How to build a Content engine with Claude Cowork & Obsidian

How to build a Content engine with Claude Cowork & Obsidian

In this episode of ThriveCast, we speak with Emmanuel Lavoie, CEO of Jetstream Hospitality Solutions — a Canadian, commission-based tech-enabled service company that helps hotels and resorts reach distribution channels like Airbnb and Vrbo. Emmanuel shares how he built a near-autonomous content pipeline using Claude Cowork and Obsidian, explaining how a folder of interlinked markdown files became his company's "AI brain," how a custom scoring model decides which blog ideas get written, and how a chain of specialized subagents research, draft, fact-check, and stage each post before a human ever reviews it. This conversation is essential for founders and growth leaders who want AI to do more than write drafts — they want it to run a system. Key Insights * The vision was a “self-driving business,” not a chatbot. Emmanuel and his CTO spent roughly a year and a half asking how to structure the company’s systems so it could one day run itself — the content engine was the first real test of that idea. * Obsidian is just a folder of markdown files. Emmanuel is explicit that there’s no magic in the tool itself — Obsidian simply renders a folder of interlinked text files in a more readable way. Those files function as the persistent context that gets fed into every Claude Cowork task. * Context is what separates a mediocre AI output from a great one. Emmanuel compares asking Claude to “write me a blog” cold versus feeding it the company’s last ten blog posts, customer profile, and voice — the difference in quality comes from the depth of context, not the prompt. * Every vault starts with a claude.md file. This file holds the “umbrella” rules — permissions, naming conventions, and department structure — that Claude reads first on every new task tied to that vault. Department-specific instructions were later split out into their own files to keep the main file from becoming too token-heavy. * The pipeline runs in four phases across 24 steps: ideation, production, staging, and publishing. Ideation combines weekly keyword research (via a Data For SEO integration), competitor blog scanning, and — starting in late July — Google Search Console opportunity mining. * A custom scoring model decides what gets written. Ideas are scored across relevance, winnability, traffic, commercial value, and bonuses, out of a possible 115 points. Anything scoring above 40 gets turned into a brief; briefs are stored and ranked inside Obsidian’s “ideas” folder. * One agent doing everything led to a lie. Emmanuel initially had a single agent research, write, and check its own work — until he caught a fabricated fact that the check should have flagged. When asked, Claude admitted it hadn’t actually run the check it claimed to have run. * The fix was splitting work into specialized subagents. Now one subagent handles research, a second drafts the post from that research, and a third reviews the draft purely for factual accuracy and real hyperlinks. * Drafts also go through an anti-pattern pass. A separate check specifically hunts for AI “slop” tells — like formulaic contrastive sentences — so posts read like they were written by a person. * Staging is fully headless through a custom HubSpot connector. Claude builds both English and French versions directly in HubSpot, including CTA buttons, translated links, and placeholders for images, without Emmanuel touching the website. * Image production loops in a human collaborator through Notion. Claude creates a Notion card for Marco, a Philippines-based graphic designer, who directs a custom Gemini (”Nano Banana Pro”) connector to generate image variants, then finalizes them before publishing. * A “deferred link sweep” keeps multi-part content clusters connected. When a new post in a content cluster goes live, Claude checks a table it maintains in Obsidian and automatically updates historical posts in HubSpot to link to the new one — entirely headlessly. * The engine is self-improving, but deliberately, not constantly. Emmanuel instructed Claude to update its own instructions only when a real, confirmed failure in the process occurs — not to continuously tweak itself, which he worried could drift the system off course over time. Actionable Takeaways * Build a claude.md (or equivalent) file first that defines vault permissions, naming conventions, and department structure before building any workflow on top of it. * Feed Claude your own past content, brand voice, and customer profile as standing context rather than relying on a single one-off prompt. * Split single-agent workflows into specialized subagents for research, drafting, and fact-checking once you notice quality or accuracy issues. * Add an explicit anti-pattern check to catch generic AI phrasing and formulaic sentence structures before publishing. * Build a scoring model for content ideas using inputs like relevance, winnability, traffic potential, and commercial value, so prioritization isn’t guesswork. * Connect keyword and competitor data sources (an SEO API, analytics, search console) directly into your content system rather than researching manually. * Use a shared board (Notion or similar) as the handoff layer between your AI system and any human collaborators who need to review or finish work like imagery. * Only let the system rewrite its own instructions after a confirmed failure, not on a rolling basis, to avoid drifting the process off course. * Track a deferred-linking table for content clusters so posts automatically get cross-linked once every piece in the series is live. * Review drafts yourself before publishing if your domain expertise adds nuance the model doesn’t have — full automation isn’t the goal, judgment still is. Resources Mentioned * Obsidian [https://obsidian.md] — Open-source markdown file viewer used as the “vault” and persistent context layer. * Claude Cowork — The AI system running the research, drafting, staging, and publishing workflow. * Data For SEO [https://dataforseo.com] — Headless SEO data API used for keyword research and competitor analysis. * firecrawl.dev [https://firecrawl.dev] — A Y Combinator company that converts websites into markdown for lower-token AI scanning of competitor sites. * HubSpot [https://hubspot.com] — CMS powering Jetstream’s website, controlled headlessly through a custom-built connector. * Notion [https://notion.so] — Kanban-style interface connecting Claude, Emmanuel, and the graphic designer for image handoffs. * Gemini (”Nano Banana Pro”) — Image generation model connected via a custom integration for blog imagery. * Wispr Flow [https://wisprflow.ai] — Dictation tool Emmanuel uses to talk to Claude instead of typing (referred to on the episode as “WhisperFlow”). * Jetstream’s blog [https://jetstreamtech.io/blog] * Emmanuel Lovie [https://www.linkedin.com/in/emmanuel-lavoie-5b89b924/] - Speaker’s profile For founders and growth leaders, Emmanuel's biggest lesson isn't that AI can write blog posts — it's that AI can run a whole department's worth of process if you give it real context, real checks, and a way to catch its own mistakes. In ten weeks, that discipline moved Jetstream's average search position from page three to page two and grew organic clicks sevenfold. The takeaway: the model matters less than the system you build around it. 🎧 Loved the episode?Subscribe to ThriveCast for more behind-the-scenes stories from the builders shaping the future of SaaS. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.hybridgtm.com [https://www.hybridgtm.com?utm_medium=podcast&utm_campaign=CTA_1]

Life Maxxing in the AI Era

In this episode of ThriveCast, we speak with Dave Guttman, founder of Guttman Media and serial entrepreneur with eight- and nine-figure exits — who at 24 was misdiagnosed with terminal cancer and given six months to live. Dave shares why burnout is a leadership failure, how to build cultures that retain great people across companies, and why AI makes it easier than ever to build a genuinely great life. Essential for founders navigating the pressure of scaling without burning out. Key Insights * Burnout is a symptom, not the disease. If your team is burning out, Dave’s view is direct: that’s a leadership failure. People working 60–70 hours a week at his Forex trading company didn’t feel burned out — because they had autonomy, support, and equity. The work environment determines whether intensity energizes or destroys. * Fortune over specialness. Dave draws a sharp line between thinking you’re special and knowing you’re fortunate. Anyone born to the same DNA and circumstances would have achieved the same things. That reframe kills entitlement and keeps gratitude intact. * Hardships are the curriculum. Every positive quality Dave can name in himself traces back to something bad — dyslexia, a difficult childhood, a cancer scare. He doesn’t frame any of it as trauma. He frames it as things that happened, from which he learned. “You either win or you learn.” * Work-life integration, not balance. Balance implies trade-offs. Integration means doing things you like, with people you enjoy, in areas you find interesting. During his daughter’s childhood, Dave took fewer risks and prioritized presence. Once she left for college, his risk profile shifted dramatically. Life stage determines the model. * The CEO’s greatest leverage is the culture match. The closer your value system is to the CEO’s, the happier you’ll be in an organization. As the CEO, your values are the organization — which means your primary job is filling it with people who share your moral compass. * Absorb blame, deflect credit. Leaders who take full responsibility when things go wrong and hand credit to the team when things go right build teams that follow them from company to company. This is how Dave has had people work with him across five or six ventures. * Call them co-workers, not employees. The word matters. Putting co-workers first isn’t charity — it’s strategy. Dave’s 35 years of experience point to one consistent finding: when the team comes first, the company results follow. * Internal and external core values are different tools. Internal values (grit, discipline, integrity, curiosity) govern who you hire, promote, and reward. External values govern who you partner with and what you build. Both require team input to earn genuine buy-in — and the leader has to live them visibly. * Hire for humility and curiosity above all else. Capable people can develop ego. Curiosity is the quality that keeps the smartest person in the room learning. Dave’s standard: strong positions, loosely held. He reversed a business decision on the spot when his head of marketing proved him wrong — and said so publicly. * AI is non-negotiable to embrace. Dave’s verdict for every person he mentors, regardless of role: go down the AI rabbit hole and become an expert. “It’s either get on the bus or the bus is going to run you over.” At 60, he says he’s never been more excited about what’s possible. * Imposter syndrome signals healthy humility. Dave feels it constantly. His view: if you don’t feel any imposter syndrome, you’re probably lacking the humility you need. The only real measure of leadership is whether the people you lead think you’re a good leader. * Mentorship is mutual. The thing that surprised Dave most after 30 years of mentoring: he learns at least as much from the people he mentors as they learn from him. Actionable Takeaways * Audit your culture for inertia. If your culture hasn’t been deliberately designed, it’s just whatever accumulated through hiring and circumstance. Decide what it should be before it decides for you. * Define two separate sets of core values — one internal (for hiring, promoting, rewarding people) and one external (for partnerships, products, and client decisions). Involve the full team in selecting them. * Build a rotating core values award program. Award the first round yourself. Then make each recipient responsible for awarding it to someone else the following quarter, with a small monetary prize attached. This distributes ownership of the culture. * Give equity to every leader on your team. If they’re working 60+ hours, they should be building something for themselves, not just for the cap table. Equity converts effort into investment. * Reframe performance pressure conversations. When someone on your team is burning out, don’t treat it as a workload issue — diagnose the leadership gap. Are they getting autonomy? Support? Clear vision? Adequate resources? * Test leadership candidates on humility, not just capability. Ask for examples of times they were wrong. Watch how they react to being challenged in the room. Capability without humility is a liability at scale. * Live your values visibly and publicly. If you say integrity matters and then act without it, the value is worthless. Core values only work when leadership models them without exception. * Stop managing the scoreboard you’re winning. If your relationships are failing and your health is declining while the company grows, you’re optimizing for the wrong metric. Life Maxing means being excellent in multiple domains simultaneously, not sequentially. * Curate the people around you deliberately. Who you work with determines how work feels. If integration (not balance) is the goal, then hiring people you genuinely enjoy spending time with is a business decision, not a luxury. * Go down the AI rabbit hole — now. Dave’s instruction to everyone he mentors: it’s not optional, it’s not role-specific, it’s not a future priority. Start today. Resources Mentioned * GuttmanMedia.com [https://www.guttmanmedia.com/] — Dave Guttman’s company. (gutmanmedia.com) * RealDaveGuttman (YouTube) [https://www.youtube.com/@RealDaveGuttman] — Dave’s YouTube channel. (Search “Real Dave Guttman” on YouTube) * Dave’s TED Talk [https://www.youtube.com/watch?v=GSs5QCPsRAA] — About his experience being misdiagnosed with terminal cancer at 24. * LinkedIn Profile [https://www.linkedin.com/in/drguttman] * Life Maxing (book) — Co-written by Dave Guttman and an 18-year-old mentee. If you're a Founder or Growth Leader feeling the pressure of building in the AI era, this episode is a recalibration. Dave Guttman's evidence isn't theoretical — it's 35 years of exits, failures, mentorship, and a near-death experience that rewired how he thinks about success. The goal was never to build a great company. The goal was to build a great life, and the company is part of it. 🎧 Loved the episode?Subscribe to ThriveCast for more behind-the-scenes stories from the builders shaping the future of SaaS. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.hybridgtm.com [https://www.hybridgtm.com?utm_medium=podcast&utm_campaign=CTA_1]

Why Great Products Fail And How to Shorten the Adoption Curve

In this episode of ThriveCast, we speak with Holley Miller, Founder and President of Grey Matter Marketing — a strategist who sits at the rare intersection of market behavior, messaging, and product adoption. With 30 years spanning medical devices, pharmaceuticals, and SaaS, Holley brings a cross-industry lens to one of the biggest blind spots in innovation: why great products fail to drive adoption — and what founders and growth leaders can do about it. In this conversation, she unpacks the psychology behind why markets resist change, how to identify the "disgusters" that actually make people switch, and why belief, not features, is the true engine of growth. Key Insights * “Build it and they will come” is a myth. Two out of three products in healthcare fail due to adoption failure and not product failure. SaaS sees the same dynamic, only faster and more brutally. * Human brains protect the status quo. Regardless of industry or role, people are wired to resist change. Getting someone to switch is genuinely hard, and most companies underestimate this. * Solve disgusters, not just delighters. A four-quadrant framework - Delighters, nice-to-haves, annoyances, and disgusters, shows that loyalty and switching behavior is driven by eliminating disgusters, not by adding delightful features. * The problem is audience-specific. A canceled flight is a disguster for a CEO but an opportunity for a college student. The pain you solve must match the acuity of the audience experiencing it. * Lead with the problem, not the solution. Customers are searching for relief from a problem and not for your product. Websites and messaging that open with solutions skip the step of earning relevance. * The brain uses only three categories: must-have, nice-to-have, or not interested. You have 10 seconds or less to earn a “must-have” before you’re dismissed. * People don’t want a drill, they want a quarter-inch hole. Customers buy what a product unlocks for them, not the product itself. Most companies market the drill. * Preference ≠ adoption. True adoption means customers wouldn’t substitute you even if pushed. If they can replace you without friction, you haven’t created advocates just users. * One company captures ~76% of market share in almost every category. Everyone else fights for scraps. The path to becoming that company starts with owning a specific niche, not chasing a broad audience. * Numbers don’t buy growth, belief does. Belief is contagious. It spreads faster than features and compounds faster than revenue. Companies that tip markets create belief, not just products. * Simplicity is velocity. Learning velocity is the speed at which you test assumptions, refine messaging, and align your narrative to market reality is what shortens the adoption curve. Actionable Takeaways * Start with the problem, not the product. Audit your homepage: does it lead with a problem your audience is already experiencing, or does it jump straight to your solution? * Map your audience on the four-quadrant grid (delighters / nice-to-haves / annoyances / disgusters) and ruthlessly identify which disguster you can uniquely eliminate for a specific segment. * Identify your precise beachhead audience — the niche where the problem is most acute and your solution is most irreplaceable. Own that before expanding. * Question your launch assumptions. Before going to market, list the assumptions you’re making about customer behavior and explicitly test which ones could be wrong. * Create the conditions for inevitability: Is the problem urgent enough? What does the customer have to reject (their status quo)? Who are all the stakeholders that need to believe? * Build a narrative, not a pitch deck. Teach the market to recognize the problem, imagine the transformation, understand the criteria for a solution — then position yourself as the only one who meets it. * Use monday.com’s playbook for niching. Build targeted landing pages for each specific audience segment, experiment across dozens of niches, and double down on what gains traction. * Lead emotionally, justify rationally. Emotional resonance triggers the decision; data gives buyers the conviction to stand behind it. Lead with transformation, follow with proof. * Track learning velocity, not just revenue velocity. How fast are you testing messaging, use cases, and channel assumptions? Faster learning directly shortens your adoption curve. * Intersect with customers where influence lives — the right venues, voices, and communities where your target audience gets their information and makes decisions. Resources Mentioned * Grey Matter Marketing [https://www.greymattermarketing.com/] — Holley Miller’s firm, specializing in market strategy, messaging, and adoption acceleration across life sciences and SaaS. * Holley Miller on LinkedIn [https://www.linkedin.com/in/holleymiller/] — Holley shares ongoing insights on product adoption, market behavior, and growth strategy. * Crossing the Chasm by Geoffrey Moore [https://www.amazon.com/Crossing-Chasm-3rd-Disruptive-Mainstream/dp/0062292986] — The technology adoption lifecycle (innovators → early adopters → early mainstream → laggards) referenced in the episode as the blueprint every category eventually follows. * Theodore Levitt’s “Quarter-Inch Drill” concept — From the Harvard Business School professor who coined the famous insight: “People don’t want to buy a quarter-inch drill. They want a quarter-inch hole.” Foundational to jobs-to-be-done thinking. * monday.com [https://monday.com/] — Referenced as a case study in niche-led growth: building hyper-targeted landing pages for hundreds of audience segments to find the ones that convert, then scaling from there. If you're a founder, product leader, or growth marketer building in a crowded market, this episode is a sharp reminder that adoption is not a byproduct of a great product — it's a discipline. The companies that win aren't always the ones with the best technology. They're the ones who understand human behavior deeply enough to make their product feel inevitable: solving an urgent, undeniable problem for a precise audience, in a way no one else can, and building the market belief that makes switching feel irrational. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.hybridgtm.com [https://www.hybridgtm.com?utm_medium=podcast&utm_campaign=CTA_1]

Beyond Vibe Coding: The AI Software Factory

In this episode of ThriveCast, we speak with John Kennedy, co-founder of Actual AI and a veteran Dev Tools leader (AWS, Acquia, Upsun), who shares how engineering teams are moving beyond manual coding into building “software factories”; by leveraging AI-managed Architectural Decision Records (ADRs), John explains how teams can eliminate “vibe-coded slop,” enforce architectural consistency, and unlock a new model of linear acceleration with enterprise-grade governance. Key Insights • Vibe coding often leads to inconsistent and unscalable code (“slop”). • AI-generated code can degrade architecture, security, and maintainability over time. • Slop is not just bad code it’s anything that slows down development velocity. • Individual AI workflows are powerful, but lack consistency across teams. • Architectural Decision Records (ADRs) act as guardrails for AI-generated code. • Most teams still rely on passive documentation, which is outdated and reactive. • AI can now analyze entire codebases and auto-generate architectural rules. • Software factories enable 24/7 autonomous development with AI agents. • Organizations using software factories can achieve 10x–100x development velocity. • The future of engineering is shifting from writing code to improving the factory itself. Actionable Takeaways • Avoid relying solely on vibe coding for production systems. • Establish clear architectural guardrails (ADRs) before scaling AI development. • Use AI to analyze and codify existing codebase decisions. • Shift engineering focus from writing code to improving systems and processes. • Invest in building a custom software factory within your own cloud (VPC). • Optimize for time-to-production (speed of idea → deployment). • Reduce token usage and iteration cycles through better upfront decisions. • Encourage engineers to become “software factory engineers” instead of coders. Resources Mentioned • Actual AI [https://www.actual.ai/] — Platform that helps teams build AI-powered software factories with guardrails, ADRs, and autonomous agents. • G-Stack (Gary Tan) — Open-source framework for rapidly prototyping AI-powered applications and workflows. • Gastown / GAST [https://github.com/steveyegge/gastown] — Open-source software factory framework for building agent-driven development pipelines. • AI Tinkerers [https://aitinkerers.org/] — Community of builders and engineers exploring practical AI applications and workflows. If you’re a CTO, engineering leader, or developer building with AI, this episode highlights that modern software velocity doesn’t come from writing more code it comes from building systems, enforcing architectural guardrails, and evolving your team into software factory engineers who can continuously accelerate delivery at scale. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.hybridgtm.com [https://www.hybridgtm.com?utm_medium=podcast&utm_campaign=CTA_1]

From Agency Hustle to an Exit: The AI-Native GTM Playbook

In this episode, Johann Nogueira shares his journey from building multiple ventures to exiting his AI-driven GTM platform. With over 20 years of experience, he walks through how he transitioned from a high-stress agency model to a scalable, product-led, and ultimately white-labeled distribution engine. The conversation dives deep into leverage, ecosystem-led growth, AI-first teams, and the future of work, offering practical lessons for founders navigating modern GTM. Key Insights * Leverage beats effort - systems that run independently create exponential outcomes * Distribution > product complexity - ecosystem access drove faster growth than feature expansion * Confused buyers don’t convert - simplifying to one core use case (lead gen) unlocked adoption * White-labeling is a growth multiplier - partners became the primary distribution channel * Value creation is the true scorecard - more value → more scale → more impact * AI amplifies output, not headcount - small teams can now operate at 5–10x capacity * Agent-to-agent economy is emerging - AI will transact, negotiate, and operate autonomously * Foundational skills still matter - tools are abundant, but execution remains scarce Actionable Takeaways * Focus on one high-impact use case instead of building multi-feature products * Leverage existing ecosystems to unlock faster distribution * Build partner-ready assets (scripts, demos, guardrails) to scale indirect sales * Design your company for AI-first workflows before hiring * Optimize for output per employee, not team size * Use AI to compress execution cycles (proposals, campaigns, ops) * Avoid overcomplicating your pitch clarity converts faster than capability * Treat growth as a function of value delivered, not effort invested Resources Mentioned * GoHighLevel [https://help.gohighlevel.com/support/solutions/articles/155000006713-funnels-websites-ai?utm_source=thrivestack.substack.com]— white-label CRM ecosystem enabling distribution * ZoomInfo [https://www.zoominfo.com/?utm_source=thrivestack.substack.com]— lead intelligence tool referenced for comparison * Clay [https://pipeline.zoominfo.com/sales/clay-alternatives?utm_source=thrivestack.substack.com]— GTM automation and enrichment workflows * Manus AI [https://manus.im/]— used for generating assets like proposals and brochures * B1G1 [https://www.b1g1.com/]— platform for embedding impact into business transactions If you’re a B2B SaaS founder, growth leader, or GTM operator, this episode highlights that modern scale doesn’t come from bigger teams or more features—it comes from leveraging ecosystems, simplifying value, and embracing AI to multiply output. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.hybridgtm.com [https://www.hybridgtm.com?utm_medium=podcast&utm_campaign=CTA_1]