations evolving as the models do. A lot of people think AI is the end-all, be-all. Although it's helpful in many ways; augmenting coding, research, data analytics, etc. It's still in its infancy in terms of its true potential.

Most people die with 90% of their potential unused because they're afraid of a few years of hard conversations, working on stuff you have no idea how to do yet, and doing way more boring work than you thought you were capable of.

@spwfeijen AI

I create AI creators in 2 minutes Examples of what’s possible: - @welnessvauult → $100K/month - @healthytipsearns → $250K/year - @yourhealthgen → $2K/post This is one of the biggest money-making secrets right now. Comment “AI” & I’ll send the full guide (must be following)

Spent five days in the Rocky Mountains wilderness backpacking at 10,500 ft elevation. I took this video at sunrise. Everyone I’ve sent it to thinks it’s AI generated. We’re stepping into a future where we can’t trust what we see. That’s terrifying.

@DStrachman I like it

Moving into our vintage garage days at 1517