#agent-design
Every post tagged "agent-design".
112 posts · showing 91–100
-
The Escalation Path Is Part of the Design
An agent with no defined way to stop will improvise one, and its improvisation is a confident answer. Escalation deserves a tool, a destination, and a metric — and one field that stops the human starting over.
-
Vector Database or Postgres? Choosing Storage for Agent Memory
Most agent memory reads are filtered similarity or plain structured lookup — relational workloads wearing an embedding. Write down your ten most common retrievals before you add a second database.
-
Specialist Agents or Specialist Prompts? The Cheaper Half of Multi-Agent
A separate agent buys separate context, separate permissions, and separate lifecycles. It does not buy expertise — that's what prompts are for, and they cost nothing and lose nothing at the boundary.
-
Where You Put Things in the Context Changes the Answer
Same instructions, same documents, different results — because the constraint sat in the middle of a long array. Two ordering rules, one of which also decides whether your prompt cache ever hits.
-
The Agent That Read Page 1 of 40: Pagination in Tool Design
It reported three overdue invoices. There were sixty-one. The tool worked as documented — which is exactly why this bug is so common and so quiet.
-
Designing for Resumability: Agents That Survive a Restart
Serializing the message array is the obvious approach and it produces subtly wrong resumptions. What has to survive a crash is a work ledger, idempotent side effects, and enough state to rebuild context from scratch.
-
Chatbot, Workflow, or Agent? Pick the Simplest Thing That Works
Six weeks building an agent for a task with three fixed steps. One question — can you draw the flowchart before seeing the input? — separates the three architectures and saves most of that time.
-
One Prompt Per Job Beats One Prompt For All: The Router Pattern
Every new case adds a paragraph, and adherence to all of them drops. Classify first and run a small prompt built for that class — with per-route tools, limits, and approval policy.
-
Where to Put the Approval: Human-in-the-Loop Is a Design, Not a Checkbox
A confirm dialog nobody reads has all the latency of oversight and none of the protection. Four placements, a routing rule based on reversibility, and the metric that tells you your gate has become a rubber stamp.
-
What Belongs in Long-Term Memory (and What's Just Transcript)
Embedding every turn gives you a transcript with a search box, not memory. Three categories deserve to outlive a conversation — and the contradiction problem needs deciding before it arrives, not after.