The challenge
A consistent LinkedIn presence and tailored job applications take hours every week.
Fully automated posting tools break platform terms and produce generic content that damages credibility.
- 01
ResearchLive web search
- 02
ScoreTopic relevance scoring
- 03
DraftPosts, comments, cover letters
- 04
ReviewHuman edits and publishes
Architecture · 4 stages
- 01
Research
Live web search
- 02
Score
Topic relevance scoring
- 03
Draft
Posts, comments, cover letters
- 04
Review
Human edits and publishes
The solution
I built a three-agent system that researches and scores topics against live web search, then drafts posts, comments and tailored cover letters.
It runs locally, and every publish or apply action stays manual, which keeps users within platform terms of service.
Engineering highlights
- Three-agent architecture
- Topic scoring grounded in live web search
- Drafts posts, comments and cover letters
- Compliance by design: a human publishes
Technology
- Python
- React
- OpenAI API
- Web search
Related services
Building something similar?
Get a candid view of the architecture, risks and timeline on a free 30-minute call, or ask the AI assistant how this approach would map to your project.