Skip to main content

Blog

Insights, analysis, and updates from the AI agent economy. Browse by tag.

·tian

The Backpressure Signal Your Inference Provider Refuses to Send

Between 200 and 429 lies a dead zone where every LLM client overshoots in lockstep. The missing load-pressure header is a protocol gap, not a client-side bug.

llm-infrastructure
backpressure
rate-limiting
agent-fleets
+1
·tian

The Branch State Your Coding Agent Forgot to Check

Coding agents reason against a snapshot of git state that goes stale silently. Worktrees, turn-preludes, branch pinning, and snapshot-and-restore turn that silent drift into a loud signal.

insider
coding-agents
git
agent-harness
+2
·tian

The Browser Selector Your Agent Memorized

Computer-use agents that memorize CSS paths are signing up for silent failure. A look at selector decay, semantic anchors, vision-grounded fallback, and why a stored selector is a bet on a rendering decision the agent does not control.

ai-agents
browser-automation
computer-use
web-scraping
·tian

The Chunk Boundary That Bisected the Sentence Your Answer Depended On

Fixed-size token chunking cuts critical clauses in half, and neither fragment retrieves alone. A look at why the failure is invisible to standard evals and which chunking strategies actually close the gap.

insider
rag
retrieval
chunking
+2
·tian

The Coding Agent That Passes Locally and Fails in CI

Coding agents inherit your laptop's warm environment and ship diffs that pass locally then fail in CI. The fix is a repo-level environment contract, a pre-flight parity check, and grading on dev-vs-CI divergence.

insider
ai-engineering
coding-agents
ci-cd
+1
·tian

The Conversation Tree Your Server Stored As A Log

Chat UIs let users edit and regenerate messages while backends quietly append every revision to a linear log — so the model answers the conversation the user thought they took back.

insider
ai-agents
chat-ui
context-engineering
+1
·tian

The Customer Who Cancelled Because Your Agent Was Too Confident

Overconfident AI agents do not lose renewals at the survey — they lose them six weeks later at the renewal call. Treating confidence display as a versioned product surface, not a stylistic accident.

ai-product
trust-calibration
churn
confidence
·tian

The Demo You Recorded in March Was the Last Time It Worked

Recorded sales demos become liability surfaces as model snapshots, prompts, tool catalogs, and retrieval substrates drift underneath them. A demo manifest plus a nightly eval suite turns recordings into testable behavioral commitments.

insider
llmops
model-drift
sales-engineering
+1
·tian

The Eval Set That Started Leaking Into Your Prompt

How few-shot retrieval and a shared CSV quietly turn a careful eval bank into the in-context examples you serve — and the storage-layer separation that stops it.

insider
llm-evaluation
prompt-engineering
mlops
+2
·tian

The Finish Reason Your Code Never Inspects

Every inference API returns a stop signal alongside the text. Ignoring it is the same shape of bug as ignoring HTTP status codes — and your dashboard cannot see the failures it causes.

llm
observability
api-design
reliability
·tian

The Free Trial That Burned Your Quarterly Inference Budget in Eleven Hours

Trial caps sized for human attention break the moment a programmatic signup points an agent at the endpoint. A field guide to redesigning quotas, detection, and exhaustion UX for the population actually signing up.

insider
ai-cost
pricing
free-trial
+2
·tian

The Hot-Reload Loop Your Coding Agent Polluted

When coding agents write faster than your dev server's watcher debounce, the HMR overlay becomes a self-exciting oscillator that the agent reads back into its own reasoning.

coding-agents
dev-tooling
hmr
file-watchers
+1
Showing 337–348 of 2314 posts
Prev29 / 193Next