ETF Agent
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 29
- ETF Agent details its Deep Research engineering and tests
ETF Agent developers say they implemented Deep Research inside the existing Native Research Loop rather than creating a separate agent, adding authorized resource tiers, runtime-aware delivery guidance, versioning and recovery. Paired Standard/Deep experiments showed that both modes could run research and deliver formal answers, but fewer calls did not consistently translate into better accuracy, speed or cost. The developers explicitly say this engineering implementation is not a feature of the current public Open ETF Agent, and the findings are vendor-reported.
掘金 · 人工智能 · 🔥 5 - ETF Agent Separates Cleanup From Result Settlement
An engineering analysis of ETF Agent examines why awaiting cancellation or closure can delay an already known failure, replace its error classification, or affect retry and fallback decisions. Using controlled reproductions and simplified teaching code—not a reported production incident—the analysis covers oversized web responses, HTTP 401 responses from remote MCP services, shared Wind MCP connections, retrieval fallback, and resource ownership. The reported fixes preserve the original failure classification and allow the call to settle without waiting for cleanup. However, a settled result does not prove that remote requests stopped or that all resources were reclaimed. The report also notes that HTTP classification and Host retry rules were tested separately rather than as one end-to-end 401-to-retry chain.
掘金 · 人工智能 · 🔥 5 - How an Agent Client Presents Research and Citations
An article on ETF Agent client architecture explains how an Agent client should map user actions, concurrent runs, real-time events, historical reads, and citations. It emphasizes that receiving an SSE string does not prove that a research result was rendered correctly. Proposed acceptance scenarios cover misrouted responses, stale revisions, premature saves, permission errors, and citations linked to the wrong version. The article also points to Open ETF Agent’s local example for reading saved reports and sources, but states that the example was not rerun during its preparation and that it is not a complete product client.
掘金 · 人工智能 · 🔥 0 - ETF Agent adds non-additive report cost attribution
ETF Agent’s author describes an implemented cost view that links published reports and files to observed physical model attempts while keeping known estimates separate from unknown usage. The view marks shared attempts as non-additive, leaves shared costs unallocated, and treats cost-read failures without breaking access to already saved deliverables; the account is a single vendor-authored implementation description.
掘金 · 人工智能 · 🔥 0 - How ETF Agent Keeps Atomic Reports from Losing Their Identity
A Juejin AI engineering article describes a case where a same-day lightweight report replaced a formal portfolio report at the same date-based path, leaving the earlier run’s history pointing to different but still valid JSON. It attributes the problem to mismatched report identities, output paths, and discovery rules rather than model hallucination. The described private fix routes lightweight reports to a separate lightweight/ subdirectory and restricts formal consumers to the approved report root.
掘金 · 人工智能 · 🔥 0 - Why Financial Agents Need Domain Capabilities, Not Necessarily a New Framework
A report argues that financial Agent systems should first build domain capabilities such as correct product identities, calculation semantics, evidence chains, and authorization boundaries. Using a teaching portfolio-research scenario, it compares the roles of Pi, Claude Agent SDK, and LangGraph, while distinguishing domain capabilities, execution frameworks, and business products. It recommends starting with mature general-purpose tools and separately evaluating whether a dedicated financial framework or custom execution runtime provides enough value. The portfolio, funds, amounts, and dates in the example are instructional constructs, not actual holdings, and the report is not a cross-framework performance benchmark.
掘金 · 人工智能 · 🔥 0 - ETF Agent Maps the Agent Client Interaction Lifecycle
An ETF Agent engineering article presents an interaction framework for research-oriented Agent clients, illustrated with a fictional fund-comparison scenario. It covers scope confirmation, progressive answers, concurrent questions, source verification, failure handling, result delivery and resuming work after leaving the page. The article emphasizes visible context, user intervention, honest gaps and continuity across conversations. Its example wording and layouts are design proposals rather than evidence that every feature has been implemented, and it provides no benchmark results for the cited engineering practices.
掘金 · 人工智能 · 🔥 0 - ETF Agent Maps the RAG Evidence-Delivery Chain
An ETF Agent engineering report organizes RAG into four interacting chains: knowledge construction, online retrieval, evidence consumption and delivery, and evaluation and governance. In the checked private knowledge path, lexical retrieval can use BM25 when the PostgreSQL pg_search extension, a BM25 index, and configuration are available; otherwise it uses PostgreSQL full-text search. Code support alone does not show that any particular query used BM25. The public Open ETF Agent repository offers a smaller teaching implementation with restricted lexical retrieval, original-page readback, and source-linked reporting on synthetic documents, rather than the full private architecture. An RQ-08 evaluation fixed three source versions to one candidate set, compared the ranking of 306 real indexed chunks, and observed actual Knowledge calls. However, the chunks lacked complete manual relevance labels, and some reads confirmed only that a location was found. The results therefore do not establish improved real Recall or end-to-end financial-answer accuracy.
掘金 · 人工智能 · 🔥 0 - ETF Agent vs. General Agent Frameworks
An engineering analysis compares ETF Agent with Pi, Claude Agent SDK, and LangGraph across execution, permissions, recovery, artifact delivery, and financial research responsibilities. It does not publish a scorecard because the four systems were not tested with the same models, data windows, budgets, and question sets. Drawing on the frameworks’ official mechanisms and checked ETF Agent implementation evidence, the analysis identifies financial methods, provenance, permissions, result identity, and verifiable delivery as the system’s distinctive strengths. It argues that its custom runtime should continue to be tested against the mature alternatives rather than treated as necessary simply because it exists.
掘金 · 人工智能 · 🔥 0 - ETF Agent Skills Architecture Separates Methods from Execution
ETF Agent authors describe an architecture in which Skills define reusable research methods while models select and synthesize them, the Host controls capabilities and source authorization, deterministic programs handle calculations, and the Runtime manages budgets, execution, and recovery. The article also covers progressive loading, differing Skill visibility for Entry, Main, and Child agents, receipt-based verification, version governance, and a reproducible public v0.2 demo. The internal fund-research bundle and private-portfolio workflow remain vendor-described, while the public implementation supports only a narrower synthetic-guide example.
掘金 · 人工智能 · 🔥 0 - ETF Agent narrows agent recovery to preserve completed work instead of rebuilding execution graphs
ETF Agent's engineering article describes a narrowed recovery design for long-running research agents, splitting what had been called "recovery" into page reopening, reconstructing a Run after a service interruption, and a user-initiated continuation. Browser reconnection is now read-only and does not trigger a fresh model call, and closing the browser does not end the server-side Run. After a server crash the design allows loss of uncommitted progress while keeping committed results, and a user-started continuation inherits eligible materials but not the old Run's execution authority, leases, or budget.
掘金 · 人工智能 · 🔥 0 - Open ETF Agent v0.7 details durable control-event handoffs
A report examines how Open ETF Agent v0.7 separates reliable delivery of control events from confirmation that their intended business effects occurred. It describes the public SQLite implementation’s Claim/Fence leases, receipt reconciliation with the original Owner, unknown outcomes, cancellation, and restart recovery. The public slice covers a narrower path for a single Run and does not include the original system’s multi-Owner control-event bus. The report also cautions that not every target, production deployment, or cross-process failure has received unified end-to-end validation.
掘金 · 人工智能 · 🔥 0 - ETF Agent adds versioned custom research profiles
ETF Agent’s engineering team says users can save personal research methods as versioned profiles that run through existing general Subagents, with each research run freezing the available profile versions. The implementation includes bounded expert discovery, explicit selection, contribution tracking and authorization boundaries, but acceptance tests do not establish that real models select personal profiles correctly or improve investment research quality.
掘金 · 人工智能 · 🔥 0 - ETF Agent adds a non-enforcing Shadow Credits usage view
ETF Agent added a P0 Shadow Credits usage view that observes research activity without blocking requests or introducing payment, billing, or new quota gates. It distinguishes run request budgets, physical model attempts, and Personal Credits, while retaining unknown or partially attributed usage instead of reporting a misleading zero. The engineering team says the feature entered the main branch on October 24, 2026, but formal closure and full PostgreSQL non-interference validation remain incomplete.
掘金 · 人工智能 · 🔥 0 - When an Agent Should Keep Researching or Start Answering
This tutorial explains how an AI Agent can decide whether more research is needed, whether to answer with qualifications, or whether to stop after hitting execution limits. Using a constructed ETF share-comparison example, it covers evidence gaps, conflicting documents, bounded research, and the separation of verified facts, assumptions, calculations, and judgments. The article also notes that the example is pedagogical rather than a live fund task, while its engineering mechanisms come from the ETF Agent design.
掘金 · 人工智能 · 🔥 0 - ETF Agent Separates Daily Research Generation From Saved Readback
An engineering article describes an ETF Agent design that separates personalized daily research generation from reading saved results: read-only requests return existing results, while explicit generation requests create or retry research. The design uses a user-and-server-UTC-date key for deduplication, PostgreSQL session-level advisory locks, and a separate limited connection pool for long-held locks so they do not exhaust the pool used by normal queries. It also distinguishes states such as not generated, in progress, successful with no selected items, failed, and saved but unreadable. A source-projection fix allows a card to retrieve the sources explicitly linked to its original research without rewriting the body or rerunning the model. The article also states that the public Open ETF Agent v0.15.2 lacks the account-level daily selection, database generation lock, and scheduled-result integration described in it.
掘金 · 人工智能 · 🔥 0 - How ETF Agent Separates Identity, Authorization, and Resource Isolation
An ETF Agent engineering article explains how a multi-user Agent should distinguish authenticated identity, resource ownership, per-request authorization, targeted sharing, and browser-view isolation. It describes one Run as the authorization lifecycle for background research while emphasizing that the public Open ETF Agent v0.15.2 teaching build is local and single-user rather than a complete multi-user implementation.
掘金 · 人工智能 · 🔥 0 - Exact Numbers Do Not Equal Correct Investment Decisions
A report presents a Numeric kernel design for financial research agents that separates deterministic decimal arithmetic from domain decisions such as formula selection, input suitability and business eligibility. It uses decimal strings, explicit units and rounding policies, and returns exact, rounded and residual values to reject incompatible operations locally. All examples use synthetic inputs, and the report cautions that local numerical tests do not certify financial research quality.
掘金 · 人工智能 · 🔥 0 - ETF Agent reconnects delayed human replies to the original research run
ETF Agent authors describe a persistent Human-in-the-Loop design that separates request acceptance, response receipt, response adoption and effect commitment, with the original run recovering after a delayed reply. Their open ETF Agent v0.13.0 example persists the question, records the reply as received but not yet adopted, and requires an explicit resume so the original call consumes it. The article uses synthetic inputs and says its local implementation does not establish production reliability or that real models will ask appropriate questions.
掘金 · 人工智能 · 🔥 0 - ETF Agent adds a Tool Surface for verifying model-visible tools
ETF Agent developers consolidated business-tool definitions under MCP and introduced Model Capability Presentation and Tool Surface to verify the final logical tool list sent to a model. The new layer derives its expected tools from existing authorization facts and checks them after hooks, context processing, evidence assembly, and asynchronous preparation, while rejected dispatches are settled through the existing request owner. Controlled regression tests covered 13 counterexamples, according to the developers, but the report does not independently validate production behavior.
掘金 · 人工智能 · 🔥 0 - ETF Agent Details Runtime Reminder Coordination
The ETF Agent team described an architecture that turns changing runtime facts into timely advice for models while leaving facts, execution authority, and delivery to their existing modules. The design separates persistent status from repeated action suggestions, deduplicates reminders by type, and records delivery only when a reminder actually enters the submitted model request. The team says these paths have been validated in a controlled setting, but its effect on real research performance remains unobserved.
掘金 · 人工智能 · 🔥 0 - ETF Agent adds a Workspace for long-term, cross-run research
The ETF Agent author describes a Research Workspace that organizes long-term goals and links prior Runs, Publications, evidence versions, permissions, and research progress without replacing the existing execution engine. Its P0 implementation has been merged into the private codebase, where controlled tests used synthetic sources and scripted model responses to consume exact historical Publication versions across independent Runs. The feature remains disabled by default, full type checking and formal acceptance are unfinished, and the public Open ETF Agent repository does not include this complete module.
掘金 · 人工智能 · 🔥 0 - ETF Agent details isolated-context Subagent collaboration design
ETF Agent uses one Child execution mechanism for general research tasks, built-in Web, PDF and Python roles, six investment-research methods, account-specific profiles, a Research Reviewer and bounded Bull/Bear challenges. Its architecture isolates local work from the Main agent while preserving source permissions and final-answer ownership, and the report documents failures involving dropped source material, unidentified messages and interrupted execution. The article presents these as engineering behaviors, while stating that improved investment outcomes from adding specialists still require controlled validation.
掘金 · 人工智能 · 🔥 0 - A Task-Level Framework for Evaluating AI Agents
The ETF Agent evaluation framework argues that a green test only confirms that a check passed under defined conditions, not that the user’s task was completed. It recommends separating runtime behavior, evidence retrieval, content judgment and user outcomes, while preserving failed, inconclusive and corrected observations so model and system quality can be compared on a valid denominator. The article combines practical guidance on RAG, traces, model judges, sub-agent contributions and cost with historical examples from its own development process.
掘金 · 人工智能 · 🔥 0 - Financial agent architecture separates research from permissions and execution
A Juejin AI article proposes a financial-agent architecture that keeps model-led research distinct from data retrieval, deterministic computation, access controls, human review, and business execution. It uses a synthetic fund-portfolio case to show how portfolio questions can progress from public research to account access and proposed operations, while preserving share class, reporting period, comparability, calculation context, and risk concerns. The article says ETF Agent's current conversational research layer does not trade directly; orders, settlement, and institutional approvals are target divisions for future business-system integration.
掘金 · 人工智能 · 🔥 0 - ETF Agent’s Six-Layer Request-Processing Map
A technical overview describes ETF Agent’s request flow through six conceptual layers: task input and triggering; identity, session and context; Agent decisions and execution; tools and domain capabilities; result publication and delivery; and the user interface. The report says these layers form a reading map rather than six processes or a fixed pipeline, and that modules can participate across layers without transferring responsibility for permissions, facts or outcomes. Direct responses and background research share underlying capabilities but may take different paths. The portfolio-analysis example is instructional and is not an investment conclusion or live performance result. Implementation status and validation remain subject to each module’s specifications and acceptance records.
掘金 · 人工智能 · 🔥 0 - A Practical Guide to AI Agent Context Governance
The article presents a practical workflow for governing context in AI agents: before each model call, build a current working view from the effective task, permitted materials, and actual execution records. It separates stable system guidance from dynamic task materials and covers memory admission, versioned tool results and coverage, user corrections, persistence receipts, work progress, and optional context compression or subagents. Its ETF fund-research scenarios, aliases, and code examples are explicitly instructional rather than production interfaces or records of an actual run.
掘金 · 人工智能 · 🔥 0 - A Goal-Oriented Framework for AI Agent Context Governance
The article synthesizes Anthropic’s context-engineering guidance into a framework for organizing AI-agent context around goals, evidence, permissions, memory, exploration, and progress. Using a synthetic fund-comparison scenario, it argues that context should preserve source boundaries and support the next useful judgment rather than simply expand the context window. It also distinguishes model judgments from actual tool execution records and describes memory operations including writing, recall, correction, expiry, and forgetting.
掘金 · 人工智能 · 🔥 0 - Architecture for Persistent, Long-Running AI Research Agents
The article argues that long-running research requires more than larger contexts or longer timeouts: systems must separately manage the user task, each execution Run, working context, and saved research artifacts. It recommends preserving evolving judgments and execution receipts, delivering staged results, recovering interrupted Runs without duplicating effects, and treating explicit continuation as a new Run linked to its parent. A synthetic fund-comparison scenario illustrates these design patterns but does not constitute a completed investment study or verified trading capability.
掘金 · 人工智能 · 🔥 0
Experience and discussion from the community
Share my ETF Agent experienceAsk about ETF Agent
Nobody has shared their experience with ETF Agent yet.