Refinement prototype · Activate job › Evaluation criteria

Smarter skill suggestions

The “Teach your AI recruiter” step, with evaluation suggestions generated from the job title and description instead of title-taxonomy mapping — including niche terms like Mazatrol and Renishaw probing that the taxonomy doesn't have. Every suggestion is one-click accept; nothing auto-populates. Use the pill at the bottom to switch between the Generating, AI suggestions, and Taxonomy fallback states.

Describe the role

Share essential job details

Direct hire
per hour
Wisconsin
Precision Manufacturing Inc. Keep company name confidential
BI Generate my job description

Precision Manufacturing Inc. is hiring a 2nd-shift CNC Machinist for our Milwaukee plant. You'll set up and run Haas VF-2 vertical machining centers and Mazak lathes with live tooling, working from blueprints and GD&T callouts to hold tolerances to ±0.0005".

Day to day you'll make program edits at the control (Fanuc and Mazatrol), set tool offsets, verify first articles with CMM and Renishaw probing, and keep preventive maintenance logs. Strong shop math and precision measurement skills are a must. 2nd shift runs 2pm–10pm with a $1.50/hr shift premium.

Select your AI recruiter

Choose the AI recruiter that best fits this role

Copilot FactoryFix Default
Created by FactoryFix
Select

Teach your AI recruiter how to evaluate candidates

Define what makes an ideal candidate

Align on your AI recruiter's sourcing strategy

Choose where and how your AI recruiter finds the best candidates for this role

Who should your AI recruiter source for this job?

Active job seekers + passive candidates
Source from active job seekers and qualified passive talent in the FactoryFix network
Active job seekers only
Source only from candidates actively searching for a new job
Sourcing radius
Controls how far from the job location your AI recruiter will source passive candidates. Smaller radii can reduce commute mismatches, especially for hourly roles. Doesn't affect inbound applicants.
15 miles20 miles25 miles 30 miles50 miles100 miles

How would you like your AI recruiter to manage this job's visibility on job boards?

Optimize visibility
Your AI recruiter will adapt the title and description periodically to maintain high rankings and steady applicant flow
Keep original
Always use your exact job details; rankings will decline over time, reducing inbound applicant traffic

Set your AI recruiter's interview style

Decide how your AI recruiter should evaluate and interview candidates

Interview and dig deeper
Review their resume and ask meaningful questions to get the full picture
+ Add your own questions (optional)
Stick to set questions
Use your preset questions for candidates who apply directly
Skip automated screening entirely
Don't ask candidates any questions at all

Do you want your AI recruiter to schedule interviews for you?

No, I'll review first
You'll review each candidate first and decide how to proceed from there
Yes, schedule interviews BETA
Your AI recruiter will book interviews with high-scoring candidates who complete screening

Upload candidates

Add external candidates to this job by uploading their resumes

Drag and drop resumes here or click to browse

How should your AI recruiter handle these candidates?

Screen as Applicants
Add candidates to the 'New' stage for immediate screening
Contact as Prospects
Add candidates to the 'Sourcing' stage for AI-driven outreach
Skip engagement entirely
Add candidates to the 'New' stage with no automated messaging

Three behaviors that aren’t obvious from clicking around the prototype.

Reading the post. Suggestions are generated from the display title and description, with the taxonomy as a guide — clean matches keep their taxonomy IDs so structured data keeps working, and niche terms like Mazatrol arrive as custom entries instead of being dropped.

Accepting a suggestion. Nothing auto-populates — a recruiter’s click is what turns the AI’s purple suggestion into a real evaluation input, and the chip goes neutral the moment it’s theirs. A bad guess can’t silently skew screening or scoring.

When generation fails. The fields quietly fall back to today’s taxonomy suggestions and activation never blocks. Generated, shown, and accepted counts are tracked, so we can tell whether the model is helping — and where the taxonomy has gaps.

Prototype state