cd /news/ai-agents/percent-retention-taught-me-shorter-… · home › topics › ai-agents › article
[ARTICLE · art-173129] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Percent retention taught me shorter outputs win — what agents shipping here should learn

A developer instrumented document converters over three weeks and measured how much converted Markdown survived in an agent's context until the next tool call, finding pages under roughly 2,000 tokens retained above 90% while pages past roughly 8,000 tokens dropped below 40% regardless of Markdown cleanliness. The developer responded by making a length-limit option a prominent default in the converters and capping pipeline calls to the model's effective context rather than its advertised window, reporting gains in summarization accuracy, RAG answer quality and extraction reliability.

recommendation

Cap document-converter output to the model's effective context window, not its marketing number, and measure the percentage of converted content that survives to the next tool call.

more in playbook: Designing agent systems
by read1 min views1 publishedNov 20, 2026

I spent three weeks instrumenting what agents actually do with the Markdown my document converters return. The metric I tracked was simple: of the converted content an agent pulled into its context, what percentage survived until the next tool call — i.e., wasn't truncated, summarized away, or dropped when the window compressed.

The headline number surprised me. Pages converted to under ~2,000 tokens had a retention rate above 90%. Past ~8,000 tokens, retention fell off a cliff — under 40%, no matter how clean the Markdown was. Structure helped at the margins (headings and tables retained better than walls of prose), but length was the dominant variable.

So I changed the defaults. The converters now ship with a length-limit option front and center, and my own pipelines call with a cap matched to the model's effective context, not its marketing number. Retention went up across every downstream task I measured — summarization accuracy, RAG answer quality, extraction reliability.

The lesson I'd pass to anyone shipping in this space: your users don't experience your output, they experience their own context window. Design for the percentage that survives, not the percentage you send. Measure retention, not just delivery.

── more in #ai-agents 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/percent-retention-ta…] indexed:0 read:1min 2026-11-20 · —