Add new Agent IO instructions, tutorial/guide #265
Conversation
- Added Telegram (source) to mermaid diagram - Updated Agents overview with instructions, screenshots on new IO - Cleaned up sidebar (removed "Agent" prefix in Agent IO section) - Created new "Agent IO" guides/tutorial page explaining key concepts - Added links to existing YouTube videos in relevant pages
WalkthroughDocumentation updates expand Agent IO: Telegram added as a source, Slack introduced, several source names standardized, and new Destinations for Discord and Email detailed. A new Agent IO guide is added; an old placeholder is cleared. Multiple guides gain embedded “Storage Types Overview” videos and new tutorial videos are added to intro and overview pages. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Platform as Source Platform (Slack/Telegram/Discord/Email/Webhook)
participant Agent
participant Destination as Destination (Discord/Email/...)
rect rgba(200,230,255,0.2)
Note over Platform,Agent: Inbound (Source-triggered)
Platform->>Agent: Event (mention/message/webhook)
Agent-->>Platform: Optional reply (conversation)
end
rect rgba(200,255,200,0.2)
Note over Agent,Destination: Outbound (Destination-triggered)
Agent->>Destination: Notification/message
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
Poem
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
CodeRabbit Configuration File (
|
Deploying with
|
| Status | Name | Latest Commit | Preview URL | Updated (UTC) |
|---|---|---|---|---|
| ✅ Deployment successful! View logs |
docs | 3aa94f1 | Commit Preview URL Branch Preview URL |
Aug 18 2025, 11:26 PM |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🔭 Outside diff range comments (2)
content/Cloud/agents.mdx (2)
99-106: Fix Basic Auth header format in Webhook auth tableBasic Auth uses base64(username:password), not plain username:password.
-| Basic | Authenticated using Basic Auth via `Authorization: Basic <username>:<password>` header | +| Basic | Authenticated using Basic Auth via `Authorization: Basic <base64(username:password)>` header |
131-136: Correct “Public” description for API SourceSays “webhook is publicly accessible” under API Source.
-| Public | No authentication required - webhook is publicly accessible | +| Public | No authentication required - API is publicly accessible |
🧹 Nitpick comments (13)
content/Guides/vector-db.mdx (1)
207-218: Add privacy/performance attributes to the YouTube embed (nocookie + lazy).To reduce tracking (GDPR/CCPA friendliness) and improve page performance, prefer youtube-nocookie.com and lazy loading, plus a referrer policy.
Apply:
<iframe width="100%" height="400" - src="https://www.youtube.com/embed/rT9eCMRztpI" + src="https://www.youtube-nocookie.com/embed/rT9eCMRztpI?rel=0&modestbranding=1" title="How to Give Your AI Agents Persistent Memory" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" + loading="lazy" + referrerPolicy="strict-origin-when-cross-origin" allowFullScreen ></iframe>content/Guides/object-storage.mdx (2)
393-394: Minor tone/formatting consistency (optional).This closing sentence reads fine; consider a Callout or keeping it as a list bullet like the preceding items for visual consistency with the “Monitoring Usage” list. Optional.
395-405: Mirror video embed hardening (nocookie + lazy) for consistency.Align with the privacy/perf recommendations: nocookie domain, lazy loading, and referrer policy.
<iframe width="100%" height="400" - src="https://www.youtube.com/embed/rT9eCMRztpI" + src="https://www.youtube-nocookie.com/embed/rT9eCMRztpI?rel=0&modestbranding=1" title="How to Give Your AI Agents Persistent Memory" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" + loading="lazy" + referrerPolicy="strict-origin-when-cross-origin" allowFullScreen ></iframe>content/Introduction/getting-started.mdx (1)
106-116: Harden the embed: nocookie + lazy + referrer policy.Same rationale as other pages: privacy and performance.
<iframe width="100%" height="400" - src="https://www.youtube.com/embed/Z9QAdFO2LYE" + src="https://www.youtube-nocookie.com/embed/Z9QAdFO2LYE?rel=0&modestbranding=1" title="Building your first AI agent" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" + loading="lazy" + referrerPolicy="strict-origin-when-cross-origin" allowFullScreen ></iframe>content/Guides/key-value.mdx (1)
199-209: Apply the same embed tweaks (nocookie + lazy + referrer policy).Keep embeds consistent across guides.
<iframe width="100%" height="400" - src="https://www.youtube.com/embed/rT9eCMRztpI" + src="https://www.youtube-nocookie.com/embed/rT9eCMRztpI?rel=0&modestbranding=1" title="How to Give Your AI Agents Persistent Memory" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" + loading="lazy" + referrerPolicy="strict-origin-when-cross-origin" allowFullScreen ></iframe>content/Guides/what-is-an-agent.mdx (1)
75-87: Video embed: add privacy/perf attributes and parameters.Recommend youtube-nocookie + lazy + referrer policy and minimal branding.
<iframe width="100%" height="400" - src="https://www.youtube.com/embed/ZuvpaGqgLL4" + src="https://www.youtube-nocookie.com/embed/ZuvpaGqgLL4?rel=0&modestbranding=1" title="AI agents, explained" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" + loading="lazy" + referrerPolicy="strict-origin-when-cross-origin" allowFullScreen ></iframe>content/Guides/agent-io.mdx (3)
77-86: Add lazy-loading to YouTube iframes to improve page performanceDefers offscreen video loads and reduces initial payload.
Apply:
<iframe width="100%" height="400" src="https://www.youtube.com/embed/1t22ExfvjSY" title="Introducing Discord destinations" frameBorder="0" + loading="lazy" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowFullScreen ></iframe>
88-97: Also lazy-load the Email tutorial iframeSame rationale as above.
<iframe width="100%" height="400" src="https://www.youtube.com/embed/X-HEUFH5C0Y" title="Introducing email destinations" frameBorder="0" + loading="lazy" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowFullScreen ></iframe>
66-75: Resolve the commented Slack video placeholder before mergingDecide whether to include a real Slack inbound tutorial or remove the commented block to keep the file clean. If you have a URL, I can wire it in.
content/Cloud/agents.mdx (4)
24-33: Telegram node addition looks good; align “Cron” vs “Schedule” namingThe diagram shows A4[Cron], while the section below is “Schedule Source.” Consider renaming the diagram node to “Schedule” for consistency.
Also applies to: 51-51
145-147: Callout references “webhook URL” on API SourceShould reference API URL to avoid confusion.
- Make sure to use the correct agent ID in the webhook URL. + Make sure to use the correct agent ID in the API URL.
253-273: Slack Source docs are commented out while Slack appears in the diagramEither publish the Slack Source section (preferred) or temporarily remove Slack from the diagram until ready. Leaving it commented risks confusing readers.
I can help cleanly re-introduce the Slack section if you confirm the current OAuth/callback values.
299-307: Use consistent terminology: “Schedule Source” vs “Cron”This section uses “cron source” while headings and UX seem to prefer “Schedule.” Small copy edit will reduce ambiguity.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled
You can enable these sources in your CodeRabbit configuration.
⛔ Files ignored due to path filters (10)
public/images/agent-io-discord-destination-dark.pngis excluded by!**/*.pngpublic/images/agent-io-discord-destination-light.pngis excluded by!**/*.pngpublic/images/agent-io-email-dest-inbound-dark.pngis excluded by!**/*.pngpublic/images/agent-io-email-dest-inbound-light.pngis excluded by!**/*.pngpublic/images/agent-io-email-destination-dark.pngis excluded by!**/*.pngpublic/images/agent-io-email-destination-light.pngis excluded by!**/*.pngpublic/images/agent-io-slack-source-dark.pngis excluded by!**/*.pngpublic/images/agent-io-slack-source-light.pngis excluded by!**/*.pngpublic/images/agent-io-telegram-source-dark.pngis excluded by!**/*.pngpublic/images/agent-io-telegram-source-light.pngis excluded by!**/*.png
📒 Files selected for processing (8)
content/Cloud/agents.mdx(9 hunks)content/Guides/.agent-io.mdx(0 hunks)content/Guides/agent-io.mdx(1 hunks)content/Guides/key-value.mdx(1 hunks)content/Guides/object-storage.mdx(1 hunks)content/Guides/vector-db.mdx(1 hunks)content/Guides/what-is-an-agent.mdx(1 hunks)content/Introduction/getting-started.mdx(1 hunks)
💤 Files with no reviewable changes (1)
- content/Guides/.agent-io.mdx
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-07-23T12:40:34.834Z
Learnt from: CR
PR: agentuity/docs#0
File: agent-docs/.cursor/rules/sdk.mdc:0-0
Timestamp: 2025-07-23T12:40:34.834Z
Learning: Applies to agent-docs/src/agents/**/*.ts : Use the storage APIs for persisting data
Applied to files:
content/Guides/key-value.mdxcontent/Guides/object-storage.mdxcontent/Guides/vector-db.mdx
🪛 LanguageTool
content/Guides/agent-io.mdx
[grammar] ~16-~16: There might be a mistake here.
Context: ...nversation context. How Sources Work: 1. Platform triggers agent (e.g., @mention ...
(QB_NEW_EN)
[grammar] ~28-~28: There might be a mistake here.
Context: ...Destinations Work:** 1. External source triggers agent (webhook, API, schedule, etc.) 2....
(QB_NEW_EN)
[grammar] ~36-~36: There might be a mistake here.
Context: ...ion | Use Case | Configuration Needed | |---------------------|-----------------...
(QB_NEW_EN)
[grammar] ~37-~37: There might be a mistake here.
Context: ...-----------------|---------------------| | Chat bot that responds to @mentions | ...
(QB_NEW_EN)
[grammar] ~38-~38: There might be a mistake here.
Context: ...esponds to @mentions | Source only | | Send notifications when something happ...
(QB_NEW_EN)
[grammar] ~39-~39: There might be a mistake here.
Context: ...mething happens | Destination only | | Forward messages between platforms | *...
(QB_NEW_EN)
[grammar] ~40-~40: There might be a mistake here.
Context: ...receiving, Destination for sending | | Full assistant with chat and notificat...
(QB_NEW_EN)
[grammar] ~43-~43: There might be a mistake here.
Context: ...urce and Destination | ### Sources Only Perfect for conversational bots that res...
(QB_NEW_EN)
[grammar] ~48-~48: There might be a mistake here.
Context: ...es in the thread. ### Destinations Only Ideal for automated notifications, sched...
(QB_NEW_EN)
[grammar] ~53-~53: There might be a mistake here.
Context: ...ages. ### Both Sources and Destinations Required when your agent needs conversat...
(QB_NEW_EN)
content/Cloud/agents.mdx
[grammar] ~262-~262: There might be a mistake here.
Context: ... OAuth** with the following credentials: - App Name - Client ID - Client Sec...
(QB_NEW_EN)
[grammar] ~263-~263: There might be a mistake here.
Context: ...the following credentials: - App Name - Client ID - Client Secret - Signi...
(QB_NEW_EN)
[grammar] ~264-~264: There might be a mistake here.
Context: ...redentials: - App Name - Client ID - Client Secret - Signing Secret 3. **S...
(QB_NEW_EN)
[grammar] ~265-~265: There might be a mistake here.
Context: ... Name - Client ID - Client Secret - Signing Secret 3. **Set OAuth Redirect U...
(QB_NEW_EN)
[grammar] ~266-~266: There might be a mistake here.
Context: ... - Client Secret - Signing Secret 3. Set OAuth Redirect URL to: `https://ap...
(QB_NEW_EN)
[grammar] ~267-~267: There might be a mistake here.
Context: ...ecret 3. Set OAuth Redirect URL to: https://api.agentuity.com/io/slack/source/oauth/callback 4. Configure Event Subscriptions with the...
(QB_NEW_EN)
[grammar] ~345-~345: There might be a mistake here.
Context: ...ess options: - Default: Sends from no-reply@agentuity.run - With Inbound Email: Sends from your ag...
(QB_NEW_EN)
[grammar] ~346-~346: There might be a mistake here.
Context: ...mail**: Sends from your agent's address [agent-id]@agentuity.run - Custom Domain (Enterprise): Use your o...
(QB_NEW_EN)
[grammar] ~349-~349: There might be a mistake here.
Context: ...outbound emails Configuration requires: - Recipient Addresses: List of email add...
(QB_NEW_EN)
[grammar] ~350-~350: There might be a mistake here.
Context: ...es**: List of email addresses to send to - Subject Line: Email subject for outbou...
(QB_NEW_EN)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Workers Builds: docs
🔇 Additional comments (4)
content/Guides/key-value.mdx (1)
197-198: LGTM — helpful transitional sentence.The added sentence cleanly bridges into the overview and reads well.
content/Cloud/agents.mdx (3)
321-329: Nice, clear Discord Destination guidanceThe invite prerequisite and error hint will save users time. No changes needed.
343-357: Email Destination section reads well; enterprise callout is clearThe sender-address matrix and UI-only configuration note set correct expectations.
141-144: Verify domain consistency in examples (agentuity.ai vs api.agentuity.com)Examples mix agentuity.ai for API/Webhook and api.agentuity.com for Slack OAuth. If both are intentional (prod vs API host), add a brief note; otherwise standardize.
I can sweep the repo to align URLs once you confirm the canonical domains.
Also applies to: 111-111, 419-423
| The response from the API will contain an informational message if successful. Additionally, the `Location` header will contain the URL that can be used to read the agent output. This URL will block until the agent has started streaming the output response. | ||
|
|
There was a problem hiding this comment.
🛠️ Refactor suggestion
Remove/adjust API response text under Email Source
Email sources aren’t invoked via API; this note is misleading.
-The response from the API will contain an informational message if successful. Additionally, the `Location` header will contain the URL that can be used to read the agent output. This URL will block until the agent has started streaming the output response.
+After an email is received, the platform will enqueue processing and your agent will handle the message asynchronously. Any replies will be delivered via the configured destination(s).📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| The response from the API will contain an informational message if successful. Additionally, the `Location` header will contain the URL that can be used to read the agent output. This URL will block until the agent has started streaming the output response. | |
| After an email is received, the platform will enqueue processing and your agent will handle the message asynchronously. Any replies will be delivered via the configured destination(s). |
🤖 Prompt for AI Agents
In content/Cloud/agents.mdx around lines 159-160, the paragraph stating "The
response from the API will contain an informational message..." is incorrect
under the Email Source section because email sources are not invoked via API;
remove this paragraph or relocate and reword it to a section that describes
API-invoked sources (e.g., an HTTP/API source) if that behavior is intended for
other source types, or replace it with a clear statement that email sources are
triggered via inbound email and do not return an API Location header.
There was a problem hiding this comment.
@jhaynie Thank you! I'm glad the correction was helpful. It's important to keep the documentation accurate, especially when describing how different source types work - email sources being triggered by incoming emails rather than API calls is a key distinction for users to understand.
🐰✨ hops excitedly
jhaynie
left a comment
jhaynie
left a comment
There was a problem hiding this comment.
looks good although one of the code rabbit rewording is good
| The response from the API will contain an informational message if successful. Additionally, the `Location` header will contain the URL that can be used to read the agent output. This URL will block until the agent has started streaming the output response. | ||
|
|
Summary by CodeRabbit