· 5 min read
Prompt Injection Lives in Your Attachments, Not Your Chat
The real attack surface for AI agents isn't a clever chat jailbreak — it's the forwarded email, shared sheet, or PDF your agent reads with your permissions.
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
Build a Custom Agent in Tamaton: Inbox Triage in 20 Minutes
A build log for one real Tamaton custom agent that triages the inbox, checks the calendar and docs, drafts replies, and files attachments — plus the three failure modes we fixed.
· 5 min read
The Inbox Is the Real Agent Benchmark
Coding demos are graded by a test suite. Email is graded by your boss, your customer, and your calendar. Here's why the inbox is the hardest honest test of an AI agent.
· 5 min read
Reason, Plan, Act — Then What? Evaluating Agents That Do Work
Reasoning and planning demos are easy. Proving a multi-step agent actually finished the job — correctly, safely, once — is the unsolved part. Here's how to measure it.
· 5 min read
Stop Calling It an Agent: A Working Taxonomy for 2026
"Agent" now means everything from a system prompt to a six-hour autonomous process. Here's a five-tier taxonomy based on autonomy, state, and blast radius — and why most agents on sale are tier one.
· 5 min read
AI Agents Now Need Identity: Credentials for Non-Humans
AI agents aren't human users or dumb service accounts — they're a third identity class. Here's how to issue agent credentials and scope permissions before your inbox pays for it.
· 5 min read
Fine-Tuning vs. In-Context Learning: When to Bother
Most teams reach for fine-tuning when a decent retrieval pipeline and a tight prompt would have been cheaper, faster, and far easier to change tomorrow. Here's how to tell the difference.
· 5 min read
Designing an Inbox an Agent Can Actually Read
Email was built for eyeballs, so agents waste context untangling HTML soup and quoted replies. Here's what an inbox designed for machines looks like — and why the human UI should be just one renderer.
· 4 min read
Most AI Productivity Tools Don't Save Time. Here's the Test.
A defensible framework for measuring whether an AI tool actually returns hours — including verification overhead, context-switching, and the trust tax nobody counts.
· 5 min read
Guardrails Beat Bigger Models: Where Agents Put Things Down
The most reliable multi-step agents aren't the smartest — they're the ones handed structured places to stash state, permissions, and checkpoints. Here's how to build those places.
· 5 min read
RAG Isn't Search: Why Your Retrieval Keeps Lying to You
Most RAG hallucinations aren't model failures — they're retrieval failures. Here's a breakdown of chunking, recency, and permission bugs, plus fixes you can defend in code review.
· 5 min read
Why AI Agents Need Isolation, Not Just Permissions
Permissions decide what an agent may touch. Isolation decides what happens when it gets tricked. Here's how to design agent access like a network DMZ.
Page 1 of 19Older →
Get started
Reserve your @tamaton.ai email
Claim your address before someone else does — free to start, with an AI-native inbox built in.