Execute Juicebox people search with power filters and ATS export. Trigger: "find candidates", "people search", "juicebox search".
83
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Complete candidate sourcing: natural language search with power filters, scoring, and export to 41+ ATS systems.
const results = await client.search({
query: 'backend engineer distributed systems',
filters: {
location: ['San Francisco', 'Seattle', 'Remote'],
experience_years: { min: 3, max: 10 },
skills: ['Go', 'Kubernetes', 'distributed systems'],
company_size: '100-1000',
exclude_companies: ['CurrentEmployer']
},
sort: 'relevance', limit: 50
});function scoreCandidate(profile, targetSkills: string[]) {
let score = 0;
const matched = profile.skills.filter(s =>
targetSkills.some(t => s.toLowerCase().includes(t.toLowerCase()))
);
score += matched.length * 20;
if (profile.experience_years >= 5) score += 30;
return { profile, score, matchedSkills: matched };
}
const ranked = results.profiles
.map(p => scoreCandidate(p, ['Go', 'Kubernetes']))
.sort((a, b) => b.score - a.score);await client.export({
profiles: ranked.slice(0, 20).map(r => r.profile.id),
destination: 'greenhouse', // lever, ashby, recruiterflow, etc.
job_id: 'job_abc123'
});| Error | Cause | Solution |
|---|---|---|
| Low results | Filters too strict | Relax experience or location |
| Duplicates | Overlapping searches | Deduplicate by LinkedIn URL |
For enrichment, see juicebox-core-workflow-b.
c8a915c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.