· 4 min read
Model Selection in 2025: When Smaller Beats Frontier
A practical framework for routing tasks to small, fast models or frontier reasoning models based on latency, cost, and failure cost.
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#search#security#spreadsheets#startups#storage#tamaton#unified-workspace#workflow#workflows
· 4 min read
The Hidden Cost of Context Windows in Agent Workflows
A quantitative look at how context window limits quietly degrade agent performance on email threading and document synthesis—and what to do about it.
· 4 min read
How to Choose an LLM for Each Task, Not Just the Best One
Stop defaulting to the largest frontier model. Use a cost-latency-quality matrix to route each task to the right LLM and cut spend without hurting output.
· 5 min read
How to Evaluate an AI Inbox Assistant Before You Trust It
A concrete eval rubric for email AI — measuring intent precision, action safety, and hallucinated commitments — plus test cases you can run today.
· 5 min read
The Quiet Shift to Smaller, Specialized Models in 2025
Frontier models aren't always the answer. For inbox and search work, routing to small fine-tuned models is quietly becoming the default architecture.
· 4 min read
Spreadsheets as Agent Workspaces: Beyond the Formula Bar
Why the humble spreadsheet is one of the best environments for AI agents to read, write, and verify data — and why grounded tabular reasoning beats free-text prompting.
· 4 min read
How to Evaluate an AI Agent Before You Trust It With Your Inbox
A concrete eval methodology for action-taking agents: measure task success, failure recovery, and over-action risk before you hand over the keys.
· 4 min read
The Inbox Is the Best Agent Interface We Already Have
Email's threads, recipients, and async replies aren't legacy baggage — they're a proven control surface for AI agents. Here's why the inbox is great agent interface design.
· 4 min read
Designing Memory for AI Agents: What Actually Works
Memory isn't one feature. A practical breakdown of episodic, semantic, and working memory for AI agents — and how to wire them into real workflows.
· 4 min read
Why AI Struggles With Spreadsheets — and How to Fix It
LLMs reason poorly over raw grids because cells lose their meaning. Here's why ai spreadsheet analysis breaks down — and how structure fixes it.
· 5 min read
How AI Agents Should Read Your Calendar
A practical guide to what AI scheduling agents actually need — timezone handling, conflict resolution, and intent inference — and where today's automations break.
· 4 min read
Building a Custom Inbox Triage Agent in Tamaton
A step-by-step guide to building a custom email agent that reads, labels, drafts replies, and schedules follow-ups using Tamaton's unified context.
Page 1 of 6Older →
Get started
Reserve your @tamaton.ai email
Claim your address before someone else does — free to start, with an AI-native inbox built in.