Blog

Page 4 of 10.

Three lanes with different rules, and agent mail sitting in the third

3 August 2026 · 4 min read

Transactional, marketing, conversational: which one is your agent sending

The three categories have different infrastructure, different rules, and different consequences for mixing them. Where agent mail sits, and why sending it through a campaign tool goes wrong.

Several tool servers feeding one agent that holds an inbox

3 August 2026 · 4 min read

Every tool you connect is a tool your inbox can be talked into using

An agent with an inbox and a dozen connected tools has a supply chain. What a hostile or compromised server can do, why email raises the stakes, and how to connect one safely.

One conversation kept under one subject rather than split across three

3 August 2026 · 4 min read

Subject lines an agent should write, and the ones it should leave alone

The subject is the one line that decides whether anything else gets read, and the one field agents most often break. When to keep it, when to write it, and what makes a good one.

The easy half handled, leaving a smaller and harder pile

3 August 2026 · 5 min read

What your team does once the agent handles the easy half

An agent changes the shape of the work rather than the amount, and the leftover pile is harder than the average was. How roles, staffing levels, and hiring change, honestly.

Two response paths from one inbox, with very different clocks

3 August 2026 · 4 min read

Setting response time targets you can actually keep

An agent answers in seconds, which makes it tempting to promise something you cannot hold when it escalates. How to set targets per category, measure the tail, and design the fallback.

A hosted client authorising against a workspace rather than holding a key

3 August 2026 · 4 min read

Connecting a hosted client that cannot hold a key

Some clients cannot store an API key, so they authorize as you instead. How the OAuth flow works, what the scopes cover, why a token needs an agent header, and when to prefer a key.

A Node service receiving a webhook, queueing, and replying

3 August 2026 · 4 min read

Running an email agent on ordinary Node infrastructure

Not everything runs on the edge. The same agent as a Node service: webhook endpoint, a queue, per-thread locking in Postgres, and the deployment details that decide whether it survives a burst.

Nine separate messages beside one that carries the same information

3 August 2026 · 4 min read

When an agent should send one email instead of nine

Agents can send a message per event, and usually should not. How to decide between immediate, batched, and digest delivery, and how to implement the batching without losing urgency.

Portal inquiries arriving in a burst and being answered in minutes

3 August 2026 · 4 min read

Answering property inquiries before the lead goes cold

Portal inquiries arrive in bursts and decay in hours. How an agent answers the same six questions, books viewings, and hands over the moment a conversation becomes a negotiation.

Event mail arriving quietly for weeks, then all at once

3 August 2026 · 4 min read

Running an event's inbox without a spreadsheet

Registrations, dietary requirements, transfers, cancellations, and the flood of questions in the last 48 hours. What an agent handles, what it must not decide, and how to survive the week of the event.

A client thread moving through update, approval, and chase without a person

3 August 2026 · 4 min read

Keeping clients informed without a weekly status meeting

Agencies lose hours to status emails, chasing approvals, and collecting assets. An agent can run all three, provided it never negotiates scope or speaks for the team on judgement calls.

The bottom of an agent's message doing three jobs in three lines

3 August 2026 · 4 min read

What goes at the bottom of an agent's email

The signature is where disclosure, the route to a human, and your legal obligations live. What belongs there, what does not, and why an agent's footer differs from a person's.