Harmonica 🪗

Our new blog post on why facilitation is the missing infrastructure for the context layer — and what we're building to make it happen. blog.harmonica.chat/context-layer-…

100%, the context layer is where the real value lives. But the knowledge that arguably matters most is tacit, trapped in people's heads.

looking back at 2025... blog.harmonica.chat/looking-back-a…

Most "DAOs" are quickly transforming into traditional top-down management, keeping information private, and oversight based on KPIs, 1990s style. Why? 1. No more regulation requiring decentralisation theater. 2. Bad memories of the poorly designed DAOs of 2018-2024, requiring a rapid shift to executing at least something. 3. Lack of understanding in outside-in innovation (i.e., open innovation, platform designs, etc.) 4. Lack of skills in facilitation and co-creation 1 and 2 are more temporary circumstances that lead to a specific form of groupthink, but they will cycle. 3 (lack of understanding) and 4 (lack of skills) are more fundamental issues that keep web3 organisations stuck in old-fashioned organisation design. The opportunity is there for ecosystems that get curious enough to learn why organisations that nurture open innovation tend to lead their industries. And then do the work to bring in those skills. I ballpark open innovation will become a wave in 2, maybe 1.5 years. Those who start now will become the leading case studies then. And for those who can't, some basic training in facilitation skills and co-creating strategies internally (e.g., running a strategy workshop, like a real process with input and feedback) will mean you're not completely archaic. Ecosystems can start upgrading their management style now, avoid falling too far behind, and benefit from improved internal coordination. To my facilitator friends, I wish you good luck selling in this environment. You're badly needed, even if underappreciated. And to those who are more experienced in organisation design but trapped in old-fashioned structures, I invite you to try small experiments like doing a team retrospective with harmonica.chat or a quarterly priorities workshop using negationgame.com "Trying a tool" is less risky than changing the structure, so you don't need to go against the zeitgeist and can still improve things internally.

Try Harmonica for multiplayer sensemaking, powered by community-created prompts and various LLMs, incl. models provided by publicai.co and BYOM. It's not about replacing human facilitators. It's about making great facilitation accessible to every team, at any scale.

That's the next frontier. Real multiplayer AI isn't "group chat with vanilla LLM" (sorry, OpenAI). It's AI that facilitates structured async conversations across many people, cross-pollinates and then synthesizes the patterns, tensions, and shared understanding that emerge.

2026 is shaping up to be the year of multiplayer AI. @gregisenberg and @far33d have made this call in recent weeks, pointing at the same pattern we've seen before: G Docs > Word, Figma > Sketch, Airtable > Excel. All single-player tools eventually lose to multiplayer counterparts

last week we were invited to present @harmonica_chat at the @TransformComm webinar youtube.com/watch?v=8ecRSZ… it was really cool to watch someone else doing a demo of the tool we've built! thank you for having us!

Happy to be in service of plurality @EdgeEsmeralda

One of the least discussed drawbacks of voting is that it's divisive. Choose one option from => Get a team rooting for each option. This can be very detrimental to communities and also lead to non-rational behaviour and suboptimal outcomes. What we really want is deliberation and inclusion. A way to get heard and seen, even, or especially, if members do NOT have decision making power. IRL communities have long figured that out and use a plethora of formats for facilitating exactly this. At scale it becomes harder. But doable.

100% agree, editing of system prompts is a key feature of the upcoming version of Harmonica

@Jehanav @gitcoin 👋😊

With a heavy heart, I am sharing that my time at @gitcoin is coming to an end. Gitcoin has made the tough call to sunset the institutional part of its business (Grants Lab) by May 2025 — including my role and those of several others.

Every protocol that built their governance to centre around referendum based delegate voting will pivot or die. It’s a brutal reality and it will be painful. Incentive alignment was always the key and shortcuts around it all have an expiry date.

Harmonica is in Gitcoin GG23 round! In GG22, 530 people helped us raise $4,349 in matching funds, and every dollar was carefully invested in building the app. If you want to see us keep building stuff — please support us now through 16th April: explorer.gitcoin.co/#/round/42161/…

@essemmeppi @sebkrier 100%

There’s so much to explore, build, and test to make communication, agreement, and deliberation better (more explicit and efficient). Really great to have access to @sebkrier’s unpolished thoughts – I’ve been learning a lot (and happily updating my world model)

@PuncarH2D @hellomother_ai 👀

🌟 We @hellomother_ai need design partners to test our multi-agent AI framework! 🚀 Outperforms old models in: ✅ Accuracy 💰 Cost 📊 Scalability 👉 If your company’s into AI or wants an edge for your product or service, let’s team up! 🎉 What you get: 👥 Access to top AI talent to help you design AI solutions that enhance your product or automate processes. 🔧 Exclusive resources to seamlessly implement and integrate powerful AI agents. 🌠 Scalable technology that grows with your needs—just add more agents! 📨 Interested? DM me or fill out: debonair-railway-ae3.notion.site/1ba3b9aa941b80… 💡 Know a great fit? Tag them or make an intro—I’d appreciate the assist! 🌎 Let’s shape AI’s future. Who’s in? 🙋‍♂️ This format is punchy, engaging, and easy to read on X. Want me to sharpen it even more?

@rauchg Sounds quite similar to what we're doing 🤭 and then you could also ask users what they think about statements of other users... That's how you transform collective sensemaking and build alignment!

AI-native Google Forms that is purely conversational. You set up the form or survey by just writing down a bunch of prompts. It gives you a link you can share for people to “fill out the form”. But it’s just a chat UI. Who wants to press “other” and fill in a little textbox when you could just answer? Just like Typeform innovated in the UI of answering, AI provides an opportunity to improve both the creation and submission experience.

Free ideas 🧵