Multi-agent (LangGraph + Claude) app that turns an earnings call into a source-attributed analyst brief: ingest - FinBERT tone + KPI-vs-consensus - SurpriseSignal - grounding check - delivery.
Instructions file GitHub Copilot
Copilot instructions for suhaas/earnings-edge, covering earnings-edge: agent development guidelines, architecture & core concepts, the graph, agent roles and tools & skills boundary.
Instructions file GitHub Copilot
Rules for testing and evals: no network in unit tests, eval datasets versioned, scorers deterministic. Use when: writing tests, adding eval cases, updating eval suites.
Instructions file GitHub Copilot
Rules for system prompts: immutable versioning, composition, guardrails. Use when: drafting or updating prompts, promoting v1→v2, updating registry.yaml.
Instructions file GitHub Copilot
Rules for all Python files: strict typing, async-first, error wrapping, imports organization, no print(). Use when: modifying src/ files, adding agents, tools, or utility functions.
Instructions file CodexOpenCode
AGENTS.md instructions for suhaas/earnings-edge, covering earnings-edge: agent development guidelines, architecture & core concepts, the graph, agent roles and tools & skills boundary.
Instructions file
Claude Code instructions for suhaas/earnings-edge, covering earnings-edge: project memory for claude code, architecture & core concepts, the graph, agent roles and tools & skills boundary.