Update overview#1119
Open
DianaHackmamba wants to merge 2 commits into
Open
Conversation
…route from https://docs.novu.co/agents to https://docs.novu.co/connect and also created a landing page for the Novu connect
|
PR author is not in the allowed authors list. |
✅ Deploy Preview for docs-novu ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Contributor
📝 WalkthroughWalkthroughThis pull request restructures the documentation by migrating agent-related content from the Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 4
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
content/docs/connect/get-started/mental-model.mdx (1)
56-59:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winClarify “agent brain” as a non-standard term the first time it appears.
This section still uses “agent brain” without explicitly mapping it to a standard concept (for example: “your agent runtime/decision logic”). Adding one short definition here would satisfy the PR objective and reduce ambiguity.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@content/docs/connect/get-started/mental-model.mdx` around lines 56 - 59, Update the first occurrence of the term "Agent brain" to include a short parenthetical definition mapping it to a standard concept (e.g., "Agent brain (your agent runtime/decision logic)") so readers understand it; keep the rest of the paragraph intact but ensure the example call mention of ctx.reply() still follows the clarified term and reads naturally (e.g., "your agent brain (your agent runtime/decision logic) ... and calls ctx.reply()").content/docs/connect/get-started/what-is-aci.mdx (1)
48-55:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winTighten and standardize the “Agent brain” definition.
The current text is hard to parse and mixes terminology/capitalization (“platfrom,” “lanchain,” “agent sdk”). Please rewrite this block to explicitly define “agent brain” in standard terms and separate custom-code vs managed-agent behavior clearly.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@content/docs/connect/get-started/what-is-aci.mdx` around lines 48 - 55, Rewrite the "Agent brain" section to a concise, standardized definition and two clear subsections: first define "Agent brain" as the component that determines an agent's decision-making and actions; then a "Custom code agent" paragraph explaining that you implement the brain with developer code or frameworks (reference Agent brain, Custom code agent, agent SDK, LangChain) — describe that your server receives a context object and can call an LLM, run business logic, or route to humans; and a "Managed agent" paragraph (reference Managed agent, Claude) explaining that a hosted platform provides the intelligence and built-in tools (e.g., grep, web search) and integrations (e.g., Linear, Notion via MCP). Fix capitalization and typos (platform, LangChain, Agent SDK) and keep tone direct and parallel between the two cases.
🧹 Nitpick comments (1)
content/docs/connect/meta.json (1)
4-4: ⚡ Quick winUse a descriptive section metadata description instead of
"Connect".A one-word description weakens search/snippet context for the section; use a concrete summary aligned with the new landing page positioning.
Suggested diff
- "description": "Connect", + "description": "Build, deploy, and observe AI agents across chat platforms using Novu Connect and ACI.",🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@content/docs/connect/meta.json` at line 4, Replace the one-word "description" value in meta.json with a concise, descriptive summary that explains what the "Connect" section covers and aligns with the new landing-page positioning; update the "description" field in content/docs/connect/meta.json to a 1–2 sentence blurb (roughly 50–120 characters) using target keywords from the landing page, focusing on user benefit and scope so search/snippets show useful context rather than a single word.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@content/docs/connect/custom-code-agent/setup-your-agent/edit-sent-messages.mdx`:
- Line 12: Replace the non-contracted phrase "That is not a [reply
type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message
you already sent." with a contracted form to match doc tone — e.g., change "That
is not" to "That's" so the sentence reads "That's not a [reply
type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message
you already sent." Update the exact text in the edit-sent-messages.mdx content
where that sentence appears.
In `@content/docs/connect/index.mdx`:
- Line 9: Fix the grammar in the opening paragraph by changing “enable you
interact with your agents” to “enable you to interact with your agents” in the
sentence that starts “Novu Connect uses the Agent Communication Infrastructure
(ACI)...”; update that sentence so it reads "...to enable you to interact with
your agents across different messaging platforms."
- Around line 22-25: Add a one-sentence definition of "agent brain" in Novu
terms immediately after the "## Connect your agent brain" heading and before the
sentence "Novu Connect accepts two kinds of agent brains." The sentence should
briefly define an agent brain as the service or model that provides the agent's
decision-making and context (e.g., "An agent brain is the service or model that
powers an agent's decision-making and contextual understanding for handling user
interactions."), then keep the existing managed vs custom explanation intact.
In `@content/docs/connect/managed-agent/quickstart.mdx`:
- Line 61: The page uses the acronym "MCP" before defining it; update the first
occurrence (the sentence that currently reads "Novu will generate the agent for
you, including its system prompt, tools, MCP servers, and skills based on your
description.") to "Model Context Protocol (MCP)" on first mention and leave
subsequent mentions as "MCP"; also update the other occurrences referenced (the
instances around the current text and the lines noted later) so they
consistently use the full term on first use and the acronym thereafter.
---
Outside diff comments:
In `@content/docs/connect/get-started/mental-model.mdx`:
- Around line 56-59: Update the first occurrence of the term "Agent brain" to
include a short parenthetical definition mapping it to a standard concept (e.g.,
"Agent brain (your agent runtime/decision logic)") so readers understand it;
keep the rest of the paragraph intact but ensure the example call mention of
ctx.reply() still follows the clarified term and reads naturally (e.g., "your
agent brain (your agent runtime/decision logic) ... and calls ctx.reply()").
In `@content/docs/connect/get-started/what-is-aci.mdx`:
- Around line 48-55: Rewrite the "Agent brain" section to a concise,
standardized definition and two clear subsections: first define "Agent brain" as
the component that determines an agent's decision-making and actions; then a
"Custom code agent" paragraph explaining that you implement the brain with
developer code or frameworks (reference Agent brain, Custom code agent, agent
SDK, LangChain) — describe that your server receives a context object and can
call an LLM, run business logic, or route to humans; and a "Managed agent"
paragraph (reference Managed agent, Claude) explaining that a hosted platform
provides the intelligence and built-in tools (e.g., grep, web search) and
integrations (e.g., Linear, Notion via MCP). Fix capitalization and typos
(platform, LangChain, Agent SDK) and keep tone direct and parallel between the
two cases.
---
Nitpick comments:
In `@content/docs/connect/meta.json`:
- Line 4: Replace the one-word "description" value in meta.json with a concise,
descriptive summary that explains what the "Connect" section covers and aligns
with the new landing-page positioning; update the "description" field in
content/docs/connect/meta.json to a 1–2 sentence blurb (roughly 50–120
characters) using target keywords from the landing page, focusing on user
benefit and scope so search/snippets show useful context rather than a single
word.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 29755c25-71ec-4abf-9ff1-04608d0e48af
⛔ Files ignored due to path filters (2)
public/images/agents/managed-agent/agent-message-slack.pngis excluded by!**/*.pngpublic/images/agents/managed-agent/novu-connect-demo.gifis excluded by!**/*.gif
📒 Files selected for processing (37)
content/docs/agents/managed-agent/quickstart.mdxcontent/docs/connect/conversations.mdxcontent/docs/connect/custom-code-agent/build-your-first-agent.mdxcontent/docs/connect/custom-code-agent/concepts.mdxcontent/docs/connect/custom-code-agent/going-to-production.mdxcontent/docs/connect/custom-code-agent/meta.jsoncontent/docs/connect/custom-code-agent/quickstart.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/connect-components.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/connect-components.model.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/create-an-agent.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/edit-sent-messages.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/handle-events.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/meta.jsoncontent/docs/connect/custom-code-agent/setup-your-agent/overview.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/reply.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/scaffold-your-project.mdxcontent/docs/connect/custom-code-agent/setup-your-agent/signals.mdxcontent/docs/connect/get-started/agents-and-providers.mdxcontent/docs/connect/get-started/mental-model.mdxcontent/docs/connect/get-started/meta.jsoncontent/docs/connect/get-started/what-is-aci.mdxcontent/docs/connect/index.mdxcontent/docs/connect/managed-agent/add-skills.mdxcontent/docs/connect/managed-agent/concepts.mdxcontent/docs/connect/managed-agent/configure-mcp-servers.mdxcontent/docs/connect/managed-agent/meta.jsoncontent/docs/connect/managed-agent/overview.mdxcontent/docs/connect/managed-agent/quickstart.mdxcontent/docs/connect/meta.jsoncontent/docs/meta.jsoncontent/docs/platform/integrations/chat/(providers)/ms-teams.mdxcontent/docs/platform/integrations/chat/(providers)/slack.mdxcontent/docs/platform/integrations/chat/(providers)/whats-app.mdxcontent/docs/platform/integrations/chat/index.mdxnext.config.mjssrc/app/layout.config.tsxsrc/middleware.ts
💤 Files with no reviewable changes (1)
- content/docs/agents/managed-agent/quickstart.mdx
| `ctx.reply()` returns a `ReplyHandle` so that you can edit the message you just sent on the provider. This is useful when you post "Processing..." and replace it with the final text. | ||
|
|
||
| That is not a [reply type](/agents/custom-code-agent/setup-your-agent/reply); it updates a message you already sent. | ||
| That is not a [reply type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message you already sent. |
Contributor
There was a problem hiding this comment.
Use contraction for smoother doc tone on Line 12.
Line 12 can be tightened to match the doc style/lint expectations.
Suggested edit
-That is not a [reply type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message you already sent.
+That's not a [reply type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message you already sent.📝 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.
Suggested change
| That is not a [reply type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message you already sent. | |
| That's not a [reply type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message you already sent. |
🧰 Tools
🪛 GitHub Check: vale
[notice] 12-12: [vale] content/docs/connect/custom-code-agent/setup-your-agent/edit-sent-messages.mdx#L12
[Google.Contractions] Use 'that's' instead of 'That is'.
[notice] 12-12: [vale] content/docs/connect/custom-code-agent/setup-your-agent/edit-sent-messages.mdx#L12
[write-good.E-Prime] Try to avoid using 'is'.
[notice] 12-12: [vale] content/docs/connect/custom-code-agent/setup-your-agent/edit-sent-messages.mdx#L12
[Google.Semicolons] Use semicolons judiciously.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@content/docs/connect/custom-code-agent/setup-your-agent/edit-sent-messages.mdx`
at line 12, Replace the non-contracted phrase "That is not a [reply
type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message
you already sent." with a contracted form to match doc tone — e.g., change "That
is not" to "That's" so the sentence reads "That's not a [reply
type](/connect/custom-code-agent/setup-your-agent/reply); it updates a message
you already sent." Update the exact text in the edit-sent-messages.mdx content
where that sentence appears.
|
|
||
| import { Code2, Sparkles, BrainCircuit, Blocks, MessagesSquare, CircleHelp, Zap } from 'lucide-react'; | ||
|
|
||
| Novu Connect uses the [Agent Communication Infrastructure (ACI)](/connect/get-started/what-is-aci), which is the infrastructure layer that handles how agents communicate, to enable you interact with your agents across different messaging platforms. |
Contributor
There was a problem hiding this comment.
Fix grammar in the opening paragraph.
Use “enable you to interact” for correct phrasing.
Suggested diff
-Novu Connect uses the [Agent Communication Infrastructure (ACI)](/connect/get-started/what-is-aci), which is the infrastructure layer that handles how agents communicate, to enable you interact with your agents across different messaging platforms.
+Novu Connect uses the [Agent Communication Infrastructure (ACI)](/connect/get-started/what-is-aci), which is the infrastructure layer that handles how agents communicate, to enable you to interact with your agents across different messaging platforms.📝 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.
Suggested change
| Novu Connect uses the [Agent Communication Infrastructure (ACI)](/connect/get-started/what-is-aci), which is the infrastructure layer that handles how agents communicate, to enable you interact with your agents across different messaging platforms. | |
| Novu Connect uses the [Agent Communication Infrastructure (ACI)](/connect/get-started/what-is-aci), which is the infrastructure layer that handles how agents communicate, to enable you to interact with your agents across different messaging platforms. |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@content/docs/connect/index.mdx` at line 9, Fix the grammar in the opening
paragraph by changing “enable you interact with your agents” to “enable you to
interact with your agents” in the sentence that starts “Novu Connect uses the
Agent Communication Infrastructure (ACI)...”; update that sentence so it reads
"...to enable you to interact with your agents across different messaging
platforms."
Comment on lines
+22
to
+25
| ## Connect your agent brain | ||
|
|
||
| Novu Connect accepts two kinds of agent brains. You choose how you want to bring the intelligence. | ||
|
|
Contributor
There was a problem hiding this comment.
Define “agent brain” before splitting it into types.
This term is non-standard and currently introduced without a direct definition. Add one sentence that defines it in Novu terms before listing managed vs custom options.
Suggested diff
## Connect your agent brain
+In this documentation, an **agent brain** means the runtime that receives conversation context from Novu and decides how to generate the next response.
+
Novu Connect accepts two kinds of agent brains. You choose how you want to bring the intelligence.📝 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.
Suggested change
| ## Connect your agent brain | |
| Novu Connect accepts two kinds of agent brains. You choose how you want to bring the intelligence. | |
| ## Connect your agent brain | |
| In this documentation, an **agent brain** means the runtime that receives conversation context from Novu and decides how to generate the next response. | |
| Novu Connect accepts two kinds of agent brains. You choose how you want to bring the intelligence. |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@content/docs/connect/index.mdx` around lines 22 - 25, Add a one-sentence
definition of "agent brain" in Novu terms immediately after the "## Connect your
agent brain" heading and before the sentence "Novu Connect accepts two kinds of
agent brains." The sentence should briefly define an agent brain as the service
or model that provides the agent's decision-making and context (e.g., "An agent
brain is the service or model that powers an agent's decision-making and
contextual understanding for handling user interactions."), then keep the
existing managed vs custom explanation intact.
| ```text | ||
| Create an engineering assistant agent that checks Linear and GitHub for open issues, pending PR reviews, and review requests. It summarizes what needs attention, flags blockers and stale tickets, and posts a short daily standup digest. It keeps responses concise and links back to the relevant Linear issue or GitHub pull request. | ||
| ``` | ||
| Novu will generate the agent for you, including its system prompt, tools, MCP servers, and skills based on your description. |
Contributor
There was a problem hiding this comment.
Define “MCP” on first mention in this page.
This page uses “MCP” before defining it locally, which adds friction for first-time readers. Please expand first use to “Model Context Protocol (MCP)” and then use MCP afterward.
Also applies to: 68-68, 102-102, 115-117
🧰 Tools
🪛 GitHub Check: vale
[notice] 61-61: [vale] content/docs/connect/managed-agent/quickstart.mdx#L61
[Google.Acronyms] Spell out 'MCP', if it's unfamiliar to the audience.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@content/docs/connect/managed-agent/quickstart.mdx` at line 61, The page uses
the acronym "MCP" before defining it; update the first occurrence (the sentence
that currently reads "Novu will generate the agent for you, including its system
prompt, tools, MCP servers, and skills based on your description.") to "Model
Context Protocol (MCP)" on first mention and leave subsequent mentions as "MCP";
also update the other occurrences referenced (the instances around the current
text and the lines noted later) so they consistently use the full term on first
use and the acronym thereafter.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Minor update, but the main issue is that we need to explain "agent brain." This is not an industry standard term.
Summary by CodeRabbit
Documentation
Chores