· 4 min read
The Agent Reliability Gap: Why 90% Isn't Good Enough
Multi-step agents compound their error rate — a 95%-accurate step becomes a coin flip after 15 actions. Here's the math and how to design around it.
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
How to Evaluate an AI Feature When 'It Feels Better'
A practical eval playbook for AI-assisted knowledge work: build golden sets, run LLM-as-judge checks, and catch regressions without a research team.
· 4 min read
One Agent or Many? A Sober Take on Multi-Agent Hype
Multi-agent systems are trending, but most productivity work is better served by one well-scoped agent with good tools. Here's when orchestration actually earns its keep.
· 4 min read
HalluSquatting: When Your Coding Agent Trusts a Fake Repo
Hallucinated package names are becoming a real supply-chain attack. Here's how HalluSquatting works against AI coding agents — and how to defend against it.
· 4 min read
How Tamaton Grounds Agent Actions in Your Real Data
A concrete look at how shared context across inbox, docs, sheets, and calendar gives AI agents verifiable grounding — and fewer confidently wrong actions.
· 4 min read
Can LLMs Predict Human Behavior? What the Research Says
New studies suggest LLMs can forecast social-science and neuroscience results. Here's what that actually means for knowledge work — and what it doesn't.
· 5 min read
LLMs Beat Experts at Predicting Study Results. Now What?
A study found LLMs can forecast experiment outcomes better than human specialists. We unpack what that really proves — and how to use it without fooling yourself.
· 4 min read
Project Memory: The Missing Layer in AI Assistants
A bigger context window won't fix a forgetful assistant. Persistent, structured project memory is what turns chat toys into long-running collaborators.
· 4 min read
Automating Inbox Triage With Agents: What Actually Works
A field-tested breakdown of which inbox tasks AI agents handle reliably today, and where human review still isn't optional.
· 4 min read
Most AI Agents Are Demos. Here's What Real Ones Do.
A field guide to separating agents that actually finish work from the reasoning-superhero hype — and the boring, bounded jobs they quietly win at.
· 4 min read
Picking the Right Model per Task: A Router's Playbook
Stop chasing one 'best' model. Route each task — drafting, summarizing, spreadsheet reasoning, coding — to whichever model wins on quality-per-dollar.
· 5 min read
AI Agent Identity: Why Your Bot Needs Its Own Credentials
Borrowing a human's login is a security disaster waiting to happen. Here's why AI agents deserve their own scoped, revocable, auditable identities.
Get started
Reserve your @tamaton.ai email
Claim your address before someone else does — free to start, with an AI-native inbox built in.