--- title: I Turned My Resume Into an AI You Can Interrogate description: A developer built an AI-powered interactive resume called Signal Sifter that lets recruiters interrogate a career story via chat, while also serving as a... canonical: https://daily.dev/posts/i-turned-my-resume-into-an-ai-you-can-interrogate-p8yudcttn twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I Turned My Resume Into an AI You Can Interrogate | daily.dev og:description: A developer built an AI-powered interactive resume called Signal Sifter that lets recruiters interrogate a career story via chat, while also serving as a... og:url: https://daily.dev/posts/i-turned-my-resume-into-an-ai-you-can-interrogate-p8yudcttn og:image: https://api.daily.dev/og/posts/p8yUDcTTN.png og:image:alt: I Turned My Resume Into an AI You Can Interrogate og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # I Turned My Resume Into an AI You Can Interrogate **[gitconnected](https://daily.dev/sources/gc)** · 10 min read · 6 upvotes · 0 comments ## Summary A developer built an AI-powered interactive resume called Signal Sifter that lets recruiters interrogate a career story via chat, while also serving as a hidden interview practice coach. The key architectural decisions: no RAG or vector DB (the full resume JSON fits in the LLM context window), mandatory source citations on every answer using a closed key list to prevent hallucination, and five literature-based self-assessments (Belbin, Thomas-Kilmann, SDT, TIPI, Goleman) instead of generic soft-skill claims. The stack runs at $0/month using GitHub Pages, a Cloudflare Worker, and Groq's free tier. A hidden `?practice=1` mode flips the AI into a behavioral interviewer that stress-tests resume claims against the self-assessments and coaches STAR-method answers. The project is open source and forkable. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Do I need a vector database to build a chatbot that answers questions from a resume or personal document? No, a vector database is unnecessary when the source data is small enough to fit entirely in an LLM's context window, such as a resume plus career narrative totaling a few kilobytes of text. The full JSON can be stringified directly into the system prompt on every request, eliminating embeddings, chunking, and retrieval tuning. RAG is worth its cost only when a corpus is too large for context, changes faster than it can be re-embedded, or must be queried across many documents. _Anyone weighing RAG against a simple context-stuffed prompt can compare real-world LLM architecture writeups on daily.dev._ ### How can I stop an LLM chatbot from hallucinating facts when answering questions about a specific person or dataset? Force every model reply to open with a machine-readable citation line naming the exact source keys used, drawn from a closed list defined in the system prompt, before any answer text. The model can only cite from that predefined list and never invent a new source; a 'none' citation is valid for greetings or declined off-topic questions. The client strips this header and renders it as visible source badges, turning grounding into an auditable trail rather than a claim to trust. _Developers building trustworthy LLM chat interfaces can track grounding and citation techniques like this on daily.dev._ ## Similar posts on daily.dev - [How To Build An AI Agent For Talent Matching – Part 2](https://daily.dev/posts/how-to-build-an-ai-agent-for-talent-matching-part-2-zpajasr7o) · The Miners · 1 upvotes · 0 comments - [I built a Tool for helping my friend next interview](https://daily.dev/posts/i-built-a-tool-for-helping-my-friend-next-interview-qq49xrash) · DEV · 4 upvotes · 0 comments --- Tags: [#career](https://daily.dev/tags/career), [#llm](https://daily.dev/tags/llm), [#devtools](https://daily.dev/tags/devtools), [#prompt-engineering](https://daily.dev/tags/prompt-engineering), [#cloudflare](https://daily.dev/tags/cloudflare) [View this post on daily.dev](https://daily.dev/posts/i-turned-my-resume-into-an-ai-you-can-interrogate-p8yudcttn) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"I Turned My Resume Into an AI You Can Interrogate","url":"https://daily.dev/posts/i-turned-my-resume-into-an-ai-you-can-interrogate-p8yudcttn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-turned-my-resume-into-an-ai-you-can-interrogate-p8yudcttn"},"datePublished":"2026-07-23T14:52:08.530Z","dateModified":"2026-09-14T07:27:24.578Z","description":"A developer built an AI-powered interactive resume called Signal Sifter that lets recruiters interrogate a career story via chat, while also serving as a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4b3d6610838c4440f2419257ee8236ac?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4b3d6610838c4440f2419257ee8236ac?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"gitconnected","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"gitconnected","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/gc","url":"https://daily.dev/sources/gc"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-turned-my-resume-into-an-ai-you-can-interrogate-p8yudcttn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":6},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"career,llm,devtools,prompt-engineering,cloudflare","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"gitconnected","item":"https://daily.dev/sources/gc"},{"@type":"ListItem","position":3,"name":"I Turned My Resume Into an AI You Can Interrogate"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/i-turned-my-resume-into-an-ai-you-can-interrogate-p8yudcttn#faq","mainEntity":[{"@type":"Question","name":"Do I need a vector database to build a chatbot that answers questions from a resume or personal document?","acceptedAnswer":{"@type":"Answer","text":"No, a vector database is unnecessary when the source data is small enough to fit entirely in an LLM's context window, such as a resume plus career narrative totaling a few kilobytes of text. The full JSON can be stringified directly into the system prompt on every request, eliminating embeddings, chunking, and retrieval tuning. RAG is worth its cost only when a corpus is too large for context, changes faster than it can be re-embedded, or must be queried across many documents. Anyone weighing RAG against a simple context-stuffed prompt can compare real-world LLM architecture writeups on daily.dev."}},{"@type":"Question","name":"How can I stop an LLM chatbot from hallucinating facts when answering questions about a specific person or dataset?","acceptedAnswer":{"@type":"Answer","text":"Force every model reply to open with a machine-readable citation line naming the exact source keys used, drawn from a closed list defined in the system prompt, before any answer text. The model can only cite from that predefined list and never invent a new source; a 'none' citation is valid for greetings or declined off-topic questions. The client strips this header and renders it as visible source badges, turning grounding into an auditable trail rather than a claim to trust. Developers building trustworthy LLM chat interfaces can track grounding and citation techniques like this on daily.dev."}}]} ```