Skip to content

Black Friday: up to 61% off our packs until November 30.

See the packs

Blog

Blog & Insights

Practical articles on building and running AI products, agents and workflows.

All articles

    • AI Tools & Tricks

    Wispr Flow Dictionary: Fix Names and Use Spoken Snippets

    A recurring name, a persistent misspelling, and a reusable reply need different fixes. This documentation-based desktop guide explains when to add a Wispr Flow dictionary word, create an explicit correction, or save a spoken snippet, with checks you can run before relying on the inserted text.

    • AI Tools & Tricks

    Kagi Search Lenses: Scope Sources, Then Check the Evidence

    Kagi lenses, personalized website rankings, and query filters solve different research problems. This documentation-based guide shows how to build a small source boundary, search beyond it, check Quick Answer citations, and share a lens without implying that imported copies stay synchronized.

    • AI Tools & Tricks

    Granola Meeting Notes: Confirm Actions Before You Share

    A clear meeting summary is not the same as an accepted commitment. Use this documentation-based Granola review guide to inspect evidence, confirm owners and timing, and choose the right information to share.

    • AI Tools & Tricks

    Basis Conversations 1500: A Same-Clock Map for Turn-Taking Evaluation

    Basis Conversations 1500 is useful for turn-taking evaluation because it keeps participant audio on a shared clock and separates transcripts, machine labels, human moments, and votes. This walkthrough shows how to build leakage-aware evaluation windows without treating noisy ASR, provisional labels, or unreviewed overlaps as gold.

    • AI Tools & Tricks

    Vaani Noise Event Timestamp Dataset: A Practical Speech Evaluation Map

    Vaani's noise-event annotations offer a starting point for evaluating speech interfaces under real co-occurring noise. This practical map separates annotation tiers, explains conflicting inventory figures, and shows how to design matched, language-aware tests without overstating what timestamps prove.

    • AI Tools & Tricks

    Gemini Omni 1.1 Flash Video Continuity Test: A Production VCAT for AI Video Workflows

    Gemini Omni 1.1 Flash adds a broader control surface for generative video, including scene extension, first and last frame interpolation, reference-guided edits, and 4K upscaling. The production question is not whether one demo looks impressive, but whether a workflow can preserve continuity, control, safety, and delivery evidence repeatably.

    • AI Tools & Tricks

    Apple M6 Mac mini Local AI Workload Qualification Test: Benchmark Before You Buy

    The new Apple M6 Mac mini looks attractive for private local AI, but compact hardware should be qualified against real workloads before procurement. This LAWQT guide gives teams a repeatable way to test local inference, retrieval, transcription, vision, and batch automation without relying on launch excitement.

Next step

Have something to build?

Tell us what you need. We reply with a clear scope and a fixed quote.