AI tool: Nostr/Buzz vs Slack

Jack Dorsey's New App Is Coming for Slack and GitHub (buzz) - YouTube

 Jack Dorsey's company Block just launched Buzz, an open-source workplace platform built on Nostr that puts humans and AI agents in the same Slack-style workspace with their own cryptographic identities. To put it to the test, we set up two AI agents powered by different models and made them compete to build the most secure auth system, with a third agent judging the results.

The video by Better Stack explores Buzz—a new open-source workplace platform launched by Jack Dorsey’s company, Block.

---

Key Takeaways

• What is Buzz?

  It combines features of Slack and GitHub with the decentralized Nostr protocol, designed so that both human employees and autonomous AI agents share the same workspace.

• Cryptographic Identities:

  Every participant (human or AI agent) operates using their own cryptographic identity (Nostr public/private key pair).

• The AI Competition Demo:

  To test the platform, two AI agents powered by different models were tasked with building a secure authentication system. A third agent, acting as a security auditor named "Hackerman," evaluated and judged their work.

• Core Differences:

  Buzz aims to simplify multi-agent workflows and collaboration by avoiding the need to juggle dozens of separate terminals or complex harnesses.

---

Community Feedback & Discussion

• Mixed Reactions: Viewers in the comments noted that while the interface and git integration are promising for coordinating AI agents, context window limits and high API billing remain practical hurdles.

• Comparison to Existing Protocols: Commenters frequently compared Buzz to Matrix or existing AI harnesses, questioning whether a Slack-style chat interface is the ideal way humans will interact with AI agents in the long term.

nostr-protocol/nostr: a truly censorship-resistant alternative to Twitter that has a chance of working

Buzz.xyz— Your people, your agents, your project — all in one place.
"Where people and agents work together."

In this episode of The Startup Ideas Podcast, host Greg Isenberg sits down with Vinny to demonstrate Buzz, an open-source, agent-native chat application developed by Block.

Key Highlights

• Open-Source & Open Protocol: Buzz is built on an open protocol, allowing your entire chat context to move seamlessly across different environments.

• AI Agents as First-Class Teammates: AI agents participate in team discussions alongside human team members rather than acting as standalone sidecars.

• Flexible Agent Harnesses: You can dynamically swap the underlying agent engine/harness behind each agent—switching freely between Claude Code, Codex, Goose, and open-source models without losing conversation context.

• Practical Demos: The episode includes live demonstrations, including building a CRM application via natural language prompts, managing daily status digests, and enabling collaborative workflows across AI agents and team members.

Jack Dorsey's Buzz: Clearly Explained (and how to use it) - YouTube

Neuro-Symbolic AI: Agents + Ontologies

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley - YouTube

While LLM-based agents excel at probabilistic language generation, they often struggle with exact domain rules, state management, and logical boundaries—leading to hallucinations, brittle tools, and invalid operations (e.g., issuing duplicate refunds or invalid payouts). Frank Coyle argues that pure prompt engineering or system instructions are insufficient to solve these edge cases. Instead, agentic architectures require a formal ontology layer—a structured, symbolic representation of a domain that acts as logical guardrails outside the model.

---

Key Takeaways

1. The Core Problem: Probabilistic Models vs. Deterministic Realities

• LLM Limitations: Large language models predict the next likely token, making them inherently probabilistic. They lack a deterministic understanding of state, explicit constraints, and business logic.

• Failure Modes: Common agent errors—such as refunding an order twice or returning ambiguous states like "probably shipped"—stem from attempting to enforce rigid domain logic solely through natural language prompts.

2. What is an Ontology in AI?

• An ontology provides a explicit, formal framework defining:

  • Classes/Entities: The core concepts (e.g., Customer, Order, Product, Refund).

  • Properties: Attributes describing entities.

  • Relationships: How entities link together (e.g., Customer PLACED Order).

  • Constraints: Business rules that cannot be violated (e.g., An order cannot be refunded if it has already been refunded).

• Connectionist Meets Symbolic: Combining LLMs (connectionist) with ontologies (symbolic) creates a hybrid AI architecture capable of both flexible language understanding and strict rule enforcement.

3. Building an Organizational Ontology

To construct a robust ontology, Coyle recommends a meet-in-the-middle approach:

• Top-Down (Expert Systems 2.0): Domain experts explicitly define entities, relations, properties, and constraints.

• Bottom-Up (Data Mining & Extraction): Automated tools (NER, LLM mining) extract terms and relationships directly from existing documentation, logs, and user reviews.

4. Why Ontologies Outperform Raw Prompts

• Separation of Logic & Execution: Keeping domain knowledge in an external ontology keeps tool harnesses thin and modular, avoiding bloated, fragile prompts.

• Predictable Handoffs: Ontologies standardize data structures and handoff schemas when multiple agents coordinate across complex workflows.

• Deterministic Guardrails: The ontology acts as a logical validation layer prior to tool execution, catching illegal state transitions before an agent makes irreversible real-world API calls.

Frank Coyle (@coyle_frankp) / X

Frank Coyle (drC) | Empower Your AI Journey — Get Started Today

0:00 - Intro and an educator's philosophy 2:21 - Two lineages: agents and ontologies 4:04 - Neurosymbolic AI: guardrails around a probabilistic model 5:23 - What an ontology actually is 6:14 - Building one, and the expert systems era 7:55 - Reusing existing taxonomies 9:12 - RDFS and OWL: inference and constraints 12:12 - Agents, loops, and how they break 14:22 - A Claude tool use loop with an ontology validator 17:47 - Pydantic at the door, ontology at the ledger 18:52 - The errors an ontology catches that English cannot