What my AI inbox-screener actually does to the templated cold outreach hitting my inbox. Three real auto-sends, the footer that draws the line, and where this goes next.
I shipped a partnerships page. This is the why-now: capacity, an inbox auto-classifier I haven't built yet, and the years of compounding work that made it the right moment to tie it together.
How real estate developers use WisprFlow to dictate project reports, investor communications, and property analysis while managing complex development timelines.
How mortgage brokers use WisprFlow to dictate loan files, document borrower communications, and streamline mortgage processing with voice-driven efficiency.
How mobile developers use WisprFlow to write React Native, Swift, and Kotlin code by voice - debugging on device, API integration, and mobile-specific development workflows.
How immigration attorneys use WisprFlow to dictate case notes, client narratives, and legal briefs while managing high-volume caseloads and multilingual documentation needs.
How CPAs use WisprFlow to dictate tax returns, client consultations, and financial analysis while maintaining accuracy in complex accounting workflows.
How content marketing managers use WisprFlow to dictate blog posts, social media content, and marketing campaigns while managing editorial calendars and team coordination.
How auditors use WisprFlow to dictate findings, document controls testing, and prepare audit reports while maintaining accuracy in complex financial examinations.
Detailed comparison of Granola and Zoom AI Companion for meeting transcription, intelligence, and workflow integration - features, accuracy, and pricing analysis.
How UX researchers use Granola's AI to capture user interviews, analyze behavior patterns, and transform qualitative research with intelligent conversation analysis.
How software consultants use Granola's AI to capture client requirements, track project decisions, and document technical discussions for better delivery outcomes.
How patent attorneys use Granola's AI to record inventor interviews, track technical details, and streamline patent prosecution with intelligent meeting transcription.
How mobile development teams use Granola's AI to capture sprint planning, technical discussions, and stakeholder meetings for better app development coordination.
How life coaches use Granola's AI to track client breakthroughs, document coaching conversations, and build comprehensive client progress records with automated session intelligence.
How insurance agents use Granola's AI to track client needs assessments, document policy discussions, and streamline insurance sales with intelligent conversation capture.
How bankruptcy attorneys use Granola's AI to track creditor meetings, document client finances, and streamline debt relief proceedings with automated meeting intelligence.
Mortgage brokers manage complex pipelines with detailed documentation requirements. WisprFlow's voice dictation cuts loan file documentation time so brokers can close more loans per month.
Life coaches need to capture breakthroughs, commitments, and patterns from client sessions. WisprFlow lets you dictate session notes at 180 WPM immediately after each call while it's fresh.
Insurance agents spend 40% of their day on documentation. WisprFlow's AI voice transcription at 180 WPM cuts that in half, letting agents spend more time selling and serving clients.
Tax preparers handle hundreds of client files during season. WisprFlow's 180 WPM voice dictation cuts documentation time by 60% so you can take more clients without burning out.
Property managers handle maintenance requests, lease renewals, and tenant issues across dozens of units. WisprFlow turns site visits and phone calls into documented records instantly.
Event planners juggle dozens of vendor calls, client revisions, and logistics updates daily. WisprFlow turns voice into documentation instantly so nothing gets lost in the chaos.
UX researchers run user interviews, usability tests, and synthesis sessions where nuanced observations matter. Granola captures the verbatim moments that define product decisions.
Mobile developers move fast across sprint planning, App Store reviews, and crash triage calls. Granola keeps every decision documented so nothing falls through the cracks.
Software engineers sit in design reviews, incident retrospectives, and planning sessions where technical accuracy matters. Granola documents the details so you can focus on problem-solving.
In-house counsel sits in contract negotiations, compliance reviews, and board meetings where every word matters. Granola captures the full discussion so counsel can focus on advising, not transcribing.
Actuaries spend hours in model validation meetings, reserve reviews, and regulatory discussions. Granola captures technical detail accurately so you can focus on the analysis, not note-taking.
Academic researchers need accurate documentation of lab meetings, grant planning calls, and conference discussions. Granola captures the technical detail that handwritten notes miss.
After weeks of frustration, I cracked zero-lag Steam Link streaming to Apple Vision Pro. Here's the exact setup that works — and all the wrong turns I took getting there.
UX researchers spend hours converting interview insights into actionable research reports. WisprFlow's voice dictation at 150+ WPM turns real-time observations into polished findings, turning research documentation from a bottleneck into a flow state.
Nonprofit staff are stretched thin across program delivery and administrative demands. WisprFlow's voice-to-text turns verbal notes into grant narrative drafts, program reports, and donor communications at 150+ WPM, cutting documentation time in half.
I consistently hit 184 words per minute with WisprFlow. Here's what that actually means in terms of output, time saved, and what you can do with a brain that's no longer bottlenecked by typing speed.
Clergy balance sermon writing, pastoral care visits, congregational administration, and personal reflection. WisprFlow's voice dictation turns sermon thoughts into drafted messages, visits into documented care records, and reflective insights into organized notes at 150+ WPM.
Hermes was producing shallow responses. Instead of debugging from the inside, I opened Claude Code, SSH'd into the EC2 instance, found the throttled context window, fixed it, and restarted the gateway. Hermes woke up improved — without knowing it happened.
Supply chain management involves constant coordination across vendors, carriers, warehouse teams, and procurement. Granola captures every vendor negotiation, logistics coordination call, and demand planning meeting so nothing gets lost in translation.
Photographers build their business on understanding what clients actually want. Granola captures every consultation call, creative brief review, and post-shoot debrief so the vision that was agreed to is the vision that gets delivered.
Mobile developers juggle App Store review cycles, OS version fragmentation, and cross-functional stakeholder pressure. Granola captures every sprint planning session, store review debrief, and release coordination call so critical details don't get dropped.
Insurance agents manage complex client needs across commercial, personal, and specialty lines. Granola captures every needs analysis call, underwriting discussion, and renewal negotiation so coverage gaps never slip through.
Hotels, restaurants, and event venues run on precise coordination across dozens of staff and vendors. Granola captures every pre-shift briefing, vendor coordination call, and event planning meeting so nothing falls through the cracks.
Fitness coaches spend hours documenting client assessments, program design discussions, and check-in calls. Granola captures every conversation automatically so coaches can focus on coaching instead of note-taking.
Court reporters spend more time coordinating depositions than actually transcribing them. Granola captures every scheduling call, scope negotiation, and agency coordination meeting so the administrative side of the practice runs as precisely as the professional side.
A technical guide to WisprFlow for developers — what model powers it, how the API works, and practical ways to integrate voice AI into your coding workflow.
How to use Firecrawl to scrape and preprocess web content for retrieval-augmented generation pipelines — from single-page extraction to full-site crawling with structured data output.
A practical guide to the Firecrawl API — authentication, endpoints, rate limits, pricing, and how to integrate Firecrawl into your web scraping and data extraction workflows.
How WisprFlow's voice AI helps registered dietitians and nutritionists create meal plans, document client assessments, and track dietary progress at 180+ WPM through voice dictation.
How WisprFlow's voice AI accelerates mortgage processing with voice-driven application documentation, client status updates at 180+ WPM, and hands-free loan file management across lending platforms.
How WisprFlow's voice AI transforms life coaching practice with voice journaling, client goal documentation at 180+ WPM, and session note dictation that frees coaches to focus on client transformation.
How WisprFlow's voice AI helps insurance agents process claims faster, draft client communications at 180+ WPM, and document policy details through voice dictation across any insurance platform.
How WisprFlow's voice AI transforms hotel and restaurant management with hands-free operations documentation, guest feedback capture at 180+ WPM, and voice-driven staff communications.
How WisprFlow's voice AI transforms academic research workflows with voice-driven literature review, data analysis dictation, and paper writing at 180+ WPM for researchers and PhD students.
14 years of typing gave me RSI and crane neck. Now I ship code by voice while walking 5-8 miles a day. Here's the full voice-first stack: WisprFlow, Claude Code, and the tools that replaced my keyboard.
Between a full-time job at WorkOS and solo-parenting two toddlers with zero screen time, I published 14,790 words across 9 posts in two days. 47 images, 12 PRs. The secret: chatops with two AI agents I drive in compressed windows.
How Granola's AI meeting assistant helps supply chain managers capture vendor negotiations, logistics planning sessions, and cross-functional coordination meetings with automatic documentation and follow-up tracking.
How Granola's AI meeting assistant helps clergy capture pastoral counseling sessions, organize sermon research meetings, and document congregational planning with automatic transcription and follow-up tracking.
How Granola's AI meeting assistant helps photographers capture client consultation details, document creative briefs, and organize shoot planning sessions with automatic transcription and action items.
How Granola's AI meeting assistant helps mobile development teams capture sprint planning, user research sessions, and app store strategy meetings with automatic transcription and action item extraction.
How Granola's AI meeting assistant transforms fitness coaching with automatic client session transcription, progress tracking documentation, and workout plan generation from consultation recordings.
An interactive primer on the ADHD engineering brain — a 3D brain you can put through hyperfocus and crash, a simulator for what reading feels like under intrusive thoughts and notification overload, and the AI scaffolding I use to work around all of it.
VCs building internal data tools and portfolio tracking systems can ship faster with voice coding. WisprFlow at 179 WPM makes the difference between a weekend project and a week-long slog.
UX researchers who can code prototypes ship insights faster. WisprFlow lets you build React components, write analysis scripts, and document findings at speaking speed.
Supply chain analysts and ops engineers building inventory tracking, demand forecasting, and logistics systems can ship tools faster with voice coding. Here's how WisprFlow fits the workflow.
Photographers who can build their own portfolio sites and client galleries have a business edge. WisprFlow makes building these systems fast enough that it's worth doing yourself.
Nonprofit staff wearing five hats need to build donor management tools and draft grant applications without a full engineering team. WisprFlow makes it possible.
Solving the 'silent files' problem: how I built an event-driven bridge between Claude Code on my Mac and the Hermes agent running on EC2, using SSM RunCommand, Tailscale, and HMAC-signed webhooks.
I run two AI agents — Claude Code for infrastructure, Hermes for content — both controlled from my phone. Here's the split-brain architecture and why separation of concerns matters for AI agents too.
I gave a keynote about walking in the woods with AI. Then I stopped needing the laptop entirely. Now I direct AWS infrastructure and content agents from my phone on the trail.
My AI assistant Hermes writes MDX content, generates hero images, uploads to Bunny CDN, commits to git, opens pull requests, and merges — all from a Discord conversation.
Nutritionists and dietitians take detailed client histories, discuss complex protocols, and track behavior patterns over time. Granola captures the clinical nuance that typed notes miss.
Hotel managers and restaurant operators run constant coordination meetings across departments. Granola captures every action item and staff commitment so service doesn't fall apart between shifts.
Court reporters increasingly work depositions, arbitrations, and business meetings. Granola's AI transcription handles the prep meetings, client calls, and coordination work that surrounds the formal record.
YouTubers and podcasters juggle sponsors, guests, and production teams across dozens of meetings. Granola captures every commitment so nothing falls through the cracks.
Research collaboration meetings generate ideas that shape papers, proposals, and careers. Granola captures the technical nuance from lab meetings, grant calls, and conference discussions that would otherwise disappear.
Practical lessons from running hands-on technical workshops at AI Engineer World Fair SF, AI Engineering London, and beyond. What works, what doesn't, and why most conference workshops suck.
I gave a talk at AI Engineering London about staying healthy, creative, and shipping while working with AI coding agents. The core idea: the agents scale infinitely, but your nervous system doesn't. Here's the full recap.
Nick Nisi and I ran an 80-minute hands-on workshop at AI Engineering London on building Claude Code skills that are portable, executable, and composable. We taught constraints over instructions, evidence over guesses, and measurement over vibes.
I sat down with Jack Bridger on the Scaling Devtools podcast at AI Engineering London to talk about how WorkOS builds with AI coding agents, the patterns behind portable skills, and where developer tooling is heading.
