Tailoring IT Job Applications

Required inputs before starting:

1. Target job posting (text or URL)
2. Base resume
3. Optional: certifications, projects, achievements notes
4. Optional: specific application/interview questions needing answers
5. Desired deliverables (resume, cover letter, Q&A sheet, all of the above)

If any of items 1–2 are missing, stop and request them before proceeding. Items 3–5 can default: no extra background → work from resume only; no deliverables specified → produce all four (resume, cover letter, interview prep, Q&A table).

Progress:

• Step 1: Parse job posting — extract required skills, tools, certifications, years of experience, soft skills, and repeated keywords
• Step 2: Map resume to posting — identify matches, gaps, and transferable experience
• Step 3: Rewrite resume with keyword alignment (no fabrication)
• Step 4: Draft cover letter connecting candidate narrative to role/company
• Step 5: Rewrite any provided application question answers
• Step 6: Generate interview prep notes (likely topics, company research angle, talking points)
• Step 7: Build Q&A table (Question / Suggested Answer / Key Points / Difficulty Level)
• Step 8: Recommend certifications/skills based on gaps found in Step 2
• Step 9: Self-review all deliverables against the posting for keyword coverage and accuracy
• Step 10: Present deliverables, flag assumptions/gaps, ask what to refine next

Step 1 Detail: Job Posting Analysis

Produce a short requirements map before anything else:

• Must-have hard skills (languages, platforms, tools)
• Certifications required/preferred
• Years of experience expected
• Soft skills / culture signals (e.g., "cross-functional," "agile," "client-facing")
• ATS keywords — exact phrases likely scanned (e.g., "AWS," "CI/CD," "ITIL")

Step 2 Detail: Gap Mapping

Three buckets:

• Direct match — resume already demonstrates this, just needs keyword alignment
• Transferable — related experience exists, needs reframing
• Gap — not present in resume; do not fabricate — note it for the recommendations section instead

Step 3 Detail: Resume Rewrite Rules

• One page if <8 years experience, two pages max otherwise
• Lead bullets with action verbs (Led, Architected, Automated, Reduced, Migrated)
• Quantify every bullet possible (%, $, time saved, scale: "managed 200+ endpoints")
• Insert exact keyword phrases from posting where truthfully applicable (e.g., if posting says "Kubernetes," don't substitute "container orchestration" only — use both)
• Standard sections: Summary, Technical Skills, Experience, Certifications, Education
• Avoid tables, text boxes, headers/footers, graphics — these break ATS parsers
• Never invent metrics, titles, tools, or dates

Step 7 Detail: Q&A Table Format

Output as a markdown table ready for .xls export, then note: "Copy this table into Excel or Google Sheets and save as .xls."

Columns: Question | Suggested Answer | Key Points | Difficulty Level

Difficulty Level = Easy / Medium / Hard, based on technical depth or behavioral complexity.

Cover: 3-5 technical/role-specific, 3-5 behavioral (STAR format), 2-3 company/culture fit, 2-3 candidate-specific (based on resume gaps or career changes).

Example 1: Input: Job posting requires "5+ years cloud infrastructure, AWS, Terraform, on-call experience." Resume shows "3 years DevOps, Azure, scripting, rotational support." Output:

• Gap flagged: AWS/Terraform not present — resume uses Azure/scripting instead. Recommendation section suggests AWS certification (e.g., AWS Solutions Architect Associate) and notes Terraform as a high-priority skill gap.
• Resume bullet reframed: "Automated infrastructure provisioning using scripting and configuration management tools, reducing deployment time by 40%" — keeps Azure/scripting truthful while mirroring IaC language from posting.
• Interview answer coaches candidate to bridge: "My Azure/IaC background transfers directly to AWS/Terraform — same principles, different syntax" rather than claiming AWS experience.

Example 2: Input: Candidate draft answer: "I'm good at fixing problems when they come up." Output rewritten using STAR: "In my last role, a production database outage was impacting 500+ users. I led triage, identified a failed replication job within 20 minutes, and restored service in under an hour. I then implemented automated replication health checks that prevented recurrence." Key Points: ownership, speed, root-cause fix, proactive follow-through.