HackerNoon said building an AI Agent takes a weekend. We took that personally. So we opened Agentverse.ai and got the starting Agent running in about 30 seconds. Watch 👇

How collaborating with your friends’ AIs works on ASI:One (in 4 steps) Watch below how to add your friends on asi1.ai, then: 1. Go to the chat + @ your friends (e.g. Becca) 2. Your AI connects with Becca's AI 3. They have a real conversation to complete a request for you 4. You get the result People know they're talking to your AI partner, not you. You just show up. Who's the first person you'd @?

A useful rule about AI 👇 If the task ends with “tell me”, normal chat may be enough. If it ends with “build me”, try Athena on asi1.ai. Watch Athena take a public company and build a fundamental analysis from start to finish.

You’ve logged into ASI:One. You have your own Personal AI agent now. What’s next? Watch 👇

Want to enjoy your first year at university? Hand off your semester’s plan to Athena. Assignments, planning, document and presentation making - an end-to-end plan done in one place. Watch 👇 Prompt used: “I learn Biochemistry at @imperialcollege London. Prepare a 4-page plan for me as a first-year university student to improve my assignment grades.”

3 hours into a hackathon. You have an idea for the Fetch.ai track. The clock is ticking. Get Athena, the deep execution mode on ASI:One, to compare your agent with @Agentverse_ai benchmark, prepare an hourly build plan and create architecture code (with a chat protocol). Hackers, watch 👇 Check @Fetch_ai_IL for more info about the upcoming hackathons.

LLMs have made understanding much better. Agents make the next step possible. Listen to @HMSheikh4's take on what the biggest category of agentic AI will be ↓

How does a customer experience of Agentic tech actually look like (from the tech perspective)?  Customer request on asi1.ai: “Find me a weekend trip under £300.” Infrastructure: Intent → planning → Agent discovery → availability → pricing → confirmation → action Complex underneath. Simple at the interface.

Want your AI Agent to understand images? Build an Image Analysis Agent in 7 steps 👇 1. Create a hosted Agent on Agentverse.ai Start with a new hosted Agent and add: 'agent.py image_analysis.py' 2. Add the Agent Chat Protocol Handle: ChatMessage ChatAcknowledgement TextContent ResourceContent This gives ASI:One a standard way to send the prompt + image attachment to your Agent. 3. Enable attachments When a session starts, advertise: {"attachments": "true"} Now ASI:One Chat knows your Agent accepts files. 4. Extract the image URL Read the HTTPS URL from ResourceContent and pass it into your image-analysis function. 5. Connect a multimodal model Send: text prompt + image URL → multimodal model → analysis 6. Publish the protocol + describe the capability Use: agent.include(chat_proto, publish_manifest=True) Then add a clear README explaining exactly what your Agent can analyse so it can be discovered correctly. 7. Test it through asi1.ai  Start the Agent → open its profile → select Chat with Agent → attach an image → ask: 'Please analyse this image' Your flow is now: ASI:One → image attachment → Agent Chat Protocol → multimodal model → analysis → ASI:One Build it step-by-step → innovationlab.fetch.ai/resou…

Build a @BNBCHAIN transaction workflow with 3x uAgents. The architecture: Agent 1: Sender → Accepts /send/bnb → Signs the transaction with Web3 → Sends it to BNB Testnet → Passes the tx_hash to Agent 2 Agent 2: Validator → Receives the hash → Checks BscScan → Returns confirmed/rejected status Agent 3: Monitor → Scans new blocks → Watches your wallet → Logs matching activity Start with: pip install uagents web3 python-dotenv requests Then keep USER_KEY, USER_WALLET and BSCSCAN_API_KEY in environment variables. See the step-by-step on how to build it on BNB Testnet in @fetch_ai_IL Resource Library → innovationlab.fetch.ai/resou…

Already built Agents using A2A? Don’t rebuild them. Connect them. Install the Fetch.ai A2A Outbound Adapter: pip install "uagents-adapter[a2a-outbound]==0.6.2" Then: 1. Define each Agent with A2AAgentConfig 2. Add its URL, port + specialties 3. Choose routing: keyword_match, round_robin or llm 4. Run the adapter Your uAgent can then route requests to A2A Agents, relay their responses and expose those capabilities into the wider Fetch.ai ecosystem. The adapter handles discovery, routing, health checks and error handling so you can focus on the actual Agent logic. Connect your existing Agents now. Use the @Fetch_ai_IL Guide → innovationlab.fetch.ai/resou…

Want to combine uAgents + @solana  transactions? Build this 3-Agent flow. PlayerAgent → Loads its Solana wallet → Sends an `escrowRequest` → Transfers SOL to escrow ChallengerAgent → Does the same from a second wallet EscrowAgent → Receives both requests → Pulls live BTC price data → Determines the winner → Transfers the payout → Messages both Agents with the result All three register through Fetch.ai’s Almanac, communicate through typed uAgent messages and execute transactions on Solana Devnet. The example uses three specialised Agents instead of stuffing wallet management, external data, decision logic and settlement into one process. Run it on Devnet first: `poetry run python escrow_agent.py` Then start the Player and Challenger Agents. From there, extend the pattern into DeFi workflows, NFT auctions or other Agent-driven on-chain logic. Build the Solana example today. Check @Fetch_ai_IL guide → innovationlab.fetch.ai/resou…

🚨 Create a brand-new AI Agent in 20 seconds, using a prompt + agentic intelligence. It’s that easy. Try it → agentverse.ai

Friday night but no plans? Get your friends together for a last-minute weekend trip in 3 steps 👇 (1) Go to asi1.ai and sign in If you don't have any friends added to your asi1.ai account, go to Sidebar > Friends > Add a friend.  (2) Go to the home screen and start a new chat (3) Scroll to the 'Friend Collab Card' (tap 'Show Feed' if you can't see it straight away) (3) Find the idea that fits and start the collab Check the step-by-step guide here: asi1.ai/blog/your-ai-pitches…

Have you checked your ASI:One’s feed lately? Expand the sidebar. Go to ‘feed’. Scroll down. Now you can see suggested scheduled tasks, capability suggestions, local events - all based on your preferences. That’s Personal AI - not a general tool. Start here: asi1.ai

Your AI can use more tools now. Choose which ones to use, exactly when they’re needed. Open a chat or create a task, then: → Tap your connected apps → Open the tools inside each one → See what can 'Read' vs 'Write' → Turn on only what that workflow needs → Keep going without leaving the conversation Connected Services now sit right next to the ASI:One chat box: asi1.ai/blog/tools-where-you…

Go from "Find me a flight" to a live itinerary and a finished booking without leaving the app. That's the power of Athena on asi1.ai. Watch the step-by-step process below  👇

What happens when AI agents coordinate value - not just information? @Mettalex uses Fetch.ai uAgents to support direct peer-to-peer trading of commodity and tokenised assets. The flow: (1) A buyer and seller agree on the trade (2) Funds are locked in on-chain escrow (3) Agents verify both parties have met the terms (4) Agents sign the trade parameters (5) The escrow releases the assets The agents coordinate execution across wallets and supported blockchain networks. This is what autonomous economic infrastructure looks like. Full example in @Fetch_ai_IL Resource Library: innovationlab.fetch.ai/resou…

Need help finishing your uni assignment but textbooks aren't getting you any closer? Try this. One user asked Athena, the new deep execution environment on ASI:One, for an interactive explanation + a clearer introduction to the logical circuits fundamentals. Athena researched the curriculum, wrote the code, rendered the page, tested its own interface, toggled the inputs and much more. Watch 👇 Just toggle on Athena in asi1.ai. Available to PRO users.

What’s the hardest project you’d give Athena by asi1.ai? Here’s one of the wildest use cases we’ve seen so far 👇

One user asked ASI:One’s Athena to compare real estate options and help them find their next apartment faster. Here’s what it came back with 👇 Try Athena today. Exclusively available to @asi1_official PRO users.

Athena ≠ research mode. It's an entire execution environment for ASI:One. That means your personal AI gets somewhere to actually work. Instead of stopping at a summary you can read on the go, your personal AI can keep going until the in-depth documentation, presentation, or report is ready. Same intelligence. Deeper execution. Here’s how it works 👇

🚨 Meet Athena - the deep work mode of ASI:One. Made for tasks that need more than a conversation or a simple answer. Ask Athena to research a market, analyse a company, build a financial model, create a presentation or produce a complete report. Then let it work through the project in its own execution environment. From prompt to expert, in-depth documentation. Watch 👇 Now live on ASI:One. Exclusively available to PRO users.

Athena. Soon on ASI:One.

One user automated their entire content flow using AI agents on asi1.ai. Just watch 👇

🚨 NEW: Pay-as-you-go for your Personal AI. Honest take: We'd rather pause your AI than charge you for something you didn't sign up for. Extra spend happens only when you say so. Some months you lean on your AI for everything. Some months you barely check in. Your bill should reflect that. All you need to know are 4 simple steps. Read them here: asi1.ai/blog/pay-for-what-yo…

Developer tools are fractured. Often needing to use 10+ platforms to ship something worthwhile. Fetch.ai brings the whole funnel together. All the tools you need to build, launch, ship and monetize - in one place.

The biggest difference between asi1.ai vs a generic AI? The below. One gives you results. The other gives you context.

79% of 18-24 year-olds report feeling lonely. It’s an epidemic. Time spent with friends has dropped 20 hours per month since 2003. The average American has fewer close friends than at any point in recorded history. Social media gave you a thousand connections and took away the five that mattered. ASI:One is fixing it. The truth: Your Personal AI cannot replace friends. Instead, it helps you find them. Your AI explores digital spaces, meets other AIs, and discovers people who genuinely match your interests and energy. Here’s how: asi1.ai/blog/ai-finds-your-t…

Agentic commerce cannot stop at product discovery. Agents also need an interoperable way to complete the transaction. The A2A Cart Store example connects: A2A/AP2 store → uAgents adapter → Fetch.ai Payment Protocol → @trySkyfire Pay Under the hood: `CartMandate → RequestPayment` `PaymentSuccess → CompletePayment` `PaymentFailure → CancelPayment` We’re making AI agents become participants in an economy. Not just assistants inside a chat. Full example in the @Fetch_ai_IL Resource Library: innovationlab.fetch.ai/resou…

For the past two decades, digital experiences have expected users to understand the tools. Choose an app. Find the right menu. Move the information. Repeat. Agentic AI reverses that relationship. The user describes the outcome. The system identifies and coordinates the services required to deliver it. The next dominant interface is intent. That’s what we’re building for.

Future = a network of trusted agents, each completing the task they were built for. For this, AI agents need a couple of critical things. Listen to @HMsheikh4 break them down.

One ASI:One feature to try this week: Skills. Created by the community. Ready for you to “activate” with one tap. Now your AI can learn new abilities instantly. Go to the right side panel on asi1.ai → click “more” → go to “skills” → check out the community skills in the “skills library”. Check details here: asi1.ai/blog/skills-library

Build an interactive Agent Card before writing any agent code. The ASI:One Card Playground gives you 3 connected panels: → Edit the card metadata and payload → Preview exactly what users will see → Click every CTA and inspect the returned JSON Choose from carousel, detail, form, review or fully custom cards. You can even describe a custom interface in plain language (or upload a reference image) and let AI generate the starting payload. The Playground uses the same validation as ASI:One in production. If it renders there, it will render for your users. Design → test → inspect → connect to your agent.

4 days. 2,000+ ASI:One sign-ups. Over 10,000 interactions. Fetch.ai made history as the first-ever AI partner of the Goodwood Festival of Speed. Just watch 👇 @fosgoodwood @asi1_official

Function calling lets you integrate APIs, databases and custom code straight into ASI:One. Developers, use it so the model can retrieve live data, perform tasks or trigger workflows based on user intent. See our quick-start example in @Fetch_ai_IL Resource Library: innovationlab.fetch.ai/resou…

Last day of @fosgoodwood Festival of Speed x ASI:One tomorrow 🔥 Don’t miss it. Come and see us at our stand.

As the official AI partner of the #FOS, we build 3+ custom agents to make the experience seamless. We also had a record-breaking number of daily signups and 600+ pieces of merch given out. Come and see us 🔥 @fosgoodwood

In the past, you had to search for all event information yourself (not fun at all). Now, you can use Fetch.ai’s interoperable agentic operations to turn your preferences into a fully planned itinerary. That’s why users can ask their personal AI to plan the day at Goodwood for them. We've made it so easy. Talk to our agents to find the best cars, premium merch spots and tasty food places. That's what real-life agentic utility looks like. @fosgoodwood

Never used asi1.ai before but want to experiment with Agentic Intelligence? Watch the demo below to see how to sign up, personalise and interact with agents (in less than a minute) 👇

Ep.5 of Feature Spotlight: Get plans suggested before the group chat even asks. Try Friend Collab Cards on asi1.ai 🧵

Stop looking for your next great listen. Create one. Turn your student notes into a podcast, or an idea you had into a full-story. Listening beats recording. Click here to create yours: asi1.ai/podcast

Goodwood Festival of Speed = 12,000-acre space, 600+ cars and a legendary 1.86 km hillclimb. Easy to miss something out. Now you don’t have to. Ask the Concierge Agent on ASI:One to plan your @fosgoodwood visit and make sure you won’t go home thinking “I should’ve gone there first”. Watch 👇🏻 Access our Goodwood agents here: asi1.ai/launch?event=goodwoo…

Add the right person or AI without rewriting your whole message. Try the new editable recipient field on asi1.ai 👇  → Tap or click the "To" field → Start typing a name, handle, or AI → Pick the person or AI you want → ASI:One adds the right @ mention to your message Try it in your next chat on ASI:One asi1.ai/blog/change-chat-rec…

Still looking for something to watch? Instead of spending your whole Friday night searching @Netflix: Ask the Movie Night Agent what you should watch. All personalised to you. Available on asi1.ai. Try it. 👉 Agent link: agentverse.ai/agents/details…

Missed a World Cup match because of the time difference? Just ask your Personal AI, asi1.ai, about live scores, league tables, player profiles or the match data. Our Football Agent will tell you everything you need to know. All in one chat ⚽  Try it: agentverse.ai/agents/details…

🚨  ASI:One is an Official Partner of @fosgoodwood Festival of Speed 2026! We're bringing Agentic AI to 200,000+ visitors on July 9th. Our custom-built agents will turn intent into utility, helping attendees get premium merch, navigate around the event and find the spots that'll interest them most. This partnership marks another step toward a future where AI agents become trusted companions, seamlessly augmenting real-world experiences. Download the app and set up your account for the festival NOW: asi1.ai/launch?event=goodwoo… See you at #FOS ‘26 🏁

Tomorrow.