Kestrel
2026 · Builder + Product Thinker
AI role-readiness tool that turns a target job description and candidate profile into fit signals, ranked gaps, resume direction, and a next-step roadmap.
Turns scattered career prep into one structured decision view: what matches, what is missing, what to improve first, and what to do next.
Kestrel is a role-readiness tool for early-career candidates comparing their background against a specific job. It extracts role requirements, evaluates fit, surfaces strengths and ranked gaps, then turns the result into a roadmap the user can act on before applying. The goal is not more career advice. It is a clearer decision about what to fix, what to highlight, and what to do next.
Key Product Decision
Kestrel could have been a chatbot, but chat would have made the hardest part easier to avoid: ranking the user’s next move. I chose a structured card-based dashboard so the system had to show what it found, why it mattered, and what the user should do first. That constraint made the product more useful for career prep and more credible as a decision-support tool.
Product Thesis
Career preparation is not an information shortage problem. Candidates already have job posts, advice, and resume feedback. What they lack is a ranked order of operations tied to the specific role they want.
Product Bet
A structured output that ranks fit score, skill gaps, resume direction, and roadmap is more useful than a chat interface that gives advice without prioritization.
Early-career candidates targeting PM, Solutions Engineering, and adjacent roles often prepare from scattered inputs: job posts, resume edits, advice threads, and unclear role expectations. The result is effort without sequence. Candidates keep revising materials before knowing which gaps matter most, and they lack a clear way to judge whether they are ready for a specific role.
Job descriptions mix hard requirements, soft preferences, and filler language, making it hard to tell which gaps are serious and which are negotiable.
Candidates often revise their resume before knowing which capability gaps actually matter for the role.
Generic AI tools can produce advice, but they rarely rank what matters first. They list options without turning them into a decision path.
Built for early-career candidates targeting PM, Solutions Engineering, and SWE-adjacent roles who need to compare their background against a target job and decide where to focus preparation time.
Primary User
Early-career candidates applying across related technical/product roles who need a faster way to assess fit and prioritize preparation for each target job.
Job To Be Done
Show me where I stand against this role, rank what I should work on first, and give me a next step I can use before applying.
Kestrel parses the job description, extracts its core requirements into structured role signals, compares those signals against the user profile, and returns a readiness score, matched strengths, ranked skill gaps, resume improvement prompts, and a prioritized next-step roadmap in a card-based dashboard designed for fast scanning and clear interpretation.
Requirements Extraction
Parses job descriptions into structured role signals, separating hard requirements from soft preferences so candidates see what the role actually demands versus what it merely mentions.
Ranked Gap Analysis
Compares extracted requirements against the user profile and returns a ranked view: what is strong, what is marginal, and what is missing, ordered by likely impact on the application outcome.
Roadmap Generation
Converts the gap analysis into a concrete, sequenced action plan so users leave with a specific order of operations, not a general list of things to improve.
Kestrel decision dashboard
Turns scattered career prep into one structured decision view: what matches, what is missing, what to improve first, and what to do next.
Instead of leaving candidates with another generic suggestion list, Kestrel gives them a decision view: what to lead with in the application, what to address in preparation, and how to explain their fit with more specificity and confidence. The product reframes career preparation from scattered research into a clearer, more focused workflow.
User Shift
Candidates move from the cycle of applying-then-guessing to preparing against a specific, ranked target before the application is submitted.
Product Signal
The value is not more advice. The value is making the next action obvious and specific to a real role, not a generic profile.
The hardest technical problem was normalizing inconsistent job description text into structured, comparable role requirements. I used a staged AI pipeline with typed output schemas to keep requirements, scores, gaps, and roadmap items consistent enough to render reliably, support cross-role comparison, and stay explainable to the user.
Structured Extraction
Typed output schemas constrained the AI pipeline to return requirements in a consistent shape, which is critical for rendering, ranking, and comparing results across different job descriptions.
Explainability by Design
Card-based outputs were a deliberate constraint: each recommendation had to be specific enough to attribute to a requirement and readable in under ten seconds without additional context.
The strongest product decision was restraint. An early version tried to generate polished resume sections. That was the wrong level of abstraction. Candidates needed to know what to fix and why, not to have AI write it for them. Once the output narrowed to fit score, ranked gaps, resume direction, and roadmap, the product felt more credible, more trusted, and significantly more actionable.
What I Cut
Resume generation, open-ended coaching, and broad career comparison. All of it expanded the surface area without improving the core decision a user needed to make.
What Remained
Score, gaps, resume direction, and roadmap appear in ranked order, specific to the role. Once the scope narrowed to those four outputs, the product felt like a tool rather than a demo.