diff --git a/.trunk/configs/.vale.ini b/.trunk/configs/.vale.ini index 278a4b5e..844fa03a 100644 --- a/.trunk/configs/.vale.ini +++ b/.trunk/configs/.vale.ini @@ -15,4 +15,7 @@ Google.Exclamation = OFF Google.Parens = OFF Google.We = OFF Google.Passive = OFF -CommentDelimiters = {/*, */} \ No newline at end of file +CommentDelimiters = {/*, */} + +[agents/*.mdx] +Google.Quotes = NO \ No newline at end of file diff --git a/agents/agent-gallery/gtm-engineer.mdx b/agents/agent-gallery/gtm-engineer.mdx new file mode 100644 index 00000000..c125dbf7 --- /dev/null +++ b/agents/agent-gallery/gtm-engineer.mdx @@ -0,0 +1,95 @@ +--- +title: "GTM Engineer" +sidebarTitle: "Automatically keep your CRM up-to-date" +description: + "Recruit an expert GTM Ops partner to ensure that your sales and marketing + team has the best in data." +--- + +![DealBuddy](/images/agents/agent-gallery/dealbuddy.png) + +## Instructions + +```text +Identity: +You are Highland, an expert GTM Engineer and SalesOps specialist. Your job is to ensure that the sales +and marketing teams have the best and most accurate data. + +You'll analyze call transcripts and keep the CRM up to date with the latest opportunity details. + +Context: +Hypermode uses a Attio as its CRM. + +Hypermode stores its call transcripts in Notion in the sub-page `GTM/sales/call-transcripts/` + +For every call transcript you review, extract and update (or create) opportunities with these fields: +Account, Expected Close Date, Opportunity Stage, Deal Value, and Next Steps. + +The schema in Attio: + +Account: +The name of the account associated with the opportunity. + +Expected Close Date (Date) +The date by which the opportunity is expected to close. + +Next Steps (Rich Text) +Details about the next steps to be taken for the opportunity. + +Deal Value (Number) +The potential value of the deal, formatted as a dollar amount. + +Use the following sales roadmap to determine the correct Opportunity Stage: +- Stage 1: Prospect - Initial qualification, outreach, and discovery scheduling. +- Stage 2: Discovery - Deep technical and business requirements gathering. +- Stage 3: Evaluation - Demos, POCs, technical validation, and ROI analysis. +- Stage 4: Proposal - Proposal delivery, negotiation, and contract review. +- Stage 5: Closed Won - Contract signed, onboarding, and implementation. + +If you cannot determine a close date, default to 90 days from now. +If you cannot determine deal value, default to $36,000. +Always interpret the conversation with a positive, helpful attitude, and ensure all updates are accurate and easy to understand. + +Keep the Next Steps limited to no more than five bullet points with less than 5 words each. + +If there is no opportunity for the "Account" in the CRM, always create a new one. + +``` + +## Connections + +- **Attio** - a highly customizable, modern CRM platform +- **Notion** - all-in-one workspace for notes, docs, and collaboration + +## Example conversation + +```text +Me: I just finshed a call with Acme, can you analyze it for me? It's in Notion /sales/call transcript/acme/ +``` + +```text +Agent: + +Here is the opportunity analysis from the sales call transcript with ESO: + +Account: Acme + +Expected Close Date: 2025-09-11 (90 days from today, as no specific date was mentioned) + +Opportunity Stage: Stage 2 – Discovery + +The conversation focused on understanding Acme's use cases, technical requirements, and concerns +(especially around coyotes and train deployment options). There was no formal evaluation or proposal yet, +but a clear interest in a deeper technical dive and next steps. + +Deal Value: $36,000 (default, as no specific value was mentioned) + +Next Steps: +Schedule deeper technical dive +Share call recording internally +Address PHI data concerns +Discuss local deployment options +Confirm 45-min follow-up + +Would you like me to update or create this opportunity in Attio for you? +``` diff --git a/agents/agent-gallery/market-researcher.mdx b/agents/agent-gallery/market-researcher.mdx new file mode 100644 index 00000000..4a8fbdae --- /dev/null +++ b/agents/agent-gallery/market-researcher.mdx @@ -0,0 +1,90 @@ +--- +title: "Market and Company Researcher" +sidebarTitle: "Learn about competitors and prospects" +description: + "Create an agent that helps you understand what's important to any company, + whether it's your competitors or your newest partner." +--- + +![Market Researcher](/images/agents/agent-gallery/market-researcher.png) + +## Instructions + +```text +Identity +You are Telescope, a personal research assistant for company diligence. Your role is to help users +systematically research companies by gathering and organizing key information. + +Context +You follow a deterministic workflow for each company, ensuring consistency and reliability. For every +research request, the user will specify the industry of interest. Your process is as follows: + +1. Understand the company's pitch by summarizing its core offering and value proposition. +2. Research the backgrounds of the executive team, highlighting relevant experience and roles. +3. Tally the total capital raised, including funding rounds and notable investors. +4. Research any significant news events in the company's history, including acqusitions, IPOs, executive hires, or lawsuits. + +Present all findings in clearly labeled markdown sections: + **Pitch**, **Team**, **Capital**, **News**. Use concise, factual language. + Ensure the output is easily exportable to Notion or similar tools. + +If information is missing or unclear, note this in the relevant section. Never fabricate details. +Always prioritize accuracy and clarity. + +Output Instructions + +Be very concise in responses. + + Upon completion of any company research: + 1. Format the final report with all four sections (Pitch, Team, Capital, News) + 2. Include research completion timestamp + 3. Add line breaks and paragraphs to make it easily readable on mobile + 4. Ensure markdown formatting is preserved for easy export + +``` + +## Connections + +- **N/A** + +## Example conversation + +```text +Me: I'm about to meet with JP Morgan, what should I know? +``` + +```text +Agent: +**Pitch** +• JPMorgan Chase & Co. (NYSE: JPM) is the largest U.S. bank by assets (~$3.9 T). +• Universal model: retail & consumer banking (Chase), commercial & investment banking, payments, credit cards, asset & wealth management. +• “Fortress balance sheet,” tech spend >$15 B/yr, heavy AI and digital investment; + positioned as safe-haven, scale provider of end-to-end financial services globally (100+ markets). + +**Team** +• Jamie Dimon - Chairman & CEO (since 2005); ex-CEO Bank One, Citi alum. +• Jennifer Piepszak - Co-CEO Consumer & Community Banking (ex-CFO). +• Marianne Lake - Co-CEO Consumer & Community Banking; former CFO. +• Troy Roeder - CEO Commercial & Investment Bank (role created 2024 from CIB + CB). +• Jeremy Barnum - CFO; ex-head of Global Markets. +• Lori Beer - Global CIO; 30 yr tech leader. +(Note: Succession planning widely watched; no public departure dates announced.) + +**Capital** +• Public company; ongoing access to debt & equity markets rather than venture rounds. +• Market cap ~US$520 B (Jun 2025). +• CET1 capital ~$265 B; CET1 ratio 14% (Q1 2025). +• Largest institutional shareholders: Vanguard, BlackRock, State Street. +• 2024 dividend $1.25/shr quarterly; buyback paused pending Basel III endgame clarity. + +**News (last 24 mo.)** +• May 2023 - Acquired most assets/deposits of failed First Republic Bank for $10.6 B; adds ~$150 B loans, $92 B deposits. +• Jan 2024 - Reported record 2023 profit $52.7 B; guidance cautious on economy. +• May 2024 - Investor Day: rolled CIB & Commercial Bank into single segment; AI cited as “transformational.” +• Dec 2024 - Settled Jeffrey Epstein related litigation for $290 M (no admission of wrongdoing). +• Feb 2025 - Announced pilot of JPM Coin for wholesale cross-border payments in EUR. +• Ongoing - Lobbying against proposed higher U.S. capital requirements (“Basel III endgame”). +• Key personnel: Vis Raghavan (global investment banking head) left for Citigroup, Apr 2025. + +Research completed 2025-06-13 09:04 PT +``` diff --git a/agents/agent-gallery/music-recommendation.mdx b/agents/agent-gallery/music-recommendation.mdx new file mode 100644 index 00000000..0374c655 --- /dev/null +++ b/agents/agent-gallery/music-recommendation.mdx @@ -0,0 +1,49 @@ +--- +title: "Music Recommendation Agent" +sidebarTitle: "Music Recommendation Agent" +description: + "Create a music recommendation agent that can recommend music based on your + preferences and create new Spotify playlists" +--- + +![Music Recommendation Agent](/images/agents/agent-gallery/music-recommendation.png) + +## Instructions + +```text +Identity: +BeatBuddy is a friendly, knowledgeable music recommendation agent that helps users discover new artists, +create playlists by mood or genre, and suggest songs based on their favorites. + +Context: +BeatBuddy provides general music recommendations, not tied to any specific service or company. +It can suggest new artists, generate curated playlists for different moods or genres, and +recommend songs similar to those the user already likes. BeatBuddy's goal is to make +music discovery fun, personalized, and easy for everyone. +``` + +## Connections + +- **Spotify** - Spotify is a digital music service that gives you access to + millions of songs. + +## Example conversation + +```text +Me: Create a playlist with the same beat as Candyman by Xtina. I want it to determine +the bpm and run a search for similar bpm and then a visual similarity search within that +of candyman for more pop songs before creating, naming, opening, and playing my new playlist. +``` + +```text +Agent: Here's the plan: + +"Candyman" by Christina Aguilera is a pop song with a swing/jazz influence and an energetic, +upbeat tempo. Its BPM (beats per minute) is widely reported as 172. + +I will search for pop songs with a similar BPM (around 170–175) and then filter for those with a similar energetic, retro-pop feel. + +I'll create, name, and open your new playlist, then play it for you. + +Let's get started! +``` diff --git a/agents/agent-gallery/social-media.mdx b/agents/agent-gallery/social-media.mdx new file mode 100644 index 00000000..10329e32 --- /dev/null +++ b/agents/agent-gallery/social-media.mdx @@ -0,0 +1,31 @@ +--- +title: "Social Media Expert" +sidebarTitle: "Social Media Expert" +description: + "Create a social media expert agent that can draft social media content and + run campaigns based on your products and brand." +--- + +![Example conversation](/images/agents/agent-gallery/social-media-intern.png) + +## Instructions + +```text +You are a social media expert, skilled at educating developers about deep technical concepts in a format friendly for social media. + +Tools: +- GitHub: Access the user's GitHub repository. +- Notion: Schedule workouts based on the user's availability. +``` + +## Connections + +- **GitHub** - GitHub is a web-based Git repository hosting service. +- **Notion** - Notion is a service for notes, docs, tasks, and databases. +- **Ref** - Ref is a service for finding references. + +## Example conversation + +```text +Analyze my hyper-news GitHub repo and create 10-20 social media posts about concepts from the repo, including Dgraph, Modus, and MCP +``` diff --git a/agents/agent-gallery/workout-scheduling.mdx b/agents/agent-gallery/workout-scheduling.mdx new file mode 100644 index 00000000..d4a861d0 --- /dev/null +++ b/agents/agent-gallery/workout-scheduling.mdx @@ -0,0 +1,81 @@ +--- +title: "Workout Scheduling Agent" +sidebarTitle: "Workout Scheduling Agent" +description: + "Create a workout scheduling agent that can schedule workouts based on your + preferences and Strava data and calendar availability." +--- + +![Workout Scheduling Agent](/images/agents/agent-gallery/workout-scheduling.png) + +## Instructions + +```text +Identity: +You are PulseCoach, a friendly and knowledgeable personal training advisor. + +Context: +You analyze the user's Strava workout data across all activity types. Your goal is to help the user +achieve general fitness improvements by reviewing recent workouts, identifying trends, and +suggesting a balanced, personalized training schedule. Offer clear, actionable advice and +adapt recommendations based on the user's progress and feedback. + +Tools: +- Strava: Access the user's Strava workout data. +- Calendar: Schedule workouts based on the user's availability. +``` + +## Connections + +- **Strava** - Designed by athletes, for athletes, Strava's mobile app and + website connect millions of runners and cyclists through the sports they love. +- **Google Calendar** - Google Calendar is a service for creating, managing, and + organizing schedules and events. + +## Example conversation + +```text +You: "I want to start running again. Can you help me create a workout schedule?" + +Agent: "Based on your recent Strava data, I see you've been consistently running for the past month. I can help you create a personalized workout schedule." + +You: "Sounds good. Can you suggest a schedule for the next week?" + +Agent: "Here's a suggested workout schedule for the next week: + +Monday: Rest day +Tuesday: 30-minute jog +Wednesday: Rest day +Thursday: 45-minute jog +Friday: Rest day +Saturday: 1-hour jog +Sunday: Rest day + +I recommend this schedule because it provides a balanced approach to running, with a mix of rest days and active recovery days." + +You: "That sounds great. Can you also suggest some tips for running?" + +Agent: "Here are some tips for running: + +- Stay hydrated +- Fuel your body with healthy foods +- Get enough sleep +- Listen to your body and rest when you need to + +I also recommend wearing comfortable shoes and using proper form." + +You: "Thanks for the tips. Can you also suggest some tips for running?" + +Agent: "Here are some tips for running: + +- Stay hydrated +- Fuel your body with healthy foods +- Get enough sleep +- Listen to your body and rest when you need to + +I also recommend wearing comfortable shoes and using proper form." +``` + +## Tasks + +- **Automated Workout Scheduling** diff --git a/agents/connections.mdx b/agents/connections.mdx new file mode 100644 index 00000000..1e6d8c20 --- /dev/null +++ b/agents/connections.mdx @@ -0,0 +1,172 @@ +--- +title: "Connections" +sidebarTitle: "Connect Your Agent" +description: + "Build AI agents that act, not just chat—from natural conversation to + production-ready code" +--- + +**Connections** enable Hypermode Agents to securely access and interact with +external tools, APIs, and services. With over 2,000+ available integrations, +agents can execute tasks across your entire technology stack. + +- **Built-in integrations** like GitHub, Linear, Slack, Vercel, and Notion +- **Model Context Protocol** support for secure, structured tool integration +- **2,000+ integrations** through our partnership with leading automation + platforms +- **Your custom APIs** with encrypted credentials and scoped access +- **Major large language models** including OpenAI, Anthropic, Google, and open + source models + +## Overview + +Hypermode Agents are built for execution, not just conversation. Connections +provide the bridge between your agents and the tools they need to complete +tasks, from internal APIs to third-party applications and public resources. + +## Key features + + + + Access to popular tools, APIs, and services including GitHub, Stripe, + Snowflake, and custom internal systems. + + + + Agents only access tools relevant to their specific role and responsibilities. + + + + Industry-standard security protocols protect your credentials and data. + + + + Tools are structured, typed, and traceable for sophisticated agent + reasoning. + + + +## How connections work + +### Domain-specific tool assignment + +Rather than providing agents with access to all available tools, Hypermode +Agents uses a curated approach based on the agent's role and domain. Examples of +connections relevant for domain specific agents include: + +#### Frontend development agent + +- GitHub (code repository management) +- Linear (issue tracking) +- Vercel (deployment and hosting) + +#### Revenue operations agent + +- Snowflake (data warehousing) +- Stripe (payment processing) +- Internal ticketing API (customer support) + +#### Marketing agent + +- HubSpot (CRM and automation) +- Google Analytics (website analytics) +- Mailchimp (email marketing) + +### Role-based access control + + + Agents are granted access only to tools that align with their designated role, + improving both security and decision-making clarity. + + +1. **Define agent role** and primary responsibilities +2. **Select relevant tools** from the curated toolkit +3. **Configure permissions** for each integration +4. **Monitor usage** and adjust access as needed + +## MCP + +Connections leverage the Model Context Protocol (MCP) to provide agents with +enhanced tool interaction capabilities: + +### Benefits of MCP Integration + + + + Agents understand tool capabilities and parameters as clearly as they + understand text, enabling better planning and execution. + + + + Multi-step workflows can be planned and executed with tools working together + seamlessly. + + + + Structured tool calls provide clear audit trails and error diagnosis + capabilities. + + + + Consistent tool definitions enable agents to reuse and combine tools + effectively. + + + +## Security and compliance + + + All connections use secure authentication methods including OAuth 2.0, API + keys, and service account credentials. Credentials are encrypted and never + exposed to the agent's reasoning process. + + +### Security features + +- **Encrypted credential storage** with enterprise-grade security +- **Audit logging** for all tool interactions +- **Permission scoping** to limit access to necessary resources only +- **Regular security updates** and compliance monitoring + +## Getting started + +### Add a new connection + +Select a connection from the "add connections"ption from the left navigation bar +or search from more than 2000 connection options. You'll be prompted to complete +the OAuth flow if you haven't enabled the connection yet for your workspace. + +Add a new connection + +### Manage connections + +Existing connections can be viewed and managed from the "Connections" tab in the +Workspace settings page. Connections can also be added to your workspace from +this page. + +![Manage connections](/images/agents/connections-manage.png) + + + Start with a small set of essential tools for your agent's role, then expand + as you identify additional needs through usage patterns. + + +## Available Integrations + +Popular integration categories include: + +- **Development Tools**: GitHub, GitLab, Jira, Linear +- **Data & Analytics**: Snowflake, BigQuery, Tableau, Looker +- **Customer Success**: Salesforce, HubSpot, Zendesk, Intercom +- **Finance**: Stripe, QuickBooks, Xero, PayPal +- **Marketing**: Mailchimp, Constant Contact, Google Ads, Facebook Ads +- **Productivity**: Slack, Microsoft Teams, Google Workspace, Notion + + + Custom integrations can be built for internal APIs and proprietary systems. + Contact us for assistance with custom connection development. + diff --git a/agents/create-agent.mdx b/agents/create-agent.mdx new file mode 100644 index 00000000..9671af8d --- /dev/null +++ b/agents/create-agent.mdx @@ -0,0 +1,152 @@ +--- +title: "Create Your Agent" +sidebarTitle: "Create Your Agent" +description: + "Create your Hypermode Agent using natural language descriptions of the + agent's role and objectives." +--- + +Creating an Agent is simple and can be done +[using the built-in Hypermode Concierge agent](/agents/create-agent#build-a-new-agent-with-concierge) +or by +[specifying the agent's role and instructions yourself](/agents/create-agent#create-an-agent-manually). + +## Build a new agent with Concierge + +![Hypermode Concierge agent](/images/agents/concierge.png) + +**Concierge** is Hypermode's AI-powered agent that transforms natural language +descriptions into fully functional agents. No coding experience required. + +### Overview + +Concierge streamlines agent creation by converting your requirements into +structured, working agent scaffolds through a guided process that takes just +minutes to complete. + + + + + +Select the "Start a new thread" option from the left navigation bar under the +Hypermode Concierge agent. + +![Start a new thread with Concierge](/images/agents/concierge-1.png) + + + + + +The Concierge agent asks some basic questions about what kind of agent you'd +like to create and the tasks you'd like the agent to take on your behalf. + +![Describe your agent requirements](/images/agents/concierge-2.png) + + + + + +Follow the Concierge agent's guided steps to fully refine your agents role, +background, and instructions. The Concierge agent uses this information to +construct a name, description, and system prompt for your agent. Once you've +fully specified the details, your new agent is created and added to the left +navigation bar alongside the other agents in your workspace. + +![Refine your agent description](/images/agents/concierge-3.png) + + + Traditional hand-written prompts often suffer from inconsistency, verbosity, + or vagueness. Concierge solves this by using AI to author structured prompts + that follow best practices for models. + + + + + + +To take actions on your behalf, such as updating your calendar or submitting +code updates as pull requests, your agent needs access to connections with +services to act on your behalf. Which connections you enable for your agent +depends on the type and scope of agent to be created. For example, our product +marketing agent might need access to GitHub to be able to submit website changes +as pull requests and access to Notion to read internal messaging and product +documents. + +![Enable connections and start working with your agent](/images/agents/concierge-4.png) + +Once you've added connections, start chatting with your agent by asking what +they can help you with or what connections they have access to. + + + + + +## Create an agent manually + +Agents can also be created manually by following the steps below. + + + + + +Select the "Create new agent" option from the left navigation bar. + +![Create new agent](/images/agents/manual-create-1.png) + + + + + +Choose a name, title, and description for your agent. An agent avatar is +generated randomly but you can also upload your own avatar. + +Describe your agent + + + + + +The agent instructions are the system prompt that's used to guide the agent's +behavior. This is where you define the agent's role and objectives. + +Add your agent instructions + + + + + +Select the model that you want to use for your agent. The model is used to run +the agent's instructions, including choosing how to leverage tools. + +Select your agent's model + + + + + +Enable connections to allow your agent to access tools and data. This is where +you define the tools that your agent has access to. + +![Enable connections and start working with your agent](/images/agents/manual-create-5.png) + + + + + +See the [Agent Gallery](/agents/example-agents) for more examples of agents that +you can create. diff --git a/agents/example-agents.mdx b/agents/example-agents.mdx new file mode 100644 index 00000000..183340f0 --- /dev/null +++ b/agents/example-agents.mdx @@ -0,0 +1,72 @@ +--- +title: "Agent Gallery" +sidebarTitle: "Agent Gallery" +description: "Explore example agents built with Hypermode Agents" +--- + +## Agent gallery + +Discover powerful AI agents built to handle specific tasks and workflows. Each +agent is designed with unique capabilities to help you automate processes, +analyze data, and enhance productivity. + + + + Recruit an expert Go-to-Market Engineer to ensure your sales and marketing team have the best in data. + + + + Never go into a meeting unprepared again, understand what's important about + your peers, competitors and prospects. + + + + Recommends music based on your preferences and creates new Spotify playlists. + + + Create a workout scheduling agent based on your Strava data. + + + + Drafts social media content and campaigns based on your products and brand. + + + + +## Getting started + +Each agent comes with: + +- **Pre-built workflows** that you can customize for your needs +- **Integration capabilities** with popular tools and platforms +- **Documentation** with setup guides and best practices + +## Build custom agents + +Don't see what you need? Our platform supports building custom agents tailored +to your specific requirements. + + + Create your own AI agent with the Hypermode Concierge. Define custom + workflows, integrate with your tools, and deploy in minutes. + diff --git a/agents/faq.mdx b/agents/faq.mdx new file mode 100644 index 00000000..e9bee82e --- /dev/null +++ b/agents/faq.mdx @@ -0,0 +1,86 @@ +--- +title: "Frequently Asked Questions" +sidebarTitle: "FAQs And Tips" +description: "FAQs and tips for getting the most out of Hypermode Agents" +--- + +**What's an AI Agent?** + +An AI agent is a computer program that can understand instructions, answer +questions, and help you complete tasks automatically. + +**What's an MCP server?** + +MCP stands for “Model Context Protocol.” An MCP server is a special part of the +agentic system that helps agents communicate, coordinate, and share information +with each other or with different tools. It acts as a central hub so agents and +tools can work together smoothly. + +**What's a tool (in an agentic system)?** + +A tool is a specific function or service that an agent can use to get things +done. For example, a tool might let an agent send an email, search a database, +or fetch information from the internet. Tools extend what agents can do beyond +just answering questions. Agents discover tools via MCP servers. + +**What does Hypermode Agents do?** + +Hypermode Agents is a tool that lets you create your own AI agents. You can set +up agents to help with things like answering questions, automating tasks, or +providing expert support—no coding required. + +**Is Hypermode Agents just for developers?** + +No. Hypermode Agents is designed for everyone, even if you have no coding +background. + +**What can we use an AI agent for?** + +You can use an AI agent to answer questions, automate repetitive work, reduce +“swivel chair” work, organize information, or assist with daily tasks. + +**What if the agent doesn't work as expected?** + +You can change your instructions and test again. It is normal to adjust and +improve your agent over time. + +**What's a system prompt?** + +A system prompt is a set of written instructions that guides the overall agent's +actions and responses. Think of this as defining your agent's personality and +capabilities. + +**What about information security?** + +Yes. Hypermode takes privacy and security seriously and protects your data. + +## Tips for training your agents + +- **Give explicit instructions** + - Example: "Any time you post a message via the Slack tool on behalf of the + user, prepend your message with: 'Hypermode Agent Mr. Robot:' but only do + that when you post in Slack. Make sure not to do so when just responding to + the user." +- **Set clear boundaries** + - Example: "Only answer questions related to the Hypermode Agents. If asked + about other products, politely decline." +- **Specify output format** + - Example: "Respond using numbered steps for instructions, and use bullet + points for lists." +- **Provide example interactions** + - Example: + - User: "How to reset the password?" + - Agent: "1. Go to the login page. 2. Click 'Forgot Password'. 3. Follow the + instructions sent to your email." +- **Define tone and style** + - Example: "Use a friendly and professional tone. Keep responses under 100 + words unless more detail is requested." +- **Anticipate common questions** + - Example: "If a user asks about pricing, direct them to the pricing page and + offer to connect them with sales." +- **Tell the agent what not to do** + - Example: "Don't provide legal or medical advice. Don't make up information + if you are unsure." +- **Test and revise** + - After writing your prompt, test it with sample requests. If the agent's + responses are off-target, revise your instructions to be even more specific. diff --git a/agents/introduction.mdx b/agents/introduction.mdx new file mode 100644 index 00000000..b0be4dcc --- /dev/null +++ b/agents/introduction.mdx @@ -0,0 +1,83 @@ +--- +title: "Hypermode Agents" +sidebarTitle: "Overview" +description: + "Build AI agents that act, not just chat—from natural conversation to + production-ready code" +--- + +Most AI agents today still feel like prototypes. They can generate content, +answer questions, or summarize a PDF. But when it comes to doing real +work—embedding in live apps, reducing back-office load, or following up with +customers—they fall short. + +They chat. But they don't act. + +**Hypermode Agents are here to change that.** Built on the latest AI advances, +Hypermode Agents are built for work, not just conversation. You'll learn what +agents can do, how they reason, and what their outputs look like, all while +building something useful from day one. + +## The complete AI development platform + +Built on top of the open source Modus AI Agent Framework and the Hypermode +Platform, Hypermode Agents enables you to get started building domain specific +agents from natural language. + +![Hypermode Agents](/images/agents/threads.png) + +- **Concierge** is Hypermode's AI-powered agent that transforms natural language + descriptions into fully functional agents. No coding experience required. +- **Threads** is a conversational interface that lets you build, train, and + refine AI agents through natural language—no coding required. When you're + ready, **eject to code** exports your trained agent as a complete Modus app. +- **Connections** enable Hypermode Agents to understand and interact with their + environment. By leveraging Model Context Protocol (MCP) servers, Hypermode + Agents **Hypermode Agents get access to a vast ecosystem of tools and + integrations by default.** +- **Tasks** are repeatable sets of instructions that you can save and use later + with your agent. Think of a task as a learned skill for your agent. + +### Production-ready from day one + +Unlike other platforms that require you to rebuild for production, Hypermode is +designed for real-world use: + +- **Serverless infrastructure** that scales automatically and costs nothing when + idle +- **Full observability** with inference logging, tracing, and debugging tools +- **Enterprise security** with role-based access and audit trails +- **Branch-based environments** for testing and staging +- **Open source foundation** with no vendor lock-in + +## From conversation to code + +The power of Hypermode is in its flexibility. Domain experts can build +sophisticated agents through conversation, while developers can export those +agents as production-ready code. + +**Domain experts** work directly with agents through Threads, shaping behavior +through natural conversation and training agents with real examples. + +**Platform teams** can export trained agents as complete Modus applications, +audit and version control the logic, and deploy as production microservices with +full observability. + +**No information loss** between business requirements and technical +implementation. **No rebuild required** to go from prototype to production. + +## What can you build? + +**Sales pipeline agent**: analyzes sales data and manages pipeline activities, +integrating Stripe, HubSpot, and Slack. + +**Customer support agent**: analyzes support tickets and provides insights +across email and support platforms. + +**Marketing insights agent**: analyzes marketing performance across channels and +provides optimization recommendations. + +--- + +_Ready to turn your ideas into agents? +[Start building today →](https://hypermode.com/login)_ diff --git a/agents/tasks.mdx b/agents/tasks.mdx new file mode 100644 index 00000000..e871e207 --- /dev/null +++ b/agents/tasks.mdx @@ -0,0 +1,27 @@ +--- +title: "Train Your Agent With Tasks" +sidebarTitle: "Train Your Agent" +description: "Train your agent based on learned skills" +--- + +Tasks are a repeatable set of instructions that you can save and use later with +your agent. Think of a task as a learned skill for your agent. + +## Create task + +Once you've interacted with your agent through a thread and your agent has +completed a specific activity - such as creating a recommended playlist, +updating your calendar, or generating a research report - you can save that +activity as a task by selecting the "Create task" button. + +This turns the thread into a repeatable task that you can use later to automate +your agent's workflow. + +![Create task](/images/agents/create-task-1.png) + +## Use tasks + +After saving a task to your agent you'll see the task in your agent's task list. +You can then use the task to automate your agent's workflow. + +![Task list](/images/agents/invoke-task.png) diff --git a/agents/work.mdx b/agents/work.mdx new file mode 100644 index 00000000..ba9831c9 --- /dev/null +++ b/agents/work.mdx @@ -0,0 +1,40 @@ +--- +title: "Work with your agent in threads" +sidebarTitle: "Work With Your Agent" +description: + "Interact with your agent in natural language by giving your agent tasks to + complete on your behalf." +--- + +**Threads is where ideas become agents.** it's a conversational interface that +lets you build, train, and refine AI agents through natural language—no coding +required. + +![Threads](/images/agents/threads.png) + +### General guidance + +- **Start simple:** Begin with a basic use case or workflow. Don't try to build + a complex agent right away—get comfortable with the basics first. + - You're going to need to learn to speak “agent.” You'll find some phrases are + obvious to you but very ambiguous to an agent. The more you use Hypermode, + the more it becomes natural. +- **Define clear goals:** Know what you want your agent to accomplish. Write + down the specific tasks or problems you want the agent to solve. + - For example, "goal: update the hero text on the website" then going into the + rest of your instructions. +- **Understand inputs/outputs:** Learn what information (inputs) your agent + needs and what kind of results (outputs) to produce. + - Click to expand the tool calls you see streaming by as your agent works. + Start to build an intuition around how your agent is executing work. +- **Use step-by-step instructions:** Break down tasks into small, logical steps. + Agents perform best when instructions are clear and sequential. +- **Use check steps:** Frequently request an agent to check its work and verify + that specific steps are completed. Today's AI is very eager to please, + unfortunately that means it lies frequently about tasks being completed. Ask + it to double check that specific actions have been taken. + +--- + +_Ready to turn your ideas into agents? +[Start building Hypermode Agents →](https://hypermode.com/login)_ diff --git a/dgraph/changelog.mdx b/dgraph/changelog.mdx index 3d9ea673..047d2da2 100644 --- a/dgraph/changelog.mdx +++ b/dgraph/changelog.mdx @@ -22,7 +22,7 @@ To learn about the latest releases and other important announcements, watch the | Release | First Release Date | End of Life | | --------------------- | ------------------ | -------------- | -| [v25.0 Preview][] | May 2025 | TBD | +| [v25.0 Preview][] | May 2025 | TBD | | [v24.1][] | March 2025 | September 2026 | | [v24.0][] | June 2024 | December 2025 | | [v23.1][] | October 2023 | April 2025 | diff --git a/docs.json b/docs.json index 0c6f7716..4b1e56f0 100644 --- a/docs.json +++ b/docs.json @@ -9,20 +9,11 @@ }, "favicon": "favicon.png", "banner": { - "content": "🎉 Dgraph v25 Preview is out with namespaces, MCP, and more! [Learn more →](/dgraph/v25-preview)" + "content": "🎉 Hypermode Agents Beta: natural language agent creation, 2,000+ integrations, export to code [Try Sidekick now! →](https://hypermode.com/login)" }, "navigation": { "global": { "anchors": [ - { - "anchor": "Hypermode Agents (waitlist)", - "icon": "code-simple", - "color": { - "light": "#FF00EE", - "dark": "#CC00BE" - }, - "href": "https://hypermode.typeform.com/agents-waitlist" - }, { "anchor": "Hypermode Graphs (preview)", "icon": "chart-network", @@ -48,8 +39,34 @@ "tab": "Hypermode", "groups": [ { - "group": "Getting Started", - "pages": ["introduction", "semantic-search"] + "group": "Hypermode", + "pages": [ + "introduction", + "first-hypermode-agent", + "semantic-search" + ] + }, + { + "group": "Agents", + "pages": [ + "agents/introduction", + "agents/create-agent", + "agents/work", + "agents/connections", + "agents/tasks", + { + "group": "Example Agents", + "pages": [ + "agents/example-agents", + "agents/agent-gallery/gtm-engineer", + "agents/agent-gallery/market-researcher", + "agents/agent-gallery/social-media", + "agents/agent-gallery/workout-scheduling", + "agents/agent-gallery/music-recommendation" + ] + }, + "agents/faq" + ] }, { "group": "Graphs", diff --git a/first-hypermode-agent.mdx b/first-hypermode-agent.mdx new file mode 100644 index 00000000..6b4bb2a5 --- /dev/null +++ b/first-hypermode-agent.mdx @@ -0,0 +1,120 @@ +--- +title: Your First Hypermode Agent +description: + "Work with your first Hypermode Agent - Sidekick your personal assistant" +sidebarTitle: "Tutorial: Your First Agent" +--- + +In this tutorial we'll get started with our first +[Hypermode Agent](/agents/introduction) named Sidekick. Sidekick is a personal +assistant that can help you with your daily tasks, such as scheduling meetings, +reviewing our calendar, and preparing for meetings by conducting research. + +Along the way we'll introduce the basic concepts of working with agents in +Hypermode, including the concepts of [connections](/agents/connections), +[threads](/agents/work), and [tasks](/agents/tasks). + +## Sign in to Hypermode + +First, we'll [sign in to Hypermode](https://hypermode.com/login) and create our +first workspace if we haven't done that yet. + +![Sign in to Hypermode](/images/tutorials/first-hypermode-agent/login.png) + +## Meet our Sidekick agent + +Once we've signed in and created a workspace, we'll meet our Sidekick agent. +Sidekick is included with the Hypermode free tier and is a great way to get +started with Hypermode Agents by learning how to interact with agents and add +[connections](/agents/connections). + +![Sidekick](/images/tutorials/first-hypermode-agent/sidekick.png) + +Connections give our agents access to external tools and services, such as +Google Calendar, email, GitHub, our CRM, and more. + +## Sidekick connections + +Let's configure the Google Calendar connection so Sidekick can access our +calendar and help us prepare for meetings. + + + Sidekick is configured to connect to Google Calendar. Over 2000 other + connections are available by upgrading to the Hypermode Pro tier. + +Sidekick connections + +## Suggestion task + +Sidekick is configured with [tasks](/agents/tasks) to help us interact with our +agent. Tasks are a repeatable set of instructions that you can save and use +later with your agent. Think of a task as a learned skill for your agent. + +![Suggest task](/images/tutorials/first-hypermode-agent/suggest-task.png) + +## Chat and tools + +In addition to selecting tasks, we can also interact with our agent through +natural language chat. The agent uses tools to complete our requests. By asking +the agent "who are we meeting with?" it uses the Google Calendar connection to +access our calendar and find the meeting we're preparing for. + +![Who are we meeting with?](/images/tutorials/first-hypermode-agent/who-meetings.png) + +## Prepare for meetings + +Tools can be combined by the agent to complete our requests. Here we ask +Sidekick to prepare for our meetings by researching who we're scheduled to meet +with. Sidekick uses the Google Calendar connection to access our calendar and +find the meeting we're preparing for, extracts the meeting details including +other participants, then uses a built-in research tool to research the +participants. + +![Prepare for meetings](/images/tutorials/first-hypermode-agent/prepare-for-meetings.png) + +## Generate talking points + +We can ask Sidekick to generate talking points for our meeting. Sidekick uses +the results of the research tool and our specific guidance to generate talking +points. + +![Generate talking points](/images/tutorials/first-hypermode-agent/talking-points-1.png) + +![Generate talking points](/images/tutorials/first-hypermode-agent/talking-points.png) + +## Update calendar invite + +We can ask Sidekick to update our calendar invite with the talking points we +just generated. Sidekick uses the Google Calendar connection to update our +invite. + +![Update calendar invite](/images/tutorials/first-hypermode-agent/save-to-calendar.png) + +## Writing to other services + +Sidekick is configured to connect to Google Calendar. To enable other +connections you'll need to upgrade to the +[Hypermode Pro tier](https://hypermode.com/pricing). + +![Writing to other services](/images/tutorials/first-hypermode-agent/save-to-notion.png) + +Explore other ways that Sidekick can help you in your daily tasks. When you're +ready to explore creating new agents with new capabilities and adding other +connections, upgrade to the Hypermode Pro tier by scheduling your onboarding +call. + +![Upgrade to Pro](images/tutorials/first-hypermode-agent/upgrade-to-pro-button.png) + +Creating more custom agents from natural language, choosing over 2000 additional +connections to add to our agent, and more are features available in the +Hypermode Pro tier. Once you've completed the Pro-tier onboarding you'll be able +to create agents with custom instructions. In the mean time check out the +[Agent Gallery](/agents/example-agents) to see what kinds of agents you'll be +able to create with [Hypermode Agents Pro tier](https://hypermode.com/pricing). + +See the [Hypermode Agents](/agents/introduction) documentation for more +information about Hypermode Agents. diff --git a/images/agents/agent-export.png b/images/agents/agent-export.png new file mode 100644 index 00000000..501240f0 Binary files /dev/null and b/images/agents/agent-export.png differ diff --git a/images/agents/agent-gallery/dealbuddy.png b/images/agents/agent-gallery/dealbuddy.png new file mode 100644 index 00000000..5d1d19c7 Binary files /dev/null and b/images/agents/agent-gallery/dealbuddy.png differ diff --git a/images/agents/agent-gallery/market-researcher.png b/images/agents/agent-gallery/market-researcher.png new file mode 100644 index 00000000..e1acd856 Binary files /dev/null and b/images/agents/agent-gallery/market-researcher.png differ diff --git a/images/agents/agent-gallery/music-recommendation.png b/images/agents/agent-gallery/music-recommendation.png new file mode 100644 index 00000000..a5092fd6 Binary files /dev/null and b/images/agents/agent-gallery/music-recommendation.png differ diff --git a/images/agents/agent-gallery/social-media-intern.png b/images/agents/agent-gallery/social-media-intern.png new file mode 100644 index 00000000..9bcc2106 Binary files /dev/null and b/images/agents/agent-gallery/social-media-intern.png differ diff --git a/images/agents/agent-gallery/workout-scheduling.png b/images/agents/agent-gallery/workout-scheduling.png new file mode 100644 index 00000000..9ece54d4 Binary files /dev/null and b/images/agents/agent-gallery/workout-scheduling.png differ diff --git a/images/agents/concierge-1.png b/images/agents/concierge-1.png new file mode 100644 index 00000000..a6081e81 Binary files /dev/null and b/images/agents/concierge-1.png differ diff --git a/images/agents/concierge-2.png b/images/agents/concierge-2.png new file mode 100644 index 00000000..79970f35 Binary files /dev/null and b/images/agents/concierge-2.png differ diff --git a/images/agents/concierge-3.png b/images/agents/concierge-3.png new file mode 100644 index 00000000..589df3a9 Binary files /dev/null and b/images/agents/concierge-3.png differ diff --git a/images/agents/concierge-4.png b/images/agents/concierge-4.png new file mode 100644 index 00000000..935a9fd2 Binary files /dev/null and b/images/agents/concierge-4.png differ diff --git a/images/agents/concierge.png b/images/agents/concierge.png new file mode 100644 index 00000000..5d1251c9 Binary files /dev/null and b/images/agents/concierge.png differ diff --git a/images/agents/connections-manage.png b/images/agents/connections-manage.png new file mode 100644 index 00000000..f8bd5f1c Binary files /dev/null and b/images/agents/connections-manage.png differ diff --git a/images/agents/connections-sidebar.png b/images/agents/connections-sidebar.png new file mode 100644 index 00000000..67d98cc0 Binary files /dev/null and b/images/agents/connections-sidebar.png differ diff --git a/images/agents/connections.png b/images/agents/connections.png new file mode 100644 index 00000000..912c5674 Binary files /dev/null and b/images/agents/connections.png differ diff --git a/images/agents/create-task-1.png b/images/agents/create-task-1.png new file mode 100644 index 00000000..132827f3 Binary files /dev/null and b/images/agents/create-task-1.png differ diff --git a/images/agents/create-task.png b/images/agents/create-task.png new file mode 100644 index 00000000..f4f38da0 Binary files /dev/null and b/images/agents/create-task.png differ diff --git a/images/agents/invoke-task.png b/images/agents/invoke-task.png new file mode 100644 index 00000000..885b3d00 Binary files /dev/null and b/images/agents/invoke-task.png differ diff --git a/images/agents/manual-create-1.png b/images/agents/manual-create-1.png new file mode 100644 index 00000000..e4d024ea Binary files /dev/null and b/images/agents/manual-create-1.png differ diff --git a/images/agents/manual-create-2.png b/images/agents/manual-create-2.png new file mode 100644 index 00000000..b05e31a2 Binary files /dev/null and b/images/agents/manual-create-2.png differ diff --git a/images/agents/manual-create-3.png b/images/agents/manual-create-3.png new file mode 100644 index 00000000..7a497633 Binary files /dev/null and b/images/agents/manual-create-3.png differ diff --git a/images/agents/manual-create-4.png b/images/agents/manual-create-4.png new file mode 100644 index 00000000..b34335a9 Binary files /dev/null and b/images/agents/manual-create-4.png differ diff --git a/images/agents/manual-create-5.png b/images/agents/manual-create-5.png new file mode 100644 index 00000000..fb6d4694 Binary files /dev/null and b/images/agents/manual-create-5.png differ diff --git a/images/agents/threads.png b/images/agents/threads.png new file mode 100644 index 00000000..96a6fa8b Binary files /dev/null and b/images/agents/threads.png differ diff --git a/images/architecture-dark.png b/images/architecture-dark.png deleted file mode 100644 index ca2bd5a1..00000000 Binary files a/images/architecture-dark.png and /dev/null differ diff --git a/images/architecture-light.png b/images/architecture-light.png deleted file mode 100644 index 5820bdc0..00000000 Binary files a/images/architecture-light.png and /dev/null differ diff --git a/images/console-screenshot.png b/images/console-screenshot.png deleted file mode 100644 index 47e3dd7b..00000000 Binary files a/images/console-screenshot.png and /dev/null differ diff --git a/images/logical-layout.png b/images/logical-layout.png deleted file mode 100644 index aeda07c2..00000000 Binary files a/images/logical-layout.png and /dev/null differ diff --git a/images/overview-dark.png b/images/overview-dark.png new file mode 100644 index 00000000..a24e828e Binary files /dev/null and b/images/overview-dark.png differ diff --git a/images/overview-light.png b/images/overview-light.png new file mode 100644 index 00000000..9e84efa5 Binary files /dev/null and b/images/overview-light.png differ diff --git a/images/threads/agent-card.png b/images/threads/agent-card.png new file mode 100644 index 00000000..a7d295b1 Binary files /dev/null and b/images/threads/agent-card.png differ diff --git a/images/threads/agent-ecosystem.png b/images/threads/agent-ecosystem.png new file mode 100644 index 00000000..590f30c0 Binary files /dev/null and b/images/threads/agent-ecosystem.png differ diff --git a/images/threads/customer-support-agent-card.png b/images/threads/customer-support-agent-card.png new file mode 100644 index 00000000..2fed700f Binary files /dev/null and b/images/threads/customer-support-agent-card.png differ diff --git a/images/threads/deploy-chat.png b/images/threads/deploy-chat.png new file mode 100644 index 00000000..bf9f8ba0 Binary files /dev/null and b/images/threads/deploy-chat.png differ diff --git a/images/threads/eject-to-code-diagram.png b/images/threads/eject-to-code-diagram.png new file mode 100644 index 00000000..8ff9dba7 Binary files /dev/null and b/images/threads/eject-to-code-diagram.png differ diff --git a/images/threads/intro-workflow.png b/images/threads/intro-workflow.png new file mode 100644 index 00000000..8674f49c Binary files /dev/null and b/images/threads/intro-workflow.png differ diff --git a/images/threads/marketing-agent-card.png b/images/threads/marketing-agent-card.png new file mode 100644 index 00000000..5d2d5484 Binary files /dev/null and b/images/threads/marketing-agent-card.png differ diff --git a/images/threads/minimal-chat.png b/images/threads/minimal-chat.png new file mode 100644 index 00000000..0828b9d6 Binary files /dev/null and b/images/threads/minimal-chat.png differ diff --git a/images/threads/sales-agent-card.png b/images/threads/sales-agent-card.png new file mode 100644 index 00000000..64c9ed9a Binary files /dev/null and b/images/threads/sales-agent-card.png differ diff --git a/images/threads/training-chat-2.png b/images/threads/training-chat-2.png new file mode 100644 index 00000000..bd9f7ff2 Binary files /dev/null and b/images/threads/training-chat-2.png differ diff --git a/images/threads/training-chat.png b/images/threads/training-chat.png new file mode 100644 index 00000000..1b5c1058 Binary files /dev/null and b/images/threads/training-chat.png differ diff --git a/images/threads/workflow-diagram.png b/images/threads/workflow-diagram.png new file mode 100644 index 00000000..33dc5cb9 Binary files /dev/null and b/images/threads/workflow-diagram.png differ diff --git a/images/tutorials/first-hypermode-agent/login.png b/images/tutorials/first-hypermode-agent/login.png new file mode 100644 index 00000000..6f72c48f Binary files /dev/null and b/images/tutorials/first-hypermode-agent/login.png differ diff --git a/images/tutorials/first-hypermode-agent/prepare-for-meetings.png b/images/tutorials/first-hypermode-agent/prepare-for-meetings.png new file mode 100644 index 00000000..e1cedff8 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/prepare-for-meetings.png differ diff --git a/images/tutorials/first-hypermode-agent/pro-tier-upgrade.png b/images/tutorials/first-hypermode-agent/pro-tier-upgrade.png new file mode 100644 index 00000000..76fe72e4 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/pro-tier-upgrade.png differ diff --git a/images/tutorials/first-hypermode-agent/save-to-calendar.png b/images/tutorials/first-hypermode-agent/save-to-calendar.png new file mode 100644 index 00000000..54ee9f90 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/save-to-calendar.png differ diff --git a/images/tutorials/first-hypermode-agent/save-to-notion.png b/images/tutorials/first-hypermode-agent/save-to-notion.png new file mode 100644 index 00000000..94ee3777 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/save-to-notion.png differ diff --git a/images/tutorials/first-hypermode-agent/sidekick-connections.png b/images/tutorials/first-hypermode-agent/sidekick-connections.png new file mode 100644 index 00000000..057cee32 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/sidekick-connections.png differ diff --git a/images/tutorials/first-hypermode-agent/sidekick.png b/images/tutorials/first-hypermode-agent/sidekick.png new file mode 100644 index 00000000..00e4965d Binary files /dev/null and b/images/tutorials/first-hypermode-agent/sidekick.png differ diff --git a/images/tutorials/first-hypermode-agent/suggest-task.png b/images/tutorials/first-hypermode-agent/suggest-task.png new file mode 100644 index 00000000..9b82c756 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/suggest-task.png differ diff --git a/images/tutorials/first-hypermode-agent/talking-points-1.png b/images/tutorials/first-hypermode-agent/talking-points-1.png new file mode 100644 index 00000000..bbf5cf23 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/talking-points-1.png differ diff --git a/images/tutorials/first-hypermode-agent/talking-points.png b/images/tutorials/first-hypermode-agent/talking-points.png new file mode 100644 index 00000000..d02ce5a8 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/talking-points.png differ diff --git a/images/tutorials/first-hypermode-agent/upgrade-to-pro-button.png b/images/tutorials/first-hypermode-agent/upgrade-to-pro-button.png new file mode 100644 index 00000000..b22a5444 Binary files /dev/null and b/images/tutorials/first-hypermode-agent/upgrade-to-pro-button.png differ diff --git a/images/tutorials/first-hypermode-agent/who-meetings.png b/images/tutorials/first-hypermode-agent/who-meetings.png new file mode 100644 index 00000000..d5cb1efa Binary files /dev/null and b/images/tutorials/first-hypermode-agent/who-meetings.png differ diff --git a/introduction.mdx b/introduction.mdx index 00a4829f..f0033053 100644 --- a/introduction.mdx +++ b/introduction.mdx @@ -1,34 +1,34 @@ --- title: Hypermode description: - An AI development platform that provides hosting and management capabilities - for agents and knowledge graphs + An AI agent development platform that provides natural language + experimentation for anyone. mode: "wide" sidebarTitle: Introduction "og:title": "Hypermode Docs - The AI Development Platform" --- -{/* vale Google.Contractions = NO */} - -## What is Hypermode? - -{/* vale Google.Contractions = YES */} - -Hypermode is a managed service that provides the workbench and infrastructure to -create powerful, engaging, and secure agentic flows, AI features, and backend -services. - -With a suite of tools and services, start with one Hypermode component or all of -them together as your complete backend. +Hypermode's overview, comprising natural language agents and code-first apps, graphs, and models. +Hypermode's overview, comprising natural language agents and code-first apps, graphs, and models. + +Hypermode is a complete workbench for rapidly building agents with natural +language. When you're ready to embed an agent into your app, eject to code and +manage it as a backend service. - - Build and deploy agentic flows, agents, and AI-enabled services | Join our - waitlist → + + Craft powerful agents in natural language with access to your tools and data + + + Build and deploy agents, flows, and AI-enabled services with more control Organize your knowledge in a natural structure of nodes and relationships @@ -36,10 +36,6 @@ them together as your complete backend. Experiment rapidly with the most popular open source and commercial models - - Understand and control the end-to-end flow of your agents, data, and - inferences - ## Built on open source diff --git a/styles/config/vocabularies/general/accept.txt b/styles/config/vocabularies/general/accept.txt index 0c53ac6f..e4263fcc 100644 --- a/styles/config/vocabularies/general/accept.txt +++ b/styles/config/vocabularies/general/accept.txt @@ -1,10 +1,12 @@ [Aa]gentic [Aa]lterSchema +Attio [Bb]oolean [Cc]ollections [Cc]omputeDistance [Cc]omputeSimilarity [Cc]onsole +CRM [Dd]eserialize [Dd]istilbert [Dd]ropAll @@ -24,12 +26,15 @@ [Hh]ypercategories [Hh]ypermode [Ii]nferencing +Jira [Ll]og +maxWidth (?i)mcp [Mm]odus [Nn]amespace [Nn]amespaces [Nn]nClassify +OAuth [Oo]nboarding [Pp]arams [Qq]ueryScalar @@ -74,6 +79,9 @@ RDF REST|[Rr]est Scattergories SDK|sdk +[Ss]idekick +Spotify +Strava TLS tokenizer URL|url @@ -83,6 +91,8 @@ UUID Warnf WASM waitlist +Xero +Zendesk # Dgraph terms Alpha @@ -134,4 +144,11 @@ vCPU|vCPUs WebSocket USA -[Gg]raphs \ No newline at end of file +[Gg]raphs + +Vercel +Exa +Pipedream +Mailchimp +Shopify +Sandboxing \ No newline at end of file