
Hardening Prompt Caches and SSE Streams for Coding Agents
TL;DR: Anthropic SSE Keep-Alives: We updated the model proxy to inject keep-alive pings during...
Tag archive

TL;DR: Anthropic SSE Keep-Alives: We updated the model proxy to inject keep-alive pings during...
An AI agent repeats actions after Kubernetes pod restart when completed steps live only in memory. Log each action to a durable ledger before running it.
Cline fixed a runaway agent that fired 2,100+ API calls, broken compaction, and wrong-directory file reads — then shipped a major SDK migration. Here's what went wrong and why it matters for every coding agent user.

A financially motivated attacker ran reconnaissance, exploitation, and cleanup with almost no human...
We ran an OpenAI API probe on three tool-misuse faults an order agent hits (schema drift, rate limits, fake-success replies) and recorded the recovery.
Voice agents treat the transcript as ground truth. The speech recognizer often tells you it...
We gave an AI agent an order-processing job, broke its storage mid-task on purpose, and recorded what happened. 8 runs, all on the record.

We were proud of the transfer. It worked on the first try, the call reconnected cleanly, nothing...

Here is the uncomfortable thing about the last two weeks in AI. The models did not get dumber. By...

The industry has converged on a definition of "operator-ready" that is measurable, deployable, and...
Congrats to the Hermes Agent Challenge Winners! The bar for what a solo developer can...
Salesforce shipped roughly 20,000 Agentforce deployments and found 90% of agent work happens after launch. Here is what that means for a solo builder running a small agent fleet.