Ivan Escobar | GTM Engineer

What people overlook is it takes a whole lot of strategy and expertise to do the "context engineering" that happens before this play. He arrives with a prepared list and prepared framework, it's just missing to run. 80% that most matters happens before. - understanding the company and their offers - knowing which signals are relevant - knowing which firmographics and data points to pull - building the tier scoring system and segmentation criteria @MichLieben I found a way to accelerate all these key 0-1 steps with Claude Code as well, I think it could add inmense value to your audience in LinkedIn, Youtube and here. Hit me up if you find this relevant for a walk-through like this. x.com/i/status/20427…

We spent months building a Claude Code system that runs outbound at our $7M ARR agency (and we're giving the whole thing away). Our head of GTM, Kenny, walks through the complete build on camera. Scores a target list against our ICP, pulls sales leaders via Apollo, enriches the missing emails, fetches our best-performing copy from Instantly's API, and loads 154 leads into Instantly with the copy and schedule set. Kenny packaged everything he used in the video below into a public starter kit. You get: → the GitHub repo → the CLAUDE md file we use → the Python scoring scripts Reply "send" and I'll DM you all three.

@MichLieben Send

@iamsaura_ It worked :)

Dear algo, Please show this post to founders, builders and creators in Europe that want to join 1 week hacker house in sunny Spain.

@AlfieJCarter CODE

I put the entire Claude Code GTM Engineering Playbook into ONE Notion doc. 8 sections. No fluff. - How to get set up correctly from day one: Pro plan, terminal install across Mac, Linux, and Windows, GUI install via Antigravity or VS Code, and bypass permissions mode - What to put in your project brain file, what to leave out, and how to get Claude to update it automatically when it keeps making the same mistake - How to run plan mode step by step and when to skip it for simple tasks - How to build a skill file from scratch, fix one that keeps failing, and install 5 GTM skills worth building first: lead scraping, email labeling, proposal generation, outbound sequence writing, and client onboarding - MCP install process, token cost checks after every install, the best MCPs for GTM work, and how to cut token usage by 50 to 100x by converting MCPs into skills - Sub-agents and agent teams: the 3 cases where they earn their cost, reliability math for parallel runs, and how to enable parallel variant exploration - What is eating your context before you type anything, how to use /compact and /clear correctly, and model selection for parent vs sub-agents - Modal deployment: any skill as a live URL in under 2 minutes, form interface setup, and connection to n8n, Make, or Zapier This is the setup I would have KILLED for before spending months piecing together how to actually get productive in Claude Code from documentation, YouTube tutorials, and scattered GitHub threads. Like + comment "CODE" and I'll send it over (must be connected for priority access)

I one-shotted a GTM Context live application with Claude Cowork (and it worked!) Basically a custom version of Octave that gathers all the context needed to kickstart an agentic GTM journey. I tested ClaudeCowork matched with GTM tooling and my favorite system building tool (Zite)... and honestly I'm in awe. As a GTM and system thinker, this process would've taken days of reasoning, automation and app building. Now I can describe the overview of the process I want, and in less than 10 min create something that actually moves the needle. Here's the process I followed: → Claude Cowork > New File > GTM Engine → Connected my agent with enrichment providers like Crustdata, Zoominfo via Deepline CLI → Connected it to Zite via MCP → Had previously curated the right framework to follow to build the GTM Context OS (Remember, nowadays 80% is curating the right things and having creativity to know what to build. Agents can take over the execution.) My origin prompt was something like: I want to build my GTM Context Engine to install into my AI and agentic tools with live context. You're a senior GTM engineer with uncapped technical capabilities, please follow this overview process to build this asset for [company domain]: [COMMENT "GTME" and I'll share the rest] The output was a context engine for the Go-To-Market motion of an organization: → Editable, white-label internal application → LLM's can now be connected to this OS to qualify better and write better messages → A live source of truth for the offerings, signals, value props, proof points and more → Markdown assets that will provide context for future usage of Claude & Claude Cowork It sounds cool...before you go crazy and do this, ask if this is even relevant for you. In many organizations, they're not even ready to dive into "Agentic GTM" because they're too early or have other problems (lack of clarity, unclear offers, unclear targets, etc.) This will only be valuable if you're looking to turn your GTM initiatives into something fast-pacing and open to experimentation. What they don't tell you: reaching these insights, terminology and placing the dots together comes from experience. I've spent last year running GTM automations in enterprise, startups and agencies, and learned "what NOT to do" (more often more important). Look, I'm not telling Claude to "print me money" or "become an ai sdr". I'm telling it to reverse engineer the context that Marketeers and SDR's will need embedded into their LLMs and workflows, and more importantly... make it a live tool, refinable and editable depending on business logic. Your AI capabilities in GTM are only as good as you know what truly matters at the right time.

Been playing with Hermes Agent this week to build a GTM agent to work with. And honestly? I'm quite impressed... The thing gets smarter the longer you use it - it builds experience, not just text-book skills. Hermes is an open-source AI agent that can live in your machine or installed fast via VPS. Unlike others, this one remembers everything across sessions, and writes its own skills when it solves hard problems. It can run on a $5/month server, working with all relevant AI models, and you can set it up with Hostinger in under an hour. Here's what makes it different: Here's what makes it different: → It learns from solving problems When it figures out something complex, it writes that solution down as a permanent skill. Next time you ask something similar, it doesn't start from scratch. It pulls from what it already learned. And you don't have to configure this. It just happens. → Memory sticks around for a long time Most AI agents forget everything when you close them. Hermes remembers your preferences, past conversations, and solutions. The agent in month three is fundamentally different than day one. → Use any AI model you want Switch between OpenAI, Anthropic, or 200+ models with a single command. Route expensive models to important tasks, cheap ones to simple stuff. → Your data stays on your machine Nothing gets sent to external servers unless you configure it. → It can run multiple tasks at once You can tell it something like : "every weekday at 9am, summarize my inbox and post to Slack" and it creates that schedule. No setup needed. So, while OpenClaw behaves as "claws" and it's great at executing, I find Hermes is a great "brain"! It's designed to compound, to improve as you use it, to learn from experience. After a month it won't be like anyone else's, it'll be shaped to your own work and usage. It's MIT licensed. Open source. Free to use. Yet I'll be transparent - for non-techies it won't be trivial. You'll have to learn to get comfortable with a terminal (unlike OpenClaw for instance, that offers a UI). I'm running mine through GTM automation experiments right now (lead enrichment, research tasks, multi-step workflows). Still early but the architecture is solid, and I'm learning how to make it work with other automations and agents. Anyone else playing with this? Where have you found this shines or underperforms?

As a GTME who's worked tech enabled campaigns for many years... this is probably BS, same bs that AI SDR tools primise with very little results. In the AI native world, constraint (what not to do) weights more than what's possible ("let's give this tool the power to spam my prospects with little real context")

🚨BREAKING: Someone built a money printer… you paste a website and it just starts bringing in customers in your sleep. It’s called Money Printer. It reads your site, figures out who should be buying, finds those companies, and reaches out to them automatically. I tried it on a random company and it immediately pulled in accounts I wouldn’t have found myself. Here’s what happens: → Companies already looking for what you sell → The exact people to contact inside those companies → Personalized outreach written for each account → It starts sending immediately → It even calls them No forms. No filters. No list building. Here’s the wildest part: Most teams still treat outbound like manual work. Lists. Copy. Campaigns. This skips all of it. You start with a URL. And it brings you customers.

Most of my career I've ran away from anything that looked like a terminal, yet to stay on top of AI developments, I've been facing terminals more often than ever. Here's a tip I learned that helped me in this process. Whenever I have to setup something that goes beyond my technical comfort zone - I'm relying on Perplexity Comet assistant to help me out on the details when engaging with the terminal. In the recent months I've had to dive into terminals to manage VPS for: → Setup N8N instances → Setting up ClawBot Agents → Setup Hermes Agent (in this case) So it's been very helpful to get Comet to support me when dealing with these black boxes. I can go back and forth with it, it's very permission-oriented and can control the browser while I can visualize what it's doing. I can stay in the loop, add extra information as it's running or stop it at any time. (Same logic can be achieved with Claude Extension and ChatGPT's Atlas) I'm getting past this mental blocker that terminals look way too technical. If you also try it out, you'll probably come to the conclusion that you've done way harder things than this. So next time you're facing a technical challenge - give eyes to your AI to help you right where you are - it might help unblock you where you're uncomfortable.

@ItsOriMane HELL YEAH MAN! Congrats!

After 11 months, 100+ campaigns, and 1.5M+ in influencer marketing budget allocated for B2B startups, my agency website is finally live. Check it out: omane.media

A JD is the most honest thing a company publishes. It tells you the pain, the stack, the budget, and the urgency. So while most people see a job listing - GTM Engineers see a signal. Here's one that landed in my DMs this week. A recruiter sent me a "Revenue Ops Specialist" role. Not relevant for me. But I read the JD anyway. It mentioned Zapier, n8n, Make. Salesforce data bridges. Salary range: $50-60k. That's a company telling you - publicly - exactly what hurts, what tools they already have, and what solving it is worth to them. As an advisor to Overdrive, an automation services company, the read was immediate: this is a warm account, not a cold one. SDRs and GTM operators have been doing versions of this manually for years. Find the listing, read between the lines, reach out before the role is filled. The timing advantage is real: you're reaching them while the pain is loud, before the budget goes to a hire. And even if they do hire... they might still need help. So if it can be done manually, GTMe can scale it. This is a signal that can now be captured, qualified, and acted on systematically - not just when a recruiter happens to message you. Next time a JD lands in your feed - ask: Is this a signal for someone I know? That's GTM-thinking! I'm testing a build to systematize this play in the easiest way possible - more next week.

A self-building CRM is no longer a future idea - it's coming. We’re moving from “filling CRMs” to “CRMs that build themselves.” Just sat down with some founders to brainstorm arround this and we had this realization. Everything needed for this is ready: 1. Voice-first input Tools like Wispr Flow let you capture notes, updates, and context in real time - no more manual data entry. 2. AI-native GTM engines Deepline is pushing toward an “AI-CLI for go-to-market” - enriching, qualifying, and triggering actions automatically. 3. Self updating context engines Like updating your whole GTM-brain: offers, products, services, value props... based on what you say, what happens and your updates. 4. Self-evolving interfaces Lovable-style UIs that could adapt based on usage, meaning your CRM doesn’t just store data - it restructures itself around how you work and your custom data needs. 5. Relationship intelligence layers Platforms like The Swarm map actual human connections, not just static records - turning your CRM into a living network 6. API-first sequencing Email + outbound tools are becoming composable - triggered via APIs, workflows, or MCP instead of rigid campaigns 7. Unified comms integrations Unipile abstracts LinkedIn, email, and messaging into a single layer - making outreach programmable 8. Programmatic AD campaign platforms Creating ad campaign proposals programmatically. What this means: The CRM will no longer be a system of record. It’s becoming a system of action. It should become an actual self-updating system. Imagine your CRM like calling a collegue, and having it update your systems, signals and campaigns based on your business logic. So, what's stopping this from becoming a reality? Why not have a CRM that evolved as your business evolved?

@domwhyte42 This has great GTME angles man! Great potential for outbound campaigns as well

A lot of business software lives in spreadsheets because building a full app (with frontend + backend + permissions) used to be too expensive That tradeoff is starting to change, and we just made it a bit easier in Zite 👇

People using AI for automation vs people using AI agents

@anvisha Moda

We raised $7.5M to kill AI slop. Introducing Moda: the world's first design agent with taste. RT+ comment “Moda” and we’ll design your brand for FREE.

another 10 points for Claude Skills 🤙 Just made a skill extracting the ppt style from a company and now it's designing me my 9-5 slides at god-speed, with accurate styling.

@oarojas10 @superworker_ai Looking very useful for e-commerce! Hey this might come in handy for leadgen storeleads.app

You can now connect your Shopify store to @superworker_ai Many Shopify decisions start with a CSV export. In practice that means exporting data from Shopify, cleaning the file, and stitching it together with other data before you can even start the analysis. Superworker now pulls the relevant data from Shopify, combines it with other sources, and cleans it so it’s ready to analyze. From there you can ask questions in plain English directly in the spreadsheet, and Superworker runs the analysis for you. We’re working with a small group of Shopify merchants and agencies to shape the integration. Access is currently invite-only while we onboard each store manually. We set up the connection with you and make sure the data and analysis work well for your workflow. If you run a Shopify store (or work with merchants who do), join the waitlist for early access. Link in comments.

@ItsOriMane Lol fair

@anomadbuilder No one cares about Linkedin here bro

"One connection for all of LinkedIn" Basically, making the connection from ai agents to all capabilities of LinkedIn automation. How? Option 1 -Connecting your SaaS applications (lemlist, prospeo, etc.) Option 2- Or connect your LinkedIn profile and use our own providers. You'll be able to manage everything regarding LinkedIn from a single API or connected MCP, from your tool of choice (Claude Code, Clawbot, Chatgpt, Relay, Zapier, etc.): - Catch, respond or analyze your messages - Fetch people from your network - Planning outbound campaigns - Finding people or companies - Scraping people, companies, jobs... - even browser automation Your business world, now accessible for your agent companions. >>> what do you think of this idea? roast it please

If you want to grow, be careful to join any organization with an internal ticketing mechanism. No growth will ever come from "request it to IT"