惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

aimingoo的专栏
aimingoo的专栏
宝玉的分享
宝玉的分享
博客园 - 【当耐特】
博客园 - 司徒正美
L
LangChain Blog
有赞技术团队
有赞技术团队
大猫的无限游戏
大猫的无限游戏
Stack Overflow Blog
Stack Overflow Blog
Engineering at Meta
Engineering at Meta
U
Unit 42
Microsoft Azure Blog
Microsoft Azure Blog
I
InfoQ
博客园 - 叶小钗
H
Hackread – Cybersecurity News, Data Breaches, AI and More
J
Java Code Geeks
月光博客
月光博客
量子位
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
博客园_首页
Last Week in AI
Last Week in AI
人人都是产品经理
人人都是产品经理
Google DeepMind News
Google DeepMind News
云风的 BLOG
云风的 BLOG
D
DataBreaches.Net

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
The research pipeline builder for analysts
Sharanxxxx · 2026-06-22 · via Hacker News: Show HN

Your research.
Dots connected.

Cutonce turns your investment process into automated research pipelines. Use AI to understand financial reports, gather insights from earnings calls, extract sentiment, and surface signals. Your strategy, our engine.

Built for boutique RIAs, quantitative architects, and independent analysts.

A quick tour of the canvas, a live run, and results landing in your email.

No code

build pipelines visually

Minutes

to your first scheduled run

500

free credits to start, no card

How it works

From thesis to shortlist, on repeat

Set up your research once. It runs on a schedule and delivers the answer, so you get your time back.

01

Connect your universe and data

Start from a preset universe (S&P 500, NASDAQ 100, sector indices) or your own ticker list. Cutonce already holds the SEC filings, earnings transcripts, and fundamentals.

02

Define the logic on a canvas

Chain filter, score, AI, and compare nodes to encode your thesis. No code - but every condition is explicit and yours to tune.

03

Schedule it and ship the results

Run on demand or every morning. Output to Google Sheets, Drive, email, Slack, or a webhook. Each run is logged and reproducible.

Find opportunities before they're priced in

Cross-reference earnings calls, 10-Ks, filings, and fundamentals across your entire universe in one pass. Surface what others miss while it still matters.

Structure your strategy, not someone else's

Build your research logic on a visual canvas. Define rules, weight signals, and see exactly how your thesis turns into a ranked shortlist. You direct; the engine executes.

app.cutonce.ai/canvas

ScheduleRun

10x yourself, overnight

Deploy pipelines that run on a schedule. Work that took a team a week runs while you sleep - and lands in your inbox before the open.

Run audit logREPRODUCIBLE

07:00:01Pipeline triggeredschedulera3f9c2

07:00:03SEC EDGAR fetchdatab17de4

07:00:09AI inference runaic82ab1

07:00:11Score computedscored44ef7

07:00:12Output writtenoutpute91cc3

YouTube to pipeline

Turn any video into a running strategy

Paste a link to an earnings call, an analyst breakdown, or a strategy video. Cutonce reads the full transcript, extracts the thesis and signals, and assembles them into a pipeline you can edit, schedule, and ship.

  • Works on earnings calls, interviews, and strategy breakdowns
  • Pulls out the thesis, universe, tickers, and signals automatically
  • Every generated node is yours to edit and tune
  • Schedule it to re-run as new videos drop

Try it on a video

youtube.com/watch?v=quality-investing-playbookAnalyze

Extracted from a 38-min video

StrategyBuy quality compounders on dips

UniverseS&P 500

SignalsROIC > 15%, FCF growth, 10%+ drawdown

Generated pipeline

S&P 500

ROIC > 15%

FCF growth

Email

Data

The data layer is already wired

Cutonce ingests the filings, transcripts, and fundamentals centrally, so your pipelines run on fresh data without you maintaining a single API key.

SEC EDGAR filingsEarnings call transcriptsFundamentals & ratiosTechnical indicatorsMarket & company newsInsider trades (Form 4)FRED economic dataAnalyst consensus

Outputs

Results where you already work

Google Sheets & Drive

Append or overwrite a tab, or drop a CSV/Excel into a folder.

Email

An HTML report or CSV in your inbox the moment a run finishes.

Slack

A formatted message to any channel via incoming webhook.

Webhooks

POST results to your own systems with custom headers.

Trust

Defensible by design

Cutonce keeps the analyst in control: every decision the pipeline makes is yours, written down, and repeatable.

  • Every run produces a reproducible audit log: trigger, data fetch, inference, score, output.
  • Your logic is explicit and inspectable. No black-box recommendations, no hidden model.
  • Data sourced from public SEC EDGAR and FRED, verifiable at the source.
  • Results are yours: export to Sheets, Drive, or your own systems, nothing locked in.

Run audit logREPRODUCIBLE

07:00:01Pipeline triggeredschedulera3f9c2

07:00:03SEC EDGAR fetchdatab17de4

07:00:09AI inference runaic82ab1

07:00:11Score computedscored44ef7

07:00:12Output writtenoutpute91cc3

No. Pipelines are built by chaining nodes on a visual canvas. Every filter and score is explicit, but you never touch code. If you can describe your strategy, you can build it.

Your strategy, our engine.

Your research deserves better than manual reading and rigid screeners. Start free - no card required.