Blog

Practical notes on building, operating, and improving AI agents for real teams.

Hivy journal001
Agents7 min read
AgentsJuly 18, 20267 min read

The right model for every agent is rarely the biggest one

A practical way to match model cost, context, speed, and reasoning depth to the work an agent actually does.

Read post

Latest posts

9 stories
Hivy journal002
Request from #support
Assigned to Support agent
Answer returned to the thread
Agents6 min read
AgentsJuly 14, 20266 min read

From a Slack mention to finished work, without losing the thread

How channel routing, shared context, and durable sessions turn everyday messages into reliable agent work.

Hivy journal003
Agents8 min read
AgentsJuly 9, 20268 min read

Give an agent enough access to finish the job, and nothing more

A team-first approach to connections, knowledge, skills, and the permissions agents inherit at runtime.

Hivy journal004
Knowledge5 min read
KnowledgeJuly 3, 20265 min read

Search company knowledge before reaching for another API call

Why agents should begin with indexed company context, then use live provider tools only when the work needs them.

Hivy journal005
Engineering9 min read
EngineeringJune 26, 20269 min read

Every automation should leave behind a session you can inspect

Triggers are only the start. The useful record is the request, reasoning, tool calls, result, cost, and follow-up in one place.

Hivy journal006
Engineering6 min read
EngineeringJune 19, 20266 min read

Let agents use secrets without teaching them to reveal secrets

Environment variables can stay opaque while programs still receive the credentials they need inside a sandbox.

Hivy journal007
Request from #support
Assigned to Support agent
Answer returned to the thread
Knowledge7 min read
KnowledgeJune 12, 20267 min read

Agent memory works better when part of it looks like a database

Sheets give teams a shared, inspectable place for records that need to survive a chat and change over time.

Hivy journal008
Engineering10 min read
EngineeringJune 5, 202610 min read

The quiet economics of ending idle sandboxes quickly

Small runtime decisions compound across thousands of agent sessions. Here is how we think about the idle tail.

Hivy journal009
Agents5 min read
AgentsMay 28, 20265 min read

A good agent handoff answers three questions before work starts

Who owns the request, what context travels with it, and where the answer returns determine whether the workflow holds together.

Hivy journal010
Agents11 min read
AgentsMay 21, 202611 min read

What changes when you operate AI agents as a team resource

The unit of management shifts from isolated chats to shared agents, capabilities, knowledge, and observable runs.

Put the ideas to work

Give your team agents that can finish the job.