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

V
V2EX
aimingoo的专栏
aimingoo的专栏
S
SegmentFault 最新的问题
博客园_首页
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
IT之家
IT之家
博客园 - 【当耐特】
月光博客
月光博客
C
Check Point Blog
T
The Blog of Author Tim Ferriss
罗磊的独立博客
博客园 - Franky
MongoDB | Blog
MongoDB | Blog
H
Help Net Security
Microsoft Security Blog
Microsoft Security Blog
B
Blog
阮一峰的网络日志
阮一峰的网络日志
腾讯CDC
美团技术团队
N
Netflix TechBlog - Medium
Stack Overflow Blog
Stack Overflow Blog
Y
Y Combinator Blog
L
LangChain Blog
The Cloudflare Blog

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
Dodger | The intelligence layer for product
Dodger AI, Inc. · 2026-06-25 · via Hacker News: Show HN

New · Linear, Slack & MCP integrations

The product development engine, end to end.

Dodger runs every stage of product development — from research and user stories to design and testing — grounded in your real product data.

Most teams still decide what to build like it’s 2015.

Weekly roadmap sync 11:00

The meeting where the loudest voice wins.

product

Users are asking for this 🙏

— it was one user.

roadmap.csv Confidence

A roadmap nobody in the room fully believes.
“strategy”
A gut call wearing a strategy costume.

Then you spend three weeks of suddenly-cheap engineering building it — and it lands with a thud.

You didn’t get faster. You got faster at being wrong.

Everything you have, into one clear plan.

Point Dodger at what you already have: your docs, your roadmap, your designs, your data. It reads all of it and hands back specific, ranked direction: what to build, what to skip, and why.

Support tickets PRD & docs Linear issues Figma frames PostHog

What to build first Build-ready spec What to skip Risks to watch

Your synthetic users test it. Before and after it ships.

Dodger puts synthetic users on your actual screens and watches how they react — catching friction before you ship, and the reasons people leave after.

Talk to your users.
Anytime.

Interview synthetic users grounded in your real data. They tell you what to build before you ship, and what's broken after.

  • Grounded in your research, not generic personas
  • Pulls live context from PostHog, Granola, Figma & more
  • Pushes back on your assumptions in real time

M Maya Torres Working parent · 34 · Decision fatigue Available now

What's the first thing you'd want when you open the app?

Honestly? Just tell me what to cook tonight with what I already have. By 5pm I've made 200 decisions and I want one made for me.

Ask Maya anything…

Built to live where decisions actually get made.

M Maya TorresWorking parent · 34 Live · 02:14

“Just tell me what to cook tonight with what I already have.”

Hold to talk Interrupt

Voice interviews

Don’t type — talk. Run a discovery session out loud with any synthetic user, the way you would a real one, and let them interrupt and push back in real time.

It doesn’t ask you to trust it. It shows its work.

Anyone can generate a confident answer. Dodger gives you a decision you can audit — pull any recommendation and walk it all the way back to the source it came from.

It works where you do.

No new dashboard to check. Dodger plugs into the tools your team already uses every day.

Cycle 24Reprioritized

Ten-second mobile loggingHigh impact

Offline capture & syncBuild

Full dashboard rebuildNo signal

+

Keep the roadmap honest.

Every cycle, Dodger weighs what's queued in Linear against real user signal, promoting the work that moves the needle and flagging the tickets nobody actually asked for.

+

Test designs before you build them.

Wireframes land in Figma, synthetic users run the real flows, and the friction points come back as comments, so you fix them before a single component ships.

+ +

Ship straight from spec to code.

Hand the validated spec to your editor of choice: user stories, acceptance criteria, and the research behind every decision, ready to build the moment you are.

dodger.mdValidated

User story

As a field rep, I can log a call in under 10 seconds, one-handed.

Capture works offline and syncs later

Primary action reachable with one thumb

Ready for CursorClaude CodeCodex

Simple, predictable pricing.

Every plan runs the full pipeline — research, definition, and validation. Pick the one that fits how much you ship.

Free Try the full pipeline once, free.

$0/ month

No credit card required. Sign up

What's included 1 run / month 1 project, up to 3 personas 250 credits / month Personas, interviews & ranked insights Recommendations & a wireframe starting point

Starter For solo builders shipping their first product.

$99/ month

Billed monthly. Cancel anytime. Sign up

What's included 10 runs / month 10 projects, up to 6 personas each Personas, interviews & ranked insights Wireframes & design research Chat refinement & iterations Shareable links & Markdown export

Most popular Pro For teams shipping every week.

$249/ month

Per workspace. Unlimited seats. Sign up

Everything in Starter, plus 30 runs / month 30 projects, up to 12 personas each Usability simulation & scoring PDF, MCP & clipboard export Slack, Linear & PostHog integrations Priority processing, faster runs

Pro+ For heavy use, with no limits.

$499/ month

Per workspace. Unlimited seats. Sign up

Everything in Pro, plus Unlimited runs / month 20,000 credits / month Unlimited wireframe iterations Highest-priority processing

Team Seats, roles, and pooled credits for your whole team — one shared workspace, one invoice. From 3 seats.

Book a demo

Enterprise SSO / SAML, audit logs, DPA, custom volume, and dedicated support with SLAs.

Book a demo

Frequently asked questions

The questions teams actually ask before switching to Dodger. Can’t find yours? Get in touch or book a demo.

How is Dodger different from tools like Dovetail, Productboard, or Pendo?

Those tools organize inputs — Dovetail organizes research, Productboard organizes roadmaps. Dodger answers the question they leave open: what to build next. It reads from your research, analytics, and roadmap tools as inputs, then produces the decision itself — backed by evidence, with a spec, a design starting point, and an engineering breakdown.

How accurate are Dodger’s recommendations?

Every recommendation traces back to its sources — the interview quotes, analytics, tickets, and calls behind it — and carries an honest confidence label: strong signal, worth testing, or early hypothesis. You’re never asked to trust a black box; you see the evidence and decide for yourself. If one’s off, you stay in control: dig into the sources, adjust the scope, or re-run a stage.

Does Dodger replace my PM team?

No — it removes the synthesis grind PMs dread: reading dashboards, tagging interview clips, rewriting the same status doc every week. That frees them for the work that actually moves the product — customer relationships, judgment calls, and cross-functional alignment. Teams adopt Dodger to ship faster with the headcount they already have.

What tools does Dodger integrate with?

Granola (meeting notes), Linear (two-way issue sync), Slack (insights & digests), and PostHog (persona calibration) are live today. Rolling out next: Pylon (support tickets), Jira, Notion, GitHub, and webhooks. Dodger is also a remote MCP server, so coding agents like Claude Code, Cursor, and Codex can pull your stories, personas, and wireframes directly. See the full list on the integrations page.

Does Dodger use my data to train models?

No. Your data is never used to train Dodger’s models or any third-party model. It’s processed only to produce output for your own workspace — stored in the US on AWS via Supabase, scoped to your workspace and never shared across customers — and our AI provider handles it under a no-training agreement.

Is there a free trial?

There’s no separate time-boxed trial — the Free plan is the trial. It runs the full pipeline end-to-end, no credit card required, so you can see real output before you ever pay. Upgrade to Starter, Pro, or Pro+ whenever you’re ready.