#support-agents
Every post tagged "support-agents".
13 posts · showing 1–10
-
Your Support Agent Still Remembers the Customer Who Was Furious in March. Decide What Memory Expires Before You Decide What It Stores.
Cross-session memory fails less often from forgetting than from remembering too long. A four-class expiry scheme for support agents, and the one field every stored memory needs.
-
The Refund Tool Capped Each Refund at $500. The Support Agent Issued Eleven $490 Refunds to One Customer.
A per-call limit only answers "is this action too big?" Agents fail on a different question: "is this sequence too big?" Here is how a guardrail that never fired still let the money leave, and the ledger check that would have stopped it.
-
The Refund Tool Timed Out, the Agent Retried, and the Customer Got Paid Twice. Make Every Write Tool Idempotent.
A timeout tells the agent nothing about whether the write happened, and a retry is its most reasonable next move. The fix belongs in the tool, not in the prompt.
-
Summarising the Conversation Threw Away the One ID the Next Tool Call Needed. Summarise Prose, Never Identifiers.
Context compaction reads fine to a human and breaks the agent anyway: the summary kept the story and lost the order number. The fix is to stop asking a summariser to carry identifiers at all.
-
A Two-Line Prompt Diff Is a Behavior Change. Here's the Regression Check It Needs.
A prompt edit has the blast radius of a code change and none of the safety rails — no compiler, no type error, no failing test. Six checks that turn a forty-second approval into a real regression gate.
-
A 5% Canary Mostly Samples Your Easy Tasks. Roll Agent Upgrades Out by Task Class.
Random traffic slices sample volume, but an agent's risk lives in the thin tail of long, tool-heavy, irreversible tasks. Here's how to build a rollout ladder that samples the danger instead.
-
When the Context Window Fills, Cut in This Order — and Leave a Stub Behind
Most agents evict context by dropping the oldest tokens, which reliably deletes the nine words that mattered while keeping a 4,000-token HTML dump nobody needs. Here is the order to cut in, and why every eviction should leave a stub behind.
-
Let the Model Pick the Transition, Not the Tool
A returns agent that can issue a refund before it has checked eligibility will eventually do exactly that, and no amount of prompt wording reliably stops it. Making the call unavailable is a design decision, not a prompt one.
-
The First Hour of an Agent Incident
Nothing crashed, no alert fired, and a customer just forwarded a policy answer your support agent invented. The hardest question in the first hour isn't what broke — it's when it started.
-
Was It Retrieval or Reasoning? Diagnosing a Wrong Answer
A day spent rewriting the prompt for a wrong policy answer, when the policy document was never retrieved. Three checks in the right order, and one log field that separates "ignored it" from "never saw it."