Turn skills and preferences into career direction options
Author: AILesson9 min setupTested with:ChatGPTReviewed: 2026-08-28
Quick answer
Generate testable career directions from verified evidence, constraints, and unknowns rather than personality labels. Provide: Skills and evidence, Preferences and dislikes, Practical constraints and goals. Expected result: A bounded career option set with fit evidence, gaps, trade-offs, and low-cost exploration steps.
1
Add your context
Your text stays in this browser. AILesson Prompts does not send it to a model or server.
2
Your prompt
Unfilled fields remain visible as placeholders, so you can still copy and edit the prompt
Create a set of career direction hypotheses from the supplied evidence. This is exploration, not a personality test or labor-market forecast.
Performed tasks, artifacts, outcomes, feedback, tools, knowledge, and confidence:
[evidence]
Energizing/draining activities, environment, collaboration, learning, values, and uncertainty:
[preferences]
Location, schedule, income, accessibility, caregiving, timeline, risk, credentials, and resources:
[constraints]
Separate demonstrated skill, self-report, preference, value, constraint, and unknown. Do not infer identity, aptitude, health, personality type, seniority, salary, demand, or qualification not provided. Generate a deliberately varied but bounded option set including adjacent roles, task-shaped paths, and portfolio or hybrid directions where relevant. Use role families rather than claiming exact job titles are available.
For each direction show core work, evidence of fit, tensions, transferable assets, missing proof/skill, constraint compatibility, reversibility, and confidence with reasons. Do not numerically rank without supplied weights or current market data. Propose low-cost tests—informational interview, work sample, shadowing, course sample, volunteer or internal project—with question, output, time/cost cap, privacy boundary, and evidence that would support or reject the hypothesis. End with a comparison, next-two-tests plan, and facts requiring current external verification such as local salary, openings, credentials, or visa rules.
Private by defaultPrompt assembly happens locally in your browser. Avoid placing confidential information into any AI service unless your organization allows it.
From input to outcome
A worked example
See how concrete context turns this recipe into a usable result
Actual input
Skills and evidence
For three years I coordinated monthly reports from 14 library branches, standardized spreadsheets, wrote instructions, trained 20 colleagues, and reduced reconciliation from two days to four hours. Managers praise clarity and follow-through. I use Excel well and basic SQL with supervision. I have made two simple dashboards but no formal analytics portfolio. I also handle event logistics, accurately but without enjoying vendor negotiation.
Preferences and dislikes
I enjoy finding why numbers disagree, making a reusable process, explaining it one-to-one, and having several hours of focused work. Large live presentations and constant sales-style persuasion drain me. I prefer public-service or education impact, a collaborative team, predictable hours, and room to learn. I am unsure whether I enjoy deeper statistics or people management.
Practical constraints and goals
Need mostly weekday work, hybrid within commuting distance of my city, and current-income continuity; exact income floor is not supplied. I care for a parent two evenings weekly. Can spend 4 hours/week and up to 300 dollars over two months exploring. No plan to return for a full-time degree. Current local openings, salary, and credential requirements have not been checked.
Example output
Evidence map: demonstrated—multi-branch reporting, spreadsheet standardization, documentation, training, reconciliation outcome, logistics; emerging—basic supervised SQL and two dashboards; self-reported preferences—diagnosis, process design, one-to-one explanation, focus; constraints—weekday/hybrid/care schedule/income continuity; unknown—statistics interest, management interest, exact income floor, market requirements.
Direction hypotheses: (1) Operations/reporting analyst in public service or education. Fit: direct reporting/process evidence and measurable reconciliation result. Tension: may require more SQL/dashboard proof; presentation load varies. Confidence moderate-high for task fit, market fit unknown. (2) Data quality or data operations coordinator. Fit: diagnosing mismatches, standards, repeatable controls. Gap: database validation and governance evidence; likely focus-friendly, but on-call expectations must be checked. (3) Process improvement/knowledge operations specialist. Fit: instructions, training, workflow redesign; tension: stakeholder facilitation may include larger meetings. (4) Training enablement for data/process tools as a hybrid component, not necessarily full-time trainer. Fit: 20 colleagues and one-to-one explanation; tension: frequent delivery may drain energy. (5) Program operations in a mission-led organization. Transferable logistics/reporting; vendor negotiation is a known mismatch, so role composition matters. People management is not yet supported as a direction.
Test 1, ≤6 hours/$0: create an anonymized before/after reporting case study with schema, validation rules, and a small SQL query; ask one analyst and one data-operations practitioner which real tasks it evidences. Support H1/H2 if both identify relevant work and gaps feel learnable; reconsider if core daily tasks are mostly disliked or require unavailable credentials. Test 2, ≤4 hours/$0: conduct two 20-minute informational interviews using the same task-frequency questions about focus time, presentations, schedule, and on-call work; retain no employer-confidential data.
Do not rank by salary or availability yet. Verify current local role names/openings, weekday/hybrid patterns, salary against a user-supplied floor, credential expectations, and accessibility/care compatibility before choosing training.
Why this works
1
Evidence categories stop enjoyment, competence, and external feasibility from collapsing into one vague idea of fit
2
Small reversible tests create new evidence before an expensive course or career change
Check the result
Is each direction supported by supplied evidence and labeled unknowns rather than personality inference
Are practical constraints and tensions visible alongside attractive features
Does each exploration test have a bounded cost and evidence-based stop or continue rule
Use it with confidence
Frequently asked questions
Practical answers about when to use this recipe, what to provide, and where human review still matters
What should I prepare before using “Turn skills and preferences into career direction options”?
For “Turn skills and preferences into career direction options,” prepare Skills and evidence, Preferences and dislikes, and Practical constraints and goals. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.
When is the “Turn skills and preferences into career direction options” result not ready to use?
The result is not ready if it does not yet deliver the stated outcome—A bounded career option set with fit evidence, gaps, trade-offs, and low-cost exploration steps—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.
Which AI tools have recorded tests for “Turn skills and preferences into career direction options”?
The published test record for “Turn skills and preferences into career direction options” lists ChatGPT as of 2026-08-28. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.
ChatGPT