@vartekxx: Boris Cherny just dropped 7-page PDF on Graph Engineering - how 4 Claude prompts replace 4 trained ML models The twist:…

X AI KOLs Timeline Tools
graph-engineering claude prompts knowledge-graph ml extraction resolution summarization querying

Summary

Boris Cherny released a 7-page PDF on Graph Engineering, showing how to use four Claude prompts to replace trained ML models by building a persistent knowledge graph for agents, with steps for extraction, resolution, summarization, and querying.

Boris Cherny just dropped 7-page PDF on Graph Engineering - how 4 Claude prompts replace 4 trained ML models The twist: your agent's memory dies with the context window. A knowledge graph makes it permanent - and now you build one with prompts, not ML engineers. here's 4 prompts, step by step: prompt 1 → extraction - Haiku pulls entities + relations - one call per doc - no NER, no labeled data prompt 2 → resolution - Sonnet merges duplicates string matching will never catch - two different names, same person prompt 3 → summarization - Sonnet builds profiles from multiple sources - facts that never appeared in the same document prompt 4 → querying - feed the graph to Sonnet - every answer cites a specific edge - no hallucination how to wire this into agents today: step 1 → shared memory for multi-agent teams - workers read/write one graph - orchestrator's context stays clean step 2 → grounding layer for eval loops - evaluator checks facts against graph edges, not vibes the result: one Pydantic schema replaces weeks of ML training per domain - precision 1.00 - 10k docs cost under $10 this 7-page PDF is what comes after loop engineering bookmark this, then read the article below ↓
Original Article
View Cached Full Text

Cached at: 07/24/26, 05:16 PM

Boris Cherny just dropped 7-page PDF on Graph Engineering - how 4 Claude prompts replace 4 trained ML models

The twist: your agent’s memory dies with the context window. A knowledge graph makes it permanent - and now you build one with prompts, not ML engineers.

here’s 4 prompts, step by step:

prompt 1 → extraction - Haiku pulls entities + relations - one call per doc - no NER, no labeled data

prompt 2 → resolution - Sonnet merges duplicates string matching will never catch - two different names, same person

prompt 3 → summarization - Sonnet builds profiles from multiple sources - facts that never appeared in the same document

prompt 4 → querying - feed the graph to Sonnet - every answer cites a specific edge - no hallucination

how to wire this into agents today:

step 1 → shared memory for multi-agent teams - workers read/write one graph - orchestrator’s context stays clean

step 2 → grounding layer for eval loops - evaluator checks facts against graph edges, not vibes

the result: one Pydantic schema replaces weeks of ML training per domain - precision 1.00 - 10k docs cost under $10

this 7-page PDF is what comes after loop engineering

bookmark this, then read the article below ↓

Boris Cherny - Anthropic | LinkedIn

Source: https://www.linkedin.com/in/bcherny

United States 71K followers500+ connections

About

📕 Author, OReilly’s Programming TypeScript ⚡ Github:…

Activity

71K followers

Experience & Education

  • Anthropic

View Boris’s full experience

See their title, tenure and more.

Publications

Languages

  • Russian #### Native or bilingual proficiency

  • English #### Native or bilingual proficiency

View Boris’ full profile

Join to view full profile

Other similar profiles

Explore more posts

Explore top content on LinkedIn

Find curated posts and insights for relevant topics all in one place.

View top content

Add new skills with these courses

Similar Articles

Graph Engineering (GitHub Repo)

TLDR AI

A curated collection of research papers, benchmarks, and open-source projects on Graph Engineering in the era of LLM Agents, accompanying an arXiv survey paper to advance research from individual to system intelligence.