Ambuj Systems - Career Workspace
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HF_TOKEN | No | Candidate Hugging Face ML models, spaces, and dataset proofing | |
| MONGODB_URI | No | Telemetry, generation audit logs, and user feedback persistence | |
| GITHUB_TOKEN | No | Higher rate limits for candidate public GitHub repository audits | |
| JINA_API_KEY | No | Markdown parser fallback for target company landing pages | |
| GEMINI_API_KEY | Yes | Primary synthesis engine (Google AI Studio Gemini 2.5 / Flash) | |
| TAVILY_API_KEY | Yes | Live web grounding & target company intelligence crawler | |
| OPENROUTER_API_KEY | No | Multi-model provider fallback if primary Gemini API quota is throttled |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| company_researchA | Search the web for company information using Tavily. Returns grounded data with source citations. Every claim is traceable to a source URL. |
| evidence_validatorA | Validate AI-generated claims against actual source data. Implements Claim Ledger pattern. Returns VERIFIED / PARTIAL / UNSUPPORTED per claim. |
| jd_analyzerA | Evidence-backed JD matching. Extracts skills from JD, matches each against resume with ACTUAL evidence. Returns STRONG_MATCH / PARTIAL_MATCH / TRANSFERABLE / MISSING per skill. |
| ats_readinessA | Honest ATS readiness check (NOT a fake score). Returns individual checks: keyword coverage, skills, evidence, length. Includes disclaimer: heuristic analysis, not actual ATS vendor score. |
| source_filterA | Evaluate, rank, and filter web research sources based on domain credibility and outdated news & stale tech filtering. Tier 1: Official company domains & verified newsrooms, Tier 2: Job boards & tech media, Tier 3: Noise/scrapers. |
| cover_letter_generatorA | Generate an evidence-grounded cover letter strictly bounded by candidate's verified skills and approved company research. Returns structured paragraphs with in-line citation markers. |
| github_prooferA | Inspect a candidate's public GitHub profile and repositories. Cross-references technical resume claims with verifiable production code commits. |
| huggingface_prooferB | Inspect a candidate's public Hugging Face profile, models, spaces, and datasets. Cross-references GenAI resume claims (fine-tuning, LoRA, GGUF, Quantization, Legal AI) with verifiable Hugging Face model weights, spaces, and real-world downloads. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes across the job-application pipeline (research, proofing, validation, generation). The two proofers (github_proofer vs huggingface_proofer) and the grounding-related tools (source_filter, company_research, evidence_validator) are conceptually adjacent but each targets a distinct stage, so confusion is limited.
All names use consistent snake_case and a predictable descriptor-noun convention (source_filter, evidence_validator, jd_analyzer, ats_readiness). Minor stylistic variation between agent-noun (proofer) and object-noun (generator) patterns, but readable and uniform overall.
Eight tools is well-scoped for a career workspace, with each tool mapping to a discrete step in a resume/JD/application workflow. Nothing appears redundant or bloated.
The surface covers research, JD matching, ATS checks, evidence validation, and cover letter generation with strong grounding. Minor gaps exist: no resume parsing/tailoring or interview-prep tool, but the core application lifecycle is largely covered.