eidos agi

Case Studies

Real-world tasks. Autonomous agents.

Each case study documents a real task that the Eidos system completed autonomously — the problem, the approach, the outcome, and what it reveals about how AI systems actually work.

These are not demos. They are production systems where our team of Eidos agents read structured data, plan their own work, and produce results — from ordering groceries to securing enterprise software approval.

Coming next

01

Voice notes

A Mac app records voice, transcribes locally with Whisper, classifies via Claude Agent SDK, and stores in recording buckets that a search engine indexes.

5 contracts 3 languages 3 processes
Swift + Python + JSON Schema + Omni
02

Project improvement

A forge scores any project across 10 dimensions, fixes the highest-impact gap, and records a snapshot. The snapshot schema is the contract.

1 contract 3 projects improved Self-improving
improve-forge + JSON Schema
03

Learning capture

A forge that extracts learnings from sessions, routes project-level fixes directly and proposes forge-level improvements to the overseer.

1 contract 15 learnings routed 10 proposals
learning-forge + forge-forge governance

The pattern across every case study: structured data goes in, an agent figures out how to produce the result, and the system gets better each time it runs.

How it works: The DAG of AI