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

博客园 - 三生石上(FineUI控件)
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
月光博客
月光博客
博客园 - 【当耐特】
Hugging Face - Blog
Hugging Face - Blog
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
爱范儿
爱范儿
大猫的无限游戏
大猫的无限游戏
S
SegmentFault 最新的问题
博客园_首页
雷峰网
雷峰网
量子位
有赞技术团队
有赞技术团队
博客园 - 叶小钗
博客园 - 聂微东
V
V2EX
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 司徒正美
小众软件
小众软件
The Cloudflare Blog
阮一峰的网络日志
阮一峰的网络日志
Apple Machine Learning Research
Apple Machine Learning Research
Jina AI
Jina AI
人人都是产品经理
人人都是产品经理

Show HN

The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph
The research pipeline builder for analysts
Sharanxxxx · 2026-06-22 · via 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.