Select 0.2 released: AI Agents gain autonomy based on verification records
Understand this story
Select releases version 0.2 of its open-source multi-agent platform, letting agents for development, marketing, customer service and more work within organizations designed by users. Each delivered result is validated by code against a YAML contract and a receipt is retained; only after consecutive passes does an agent upgrade from supervised mode to sampling or autonomous mode, and any blocking failure or manual correction triggers a rollback. The publisher states that accounts, onboarding setup, local IMAP/SMTP email testing, routines and the verification loop are covered by end-to-end tests, but real model API calls have not yet been verified, nor has compatibility with real providers been certified by the maintainers. OAuth is currently unsupported: Microsoft 365 and Outlook.com cannot connect, and Gmail requires an app-specific password. Users without an API key can open the demo company from the account menu and run a demo week.
AI overview based on source reports · Updated 42 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Select – AI agents that earn autonomy through verified work
Select is a multi-agent system where agents in roles like support, sales and marketing work under YAML delivery contracts whose checks are run by code, with receipts kept, and earn promotion from supervised to sampled to autonomous per task type based on verified successes, reverting on failure or human correction. It is at version 0.2, with Docker/Compose startup and end-to-end tests covering accounts, guided setup, local IMAP/SMTP mail and the verification loop, but real model API calls and real mailboxes have not yet been verified. Payments, contracts, taxes and hiring remain always supervised in code, and no benchmarks have been published yet.
Activity for this story
Not enough continuous observations to show a trend yet.