Orca Builds Automations From Prompts

// 45m agoPRODUCT UPDATE

Orca Builds Automations From Prompts

Orca now lets developers create full scheduled automations by describing them to an agent, with support across Chat UI and terminal workflows. Its automation system supports scheduled prompts, agent selection, and reviewable run conversations. [Orca docs](https://www.onorca.dev/docs/cli/reference)

// ANALYSIS

This pushes agent tooling toward a more natural interface: automation becomes something developers specify and refine conversationally rather than assemble manually.

–Chat and terminal parity lets users choose between a visual workflow and a familiar CLI-first experience
–Recorded conversations make unattended agent runs easier to inspect and audit
–Per-automation agent and model settings make recurring workflows more practical for real repositories
–Prompt-defined workflows remain flexible, but still need strong permission, branch, and secret-management guardrails
–Orca’s open-source, multi-agent foundation makes this more compelling than a standalone no-code automation builder [Orca homepage](https://www.onorca.dev/)

// TAGS

orcaagentautomationcoding-agenttool-usedevtoolopen-source

DISCOVERED

45m ago

2026-11-09

PUBLISHED

1h ago

2026-11-09

RELEVANCE

8/ 10

AUTHOR

orca_build

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH13m ago

Anthropic Paper Finds Weak-Coupling Transition First Order

An Anthropic-contributed Hexagon preprint reports that the Hawking–Page-like transition in weakly coupled N=4 super Yang–Mills remains first order, based on a negative quartic Polyakov-loop coefficient. The AI-assisted calculation was checked against known cases, but remains an unreviewed preprint.

RESEARCH13m ago

Claude Derives Sharp Large-c Bootstrap Bound

Anthropic’s primarily AI-generated Hexagon preprint reports an exact asymptotic slope, ΛV ≈ 9.1266, for spinless modular-bootstrap bounds on 2D CFT spectral gaps. The result narrows a previously broad range while remaining limited to a restricted, computer-assisted method. [Hexagon preprint](https://hexagonmath.org/2611.00174v1)

MODEL13m ago

Claude Fable 5.2 Formalizes Fermat With 1,000 Agents

Anthropic says 1,000 Claude Fable 5.2 agents formalized Fermat’s Last Theorem in Lean in about 30 hours, using shared SQL state, Git branches, automated grading, and layered safety controls. The run used one-third as many output tokens and produced a proof one-seventh the length of an earlier 11-day effort.