agentkit-challenge - #359
Conversation
|
Important Review skippedAuto reviews are limited based on label configuration. 🏷️ Required labels (at least one) (1)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository UI (base), Organization UI (inherited) Review profile: ASSERTIVE Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
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 |
|
Hey @manvendra-8822 we already have a interview prep kit. So if you can make something else that would be great. |
Interview Prep Generator
Agentic kit under kits/interview-prep-generator/ that turns a job description and a public Google Drive resume link into a resume-grounded interview prep kit.
What it does
Given a job description, a public Drive link to a resume, and an optional company name, a Supervisor agent orchestrates four branches: Guardrail (deterministic, non-LLM prompt-injection scan of the job description and extracted resume text, run first on every request), Fact Lookup (optional Tavily search for company context), Context Assembly (optional Browser Use Cloud live-browsing research on the company's interview process and culture), and Merge Research Context (combines both research arms into one block before generation), followed by Generate Text which writes the final resume-grounded interview prep kit.
A Drive-link public-accessibility pre-check runs before any LLM call and short-circuits with a specific, actionable error if the resume isn't shared publicly.
See agent.md for the full node walkthrough and failure-mode table, and README.md for inputs/output and usage.
Checklist
Contribution type: Kit, at kits/interview-prep-generator/. Single project, no unrelated changes. No secrets, API keys, or real credentials committed -- model-config credentials are left blank for the deployer to select in Studio, and the Tavily/Browser Use API keys are documented as optional Studio secrets in .env.example, never committed. Folder name is kebab-case and matches the flow ID. All changes are documented in README.md and agent.md. lamatic.config.ts has valid metadata (name, description, tags, steps, author). flows/interview-prep-generator.ts exports meta, inputs, references, nodes, and edges.