personalization · pillar 02
Generic AI gives every candidate the same answer. Mirly rebuilds the system prompt every session from your résumé, your target job, and three to five STAR stories you paste once. The model is forbidden from contradicting what you actually shipped.
Without profile
default model output
• Audited existing IAM policies across AWS accounts and services. • Implemented IAM Access Analyzer to monitor for unintended access. • Leveraged AWS Organizations for centralized user and group management. • Established a regular review cycle for IAM roles and policies. • Documented baseline least-privilege policies using Config rules.
every other candidate gets these same bullets
With profile · Sam Patel
résumé · STAR stories · JD loaded
• At Stripe the merchant team had 1,200+ IAM roles with overlapping policies. • I built an analyzer in Go that diffed real CloudTrail traffic against role policies. • It opened minimal-policy PRs automatically — three rollout waves, four months. • Cut 87% of unused permissions, ended at 312 roles. • IAM-related Sev2 incidents went to zero for two consecutive quarters.
your story, your numbers, your voice
mechanism
01
Résumé text, target JD, three to five STAR stories. Stays in localStorage on your device. Roughly five minutes of setup, lifetime payoff.
02
The system prompt is composed from your inputs at session start, with two cache breakpoints — base rules and your profile. Follow-up questions in the same call are 5× cheaper and faster.
03
Explicit instructions: cite numbers from your résumé, match your sentence cadence, do not fabricate experience. The model says it does not know rather than invent.