Skip to content
Directory
GitHub Star

ETF Agent · NotesBuild financial research agents from scratch. No Agent framework required.

Learn long-running tasks, multi-agent collaboration and verifiable research delivery through fund research. Clear principles. Runnable source code.

READ WITH A PURPOSE

Find your next read

Recently added & updated

All articles →

New articles and content changes, based on source history. Prose whitespace-only edits are skipped. Dates: UTC+8.

  1. Subagent Panorama: Independent Context, Specialist Work and Real Handoffs

    When does another expert earn its cost? Follow one fund-research question through general Children, specialist methods, Reviewer and Bull/Bear exchanges, tracing evidence into independent contexts and results back to Main while weighing repeated preparation against verifiable contributions.

    Updated
  2. Start with a Report You Can Read Back: Open ETF Agent v0.1

    Run the fixed offline example to inspect source identity, tool execution, partial writes, and independent file readback, then separate known facts from gaps in a real-model rejection.

    Updated
  3. Spec-Driven Agent Development: From Requirements to Trustworthy Delivery

    Start with the background and purpose of specifications, then follow file ingestion through principles, design, templates, behavior, verification, archiving and template maintenance—without copying project-specific ceremony.

    Updated
  4. Keep Chatting Is Not Keep Executing: Agent Conversation Admission and Task Continuation

    How does a follow-up become a legitimate new task? A practical guide to message idempotency, conversation history, clarification binding, and explicit Agent Run continuation.

    Updated
  5. Designing Half-Hour Agent Research: From Ordinary Research to Reliable Delivery

    What changes when ordinary research becomes a long-running task? Follow a three-fund comparison through concrete integration steps for request assembly, budgets and finalization, material rereading, checkpoints, and report revisions, with links to the existing implementation guides.

    Updated
  6. Why Split an Agent into Three Processes? Independent Lifecycles Without Splitting Business Truth

    A field-tested architecture case study of Core API, Product API, and Background Worker: measured lifecycle isolation, foreground capacity handoff, crash recovery, and local transport identity, without claiming production SLA gains.

    New
  7. Agent Execution Identity Panorama: From a Conversation to Model Turns—What Actually Continues?

    Follow a fund-comparison conversation down to tasks, runs, model turns, request attempts, and tool actions. See which identities continue through replies, process recovery, and scheduled execution—and use those distinctions to design and debug an agent.

    Updated
  8. View all articles Explore the complete catalogue

Engineering notes, evidence and boundaries. · Contact: hpoenixf@foxmail.com · WeChat: hpoenixf0510