· 5 min read
Your Inbox Is a Retrieval Problem, Not a Sorting Problem
Folders and filters were a workaround for bad search. In an AI-native stack, your inbox is a messy index — and treating it that way changes triage, search, and follow-up.
Blog
From the Tamaton team
Practical writing on productivity, AI, and building software.
All#ai#ai-agents#ai-productivity#applied-ai#automation#calendar#context-switching#deep-work#documents#email#engineering#engineering-leadership#invisible-ai#knowledge-work#llm-evaluation#product-updates#productivity#prompt-engineering#remote-work#search#security#spreadsheets#startups#storage#tamaton#unified-workspace#workflow#workflows
· 4 min read
Confident, Wrong, and in Your Spreadsheet
A hallucinated sentence is awkward. A hallucinated formula is expensive. Here's a taxonomy of where generative AI fails in structured work — and the guardrails that catch each type.
· 5 min read
LLMs as Research Instruments: What the Skeptics Get Right
Public policy researchers are arguing about whether LLM-assisted coding counts as method. Their objections — bias, reproducibility, opaque provenance — apply to your Tuesday afternoon analysis too.
· 5 min read
Bound the Blast Radius: Scoping Custom Agents in Tamaton
An agent with access to every email, doc, and file is a liability until you scope it. Here's how to define, test, and audit custom agent permissions in Tamaton.
· 4 min read
Give Your Agents an Identity, Not a Borrowed Password
Shared service accounts and copied human credentials make AI agents untraceable and over-privileged. Here's what agent-native identity looks like in a real productivity stack.
· 4 min read
How to Actually Evaluate an LLM Feature Before You Ship It
A practical eval playbook — golden sets, LLM-as-judge with guardrails, and regression tracking — for teams shipping AI, not writing papers.
· 5 min read
The GenAI Paradox: Faster Output, Weaker Recall
New research suggests generative AI speeds work up while quietly reducing what people actually learn. Here's how to restructure AI-assisted work so speed doesn't cost you understanding.
· 5 min read
Package Hallucinations and Other Ways Agents Invent Reality
A field guide to grounding failures — fabricated npm packages, invented spreadsheet columns, phantom calendar events — and the design patterns that catch them before they ship.
· 5 min read
RAG Is Not a Search Bar: Retrieval for Real Knowledge Work
Demo RAG retrieves from one clean corpus. Real work means retrieving across email, docs, spreadsheets, and calendar — where context is stale, duplicated, and contradictory.
· 5 min read
The Least-Privilege Agent: How to Scope What Bots Can Touch
A practical permissions model for AI agents where every action — reading email, editing a doc, calling an API — is a privilege that must be earned, not assumed.
· 5 min read
Agent Identity: The Access Problem Nobody Budgeted For
AI agents can already do the work. The bottleneck is authorization — and most teams are quietly lending agents a human's credentials and hoping for the best.
· 5 min read
Memory Is Not a Feature, It's a Retrieval Problem
Assistants don't fail at memory because models forget. They fail because memory gets stored as a text blob instead of a governed store with recency, decay, provenance and conflict rules.
Get started
Reserve your @tamaton.ai email
Claim your address before someone else does — free to start, with an AI-native inbox built in.