feat: Add mock-ai interviewer Agentkit#172
Open
sreecharan1306 wants to merge 17 commits into
Open
Conversation
* feat: Add medical-assistant AgentKit * fix coderabit suggested error * add live demo link * fix suggested error
* feat: Add legal assistant AgentKit * fix: address PR review feedback for legal assistant kit * fix: address latest CodeRabbit review comments * fix: address CodeRabbit review feedback for legal assistant kit * fix: patch deployment dependencies and update legal kit docs * docs: add live preview links for legal assistant kit
* feat: add support triage kit UI and configuration * trigger preview build * style: deploy enterprise glassmorphic UI * Fixed some minor bugs * refactor: address CodeRabbit review and secure API route * fix: remove dead utils import * fix: rename route.js to route.ts to resolve build error * fix: implement defensive initialization and strict error typing * chore: add missing flows directory to satisfy CI validation * chore: add dummy flow.json to satisfy subdirectory validation * chore: add valid flow schema files * fix: resolve light mode text visibility and remove global body bg * fix: wipe legacy globals.css to fix tailwind gradient * Fix: Light Mode UI * fix ui * kill dark mode in root --------- Co-authored-by: Aman Sharma <amanrazdan@amp.dev> Co-authored-by: Vrijraj Singh <vrijraj2396@gmail.com>
Co-authored-by: Dhruv Pamneja <100751844+d-pamneja@users.noreply.github.com>
* feat: Add meeting-notes-to-action-items template * Fix variable scoping, node dependencies, and response mapping
* feat: add AI Career Copilot AgentKit * fix: revert to tailwind v3 for stable UI and config support * docs: improve README formatting and setup instructions * Changes done update the pacakge.json wiht regarding to the vercel error * vercel.json add * fix: CSS error solved * fix: migrate to tailwind v4 and update env variables * chore: trigger CI rerun * chore: rerun CI * fix: pin dependency versions for reproducible builds * fix: update config name and env key to match flow * fix: Solved all six changes in code * feat: add live demo link to README
Contributor
|
Important Review skippedToo many files! This PR contains 271 files, which is 121 over the limit of 150. To get a review, narrow the scope: ⚙️ Run configurationConfiguration used: Repository UI (base), Organization UI (inherited) Review profile: ASSERTIVE Plan: Pro Run ID: ⛔ Files ignored due to path filters (29)
📒 Files selected for processing (271)
You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
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 |
:robot_face: AgentKit Structural ValidationExisting Kits Modified (not allowed in feat: PRs)
Check Results
❌ Errors
|
|
Failure recorded at 2026-06-03T16:02:32Z UTC. If this PR is not fixed within 4 weeks it will be automatically closed. |
Contributor
|
Please update the file structure as well from the https://github.com/Lamatic/AgentKit/blob/main/CONTRIBUTING.md#repository-layout |
Author
OK |
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
8 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.
What This Kit Does
Mockai is an AI-powered mock interviewer that helps users practice for tailored job interviews. It conducts dynamic, interactive interviews using real-time speech-to-text and provides instant, AI-generated feedback on your performance.
Providers & Prerequisites
How to Run Locally
cd kits/agentic/mockainpm installcp .env.example .envand fill in valuesnpm run devLive Preview
https://mockai-mscr.vercel.app/
Lamatic Flow
9f64b62e-6e02-4de5-afa9-677970913e007a20f813-2e7a-4597-804f-427b9b702d88Mockai - AI-Powered Mock Interviewer Agent Kit (PR #101)
Overview
Adds a complete, production-ready Next.js-based AI mock interview platform with three-step interactive workflow (setup → interview → feedback). Integrates Google Gemini via Lamatic.ai orchestration for dynamic question generation and real-time interview evaluation with speech-to-text capabilities.
Files Added: 102 Total
Configuration & Build Setup (16 files)
.env.example- LAMATIC API credentials and flow IDs.gitignore- Node/Next.js standard exclusionspackage.json- Dependencies (Next.js, React, Tailwind CSS, Radix UI, Recharts, Sonner, date-fns, input-otp, embla-carousel)package-lock.json- Locked dependency versionsnext.config.mjs- Next.js config (standalone output, image optimization disabled)tsconfig.json- TypeScript strict mode with Next.js pluginpostcss.config.mjs- PostCSS for Tailwind CSScomponents.json- Shadcn UI schema configurationconfig.json- Agent kit metadata and orchestration configCore Application (3 files)
app/layout.tsx- Root layout with global CSS, Google Fonts (Geist), Vercel Analyticsapp/page.tsx- Main interview component (~579 lines) with Web Speech API integration, audio visualizer, 3-step workflow managementapp/globals.css- Global styles with Tailwind v4, CSS variable theming (light/dark modes), chart colors, sidebar variantsServer Logic & Utilities (5 files)
actions/orchestrate.ts- Server actions:generateQuestions()andevaluateAnswers()with Lamatic flow execution and error handlinglib/lamatic-client.ts- Lamatic SDK instantiation with environment credentialslib/utils.ts-cn()utility for class merging (clsx + tailwind-merge)orchestrate.js- Orchestration config with flows and API settingshooks/use-toast.ts- Toast state management with dispatch/subscribe patternUI Components (59 files)
Hooks (2 files)
hooks/use-mobile.ts- Responsive mobile detection hook (768px breakpoint)hooks/use-toast.ts- Toast state management with in-memory store, unique IDs, auto-dismissal timersFlows (12 files - 3 flows × 4 files)
1. Question Flow (
flows/question-flow/){ jobTitle: string, yearsOfExp: int, jobDesc: string }questionsarray (10 interview questions){ questions: string[] }2. Feedback Flow (
flows/feedback-flow/){ candidateResponses: [{ question: string, answers: string }] }{ positives: string[], negatives: string[], rating: number }3. Generate Content Flow (
flows/agentic-generate-content/) - Optional/reusable{ mode: "text" | "image" | "json", instructions: string }mode == "text": routes to LLMNode_430 (text generation)mode == "image": routes to ImageGenNode_535 (image generation)mode == "json": routes to LLMNode_255 (JSON generation)else: invalid mode error code nodeAssets & Documentation (11 files)
README.md- Setup instructions, environment variables, repository structure, contributing guidelinesPR_DESCRIPTION.md- PR-specific test instructions and feature highlightsplaceholder.jpg,placeholder.svg,placeholder-user.jpg,lamatic-logo.png,icon.svg,icon-light-32x32.png,icon-dark-32x32.png,apple-icon.png,placeholder-logo.svg,placeholder-logo.pngInterview Workflow (Client-Side)
Setup Step
generateQuestions()→ Question FlowInterview Step
evaluateAnswers()on final questionFeedback Step
Technology Stack
Key Features Implemented
✅ Real-time speech-to-text with Web Speech API
✅ Audio visualizer during recording
✅ Three-step interactive interview workflow
✅ AI-generated questions from Lamatic flows
✅ Structured feedback (positives/negatives/rating)
✅ Dark/light theme with CSS variables
✅ Responsive design (mobile-aware sidebar)
✅ Toast notifications (Sonner)
✅ Comprehensive UI component library (59 components)
✅ Environment-driven flow configuration
✅ Production-ready Next.js setup (standalone mode, TypeScript strict)