Cases
Technical Intelligence

Gerolamo: Building a Technical Intelligence Corpus in Three Weeks

Adjective built Gerolamo as a public proof of the Custom Corpus model — demonstrating that a small team running a focused Operational R&D motion can ship a production intelligence system in weeks, not quarters. Started April 5, 2026. Public surface live within two weeks. The access logs from the first three weeks told a story we did not expect.

Client
Adjective (Internal Proof System)
Timeline
3 weeks to production
Sector
Technical Intelligence

Challenge

The open-source technology landscape is moving too fast for human analysts to track. Millions of new repositories, research papers, and AI models appear every month. Existing tools show what is popular — stars, downloads, trending lists — but none of them answer the questions that matter for strategic decisions: What is defensible? What is about to be commoditized by frontier labs? What is genuinely novel versus derivative? There was no intelligence product that scored the landscape on durability, risk, and novelty simultaneously, and no product that made that intelligence addressable by both human analysts and AI agents.

Approach

01

Corpus Architecture & Ingest Pipeline

Designed a multi-source ingestion system that normalizes code, research, and models into a single searchable landscape with daily refresh cycles

▪GitHub, arXiv, and Hugging Face ingestion pipelines
▪Entity normalization across ~190 technical domains
▪Daily pipeline: ingest → evaluate → fuse → materialize → embed
▪Junk filtering and deduplication layer
02

AI Evaluation & Scoring Engine

Built an LLM-powered evaluation layer that scores every entity on defensibility, frontier risk, novelty, and composability

▪Defensibility scoring (1-10) with full reasoning chains
▪Frontier risk assessment (LOW / MEDIUM / HIGH)
▪Novelty classification (breakthrough → derivative spectrum)
▪Intelligence Primitives — structured, typed, queryable units called "molecules"
03

Agent-Native Surface (MCP Server)

Exposed the entire corpus as a Model Context Protocol server so AI agents can search, score, compose, and synthesize intelligence alongside human analysts

▪23 MCP tools for agent-driven research workflows
▪Semantic search (1024-dim OpenAI embeddings)
▪Workspace composition with 5 synthesis modes
▪Compatible with Claude Code, custom GPTs, and any MCP client
04

Public Surface & Relationship Graphs

Shipped the human-facing interface with ranked views, entity drill-downs, creator profiles, trajectory charts, and the Conspectus macro-intelligence layer

▪Defensibility and trending ranked views
▪Entity detail pages with relationship graphs
▪Creator authority scoring and portfolio views
▪Conspectus: AI-generated topic-level summaries across all tracked domains

Impact

3 weeks
Time to Production

From zero to a live, scored, searchable intelligence corpus covering ~190 technical domains

2,152 MCP calls
Agent Adoption

The MCP server became the second busiest endpoint on the platform — ahead of every human-facing workflow. Agent traffic outpacing human traffic per-IP and widening week over week.

600 unique IPs
Organic Reach

Zero paid acquisition, no launch plan, no ads. Posted a few links and went back to building. MCP surface used by agents inside organizations Adjective did not introduce itself to.

5,204 visits
Defensibility Scans

399 unique browsers averaging 13 page loads per visitor on the defensibility rankings alone — indicating strong return-visit behavior in week three

"
Humans browse. Agents query. The ratio between the two seems to be widening week over week, and the agent surface is starting to feel like a first-class product on its own.
Gerolamo Platform Team
Adjective
Visit Gerolamo Explore Gerolamo

Build What's Next

Move faster. Spend smarter. Prove more before you bet big.

Start an R&D Sprint