- The Agent Roundup
- Posts
- 👾 Alien Tech Arrived - Everyone Is An AI (Agent) Builder
👾 Alien Tech Arrived - Everyone Is An AI (Agent) Builder
Explore the intersection of AI and blockchain for secure applications. Plus AI voices that sound shockingly human and ways to build multi-agent flows.
Welcome to Edition #10 of Agents Made Simple
The week was dominated by AI tool releases and version upgrades. Agentic AI is becoming more integrated into our daily lives with increasingly realistic video, image, and voice generation, enabling everyone to become a creator, not just developers.
This is happening across traditional big tech infrastructure, open source platforms, and decentralized blockchain systems.
This week’s topics:
AI meets blockchain: Making vibe coding secure
AI voices are more human-like than ever before
Build better voice agents with no-code
Build multi-agent flows with the Agents SDK
Plus AI investments, trending AI tools, and more
AI Agent News Roundup
💥 Breakthroughs
Vibe Coding on Blockchain![]() Source: Dfinity At the World Computer Summit in Zurich, Dfinity showcased Caffeine AI. This tool lets anyone create apps and websites just by talking. The catch: It builds it on the Internet Computer blockchain, making it secure and tamper-proof. The live demo showed Caffeine creating several simple apps in seconds. A beta version will be available in about a month. People can sign up for alpha access at join.caffeine.ai. | More Human-Like AI Voices Unlocked![]() Source: ElevenLabs The model introduces audio tags like [excited], [whispers], or [laughs] to add emotion and personality to voices, making them sound more human. Public API access coming soon. Bland also leveled up its voices. Unlike Eleven v3, it prioritizes real-time applications, making it practical for business use cases. | No-Code Voice Agent Builder![]() Source: Vapi The no-code voice agent platform Vapi launched a visual and programmable way to design and deploy sophisticated, multi-step voice agents with greater control. Workflows can be used both via our UI and API, and let you orchestrate conversations using a node-based system. You can map conversation logic visually, connect different tools, or hand off to a human or another agent. |
📈 Investments
🇺🇸 Meta aims to fully automate ad creation for Facebook and Instagram using AI by 2026. Meta also heavily invests in nuclear energy to fuel its AI demands and signed a 20-year agreement with Constellation Energy.
🇺🇸 IBM unveils watsonx AI Labs. An accelerator for AI builders, startups, and enterprises in New York City to co-create AI solutions and increase enterprise AI adoption.
🇺🇸 Salesforce continues its acquisitions by buying Moonhub, a startup building AI tools for hiring, just weeks after acquiring Informatica and ConvergenceAI.
🇺🇸 Amazon plans to invest $10B in North Carolina to expand its data center infrastructure to support AI and cloud computing technologies.
Enjoy newsletters in a space designed for reading
Meco is a distraction-free space for reading and discovering newsletters, separate from the inbox.
Newsletters from trusted creators are a major source of information for me, so I’m subscribed to dozens of them. The problem is that they mix with other emails in my inbox, which isn’t even the place where I want to read them anyway.
I discovered a new app that bundles all your subscriptions in one place: Meco. Connect Gmail or Outlook and instantly move your newsletters to the app.
The user interface is pretty nice with filtering and bookmark features. Overall, a much better reading experience. If you read a lot of letters, download it here.
Build Multi-Agent Flows with The OpenAI Agents SDK

Source: MadeByAgents via o3
What Is The Agents SDK?
It’s a lightweight Python framework for building agentic AI apps with small primitives (Agents, Handoffs, Guardrails). It’s designed for multi-agent workflows and tool integration, enabling the orchestration of LLM agents with built-in tracing and function tools.
What Makes It Special?
After testing the framework thoroughly, here is what makes it different from alternatives:
Guardrails On Per Agent Basis
In episode #8, I outlined the importance of guardrails for customer-facing agents in production. The Agents SDK has guardrail support built in and allows adjustment per agent to enforce input/output validation.
Streaming Support
The Agents SDK includes first-class streaming support. You can use Runner.run_streamed()
to receive an asynchronous stream of events token-by-token, or at higher levels like “tool executed” or “agent switched” via RunItemStreamEvent
and AgentUpdatedStreamEvent
. This enables real‑time progress indicators or dynamic UIs that reflect agent activity as it happens.
from agents import Agent, Runner
streaming_agent = Agent(name="Streamer", instructions="Tell me a joke.")
result = Runner.run_streamed(streaming_agent, "Please!")
async for ev in result.stream_events():
print(ev) # See token-level and event-level output as it streams
Responses API or Old Completions API
One of the most powerful aspects of the SDK is its seamless integration with the new Responses API. This API combines the simplicity of Chat Completions with built‑in tool support (web search, file search, computer use) in a single call.
from openai import OpenAI
from agents import Agent, Runner, WebSearchTool
# Auto-uses Responses API with tool support if available
agent = Agent(name="Responder", instructions="Search the web.", tools=[WebSearchTool()])
result = Runner.run_sync(agent, "What's the capital of Spain?")
print(result.final_output)
MCP Support
The SDK supports Model Context Protocol (MCP) servers, enabling agents to call external data sources or business systems (like GitHub, Postgres, Slack) as tools.
Require Agent to Use Specific Tool or Use Auto Mode
You can finely control tool usage per agent. Agents can either be forced to call specific tools via instructions or run in auto mode, where the LLM chooses tools dynamically. Tools are regular Python or MCP-backed functions with auto-generated Pydantic schemas.
Tracing Dashboard
The OpenAI tracing dashboard is enabled by default, which means it’s tracking a lot of different metrics of the workflow. This helps to debug and improve the system over time.
On the other hand, it raises privacy concerns, especially when handling sensitive customer data. The tracing can be disabled or replaced with custom tracing solutions.
Orchestrate Via LLM or More Deterministic Via Functions
Orchestration is flexible. You can build LLM‑led workflows using instructions and handoffs, letting agents decide dynamically who runs next, or implement a more deterministic control flow in pure Python. Handoffs are just treated as tools, and agents can chain or delegate control, enabling both dynamic and scripted workflows.
from agents import Agent, Runner, handoff
agent_a = Agent(name="Analyst", instructions="Analyze.")
agent_b = Agent(name="Reporter", instructions="Report.")
triage = Agent(
name="Triager",
instructions="If analysis needed, handoff to Analyst, else to Reporter.",
handoffs=[agent_a, agent_b]
)
print(Runner.run_sync(triage, "Tell me about the market.").final_output)
Works with Any Model Supported by LiteLLM
The Agents SDK is provider-agnostic. That means it supports a range of different models, from OpenAI models via the Responses API to 100+ other LLMs via LiteLLM integration. But internal tools like the web search and vector file search are only supported by OpenAI models.
Generate Graph with Graphviz
The Agents SDK includes built-in Graphviz visualization via the draw_graph
utility, making it easy to inspect and understand your system. You can generate a directed graph of your entire agent workflow at a glance.
Voice Agent Package
The built-in voice pipeline facilitates the integration of voice capabilities. You can decide which models to use for speech-to-text and text-to-speech conversion. Build real-time voice agents via WebRTC/WebSockets and Jupyter integration.
Dynamic System Prompts
Agents support dynamic system prompts: the instructions
parameter accepts callables that receive the current context and agent, allowing the provisioning of runtime-tailored system prompts. This enables agents to adapt based on state, previous interactions, or metadata, making behavior highly flexible.
agent = Agent(
name="LocaleBot",
instructions=lambda ctx, ag: f"You are a {ctx['locale']} assistant."
)
result = Runner.run_sync(agent, "Hola!")
print(result.final_output)
Bonus: I'm currently working on a new YouTube video where I’ll break down the Agents SDK step by step and build a working agent that showcases many of its features. If you’re curious to see the framework in action, stay tuned.
Tool Spotlight
👾 Cursor 1.0 – What’s New

Source: Cursor
Some of the new features for your next vibe coding project:
Automatic code review with BugBot: BugBot automatically reviews your PRs and catches potential bugs and issues.
MCP one-click install and OAuth support: You can now set up MCP servers in Cursor with one click, and together with OAuth support, you can easily authenticate servers that support it.
Background Agent for everyone: The remote coding agent feature is now available to all users.
Agent in Jupyter Notebooks: Cursor can now implement changes in Jupyter Notebooks.
Richer Chat responses: Cursor can now render visualizations inside a conversation. In particular, Mermaid diagrams and Markdown tables can now be generated and viewed in the same place.
🎛️ Bing Video Creator: Microsoft’s mobile app that lets you generate AI videos for free based on OpenAI’s Sora model.
🧙♂️ Character AI: The new AvatarFX turns images into videos. Grab an image. Choose a voice. Write a fun script. Watch your images come to life!
💁 HeyGen AI Studio: Fine-tune vocal emphasis, hand gestures, and more for realistic AI avatars.
⌨️ Mistral Code: An enterprise-grade coding assistant that combines several specialized Mistral models to complete development tasks.
📹 Higgsfield Speak: A new update enabling realistic talking avatars with custom styles, scripts, and motion.
More Resources
Blog: In-depth articles on AI workflows and practical strategies for growth
AI Tool Collection: Discover and compare validated AI solutions
Consultancy: I help you discover AI potential or train your team
See you next time!
Tobias from MadeByAgents